Ubiquitous Internet of Things refers to the interconnection and interaction of information at any time, any place, anyone, and anything. The ubiquitous power Internet of Things (UPIoT) refers to the application of ubiquitous IoT technology in power systems. Its implementation has the following advantages for power grids: connecting the devices that should have been connected; sharing the data that should have been shared, and the value of data can be used more efficiently. Different from the smart grid, which is designed to build a multienergy integrated network and distributed management intelligent system with intelligent judgment and adaptive adjustment ability, the essence of UPIoT is to realize holistic perception and ubiquitous connection of energy. This paper introduces a technical architecture proposed by China State Grid Corporation, based on which the key communication and information technologies of UPIoT are analyzed in detail from the four elements of UPIoT. The challenges of implementing UPIoT are also introduced.

The traditional power grid is composed of a large quantity of loosely interconnected synchronous AC grids,1 which is required to realize the functions of production, transmission, and distribution of electricity. In the power plant, electricity is generated by burning coal and other fuels, and the generated electric energy is transmitted to the remote load center through the high-voltage transmission line, and the power distribution system reduces the voltage to distribute the electric energy to the end-user. To ensure that the power produced by the power plant matches the needs of the users, the power grid is uniformly controlled and monitored. From 1870 to 1970, the traditional power grid operated well.1 However, with the explosive growth of electronic equipment and the generation of high-power power sources such as electric vehicles (EV), the operation of power grids faces enormous challenges. With the use of inefficient appliances, and the lack of intelligent technology, reliable communication and monitoring, and electricity energy storage mechanisms,2–4 the phenomenon of energy waste in the power grid is very serious.

Smart grid (SG) provides an effective and reliable solution to these challenges. SG has a variety of information and communication technologies that can improve the reliability, security, stability, efficiency, and scalability of the power grid.5 SG uses the real-time electricity price, self-healing (detection failure and recovery), power consumption scheduling, and other methods to maintain the balance between power generation and consumption6 according to the demands of consumers, so that the energy production volume and demand are closely matched.2–4 SG deploys a large number of instruments (reaching hundreds of millions or even billions) in power plants, transmission lines, distribution centers, and customers to monitor, analyze, and control the power grid. Therefore, connecting these devices together and performing distributed monitoring, analysis, and control through high-speed, ubiquitous and two-way digital communication technologies have become the main concerns of SG. IoT is the best way to achieve these functions. IoT technology combines all kinds of sensing devices such as images, audio, video, and positioning. Through the integration of IoT devices, it is possible to realize the monitoring, and control of large-scale scenes by collecting, processing, and transmitting information between objects.7 At present, IoT has been widely used in the positioning and traceability, dispatching command, remote control, decision support, and other aspects of all walks of life.

However, with the reform of the electricity price system, and the development trend of large-scale high-density access to new energy, the power grid is facing three big challenges now. On the one hand, the reliability of social power supply is required to be higher; uncertainty disturbance sources are increasing day by day and the power grid configuration caused by power electronic equipment makes the power grid safe and stable operation under great pressure.8 On the other hand, influenced by the liberalization of the power market, the reduction of electricity transmission and distribution price, and the deceleration of electricity growth, the operation of power grid enterprises has encountered great challenges.9 Besides, the changes in the forms of the social economy such as Internet economy and digital economy have brought great challenges to the traditional power industry. Therefore, in response to this situation, China State Grid Corporation (CSGC) proposed the concept of ubiquitous power Internet of things (UPIoT), arguing that the most urgent and most important task at present is to build UPIoT.9 Subsequently, the concept quickly received responses from a large number of domestic research scholars and various related meetings were held.

CSGC defined UPIoT as “fully applying modern information technologies such as mobile internet and artificial intelligence (AI), and advanced communication technologies to achieve the interconnection and human-computer interaction around all the aspects of the power system, and finally form a smart service system with comprehensive state perception, efficient information processing, and convenient and flexible application.”10 Compared with the existing research on the Internet of Things in the power system, the ubiquitous power Internet of Things emphasizes the ubiquitous connection, the sharing of data, platform services, and intelligent terminal.

There are four aspects between UPIoT and existing research on the applications of IoT technologies in power systems.

First, compared to existing research on the applications of IoT technologies in power systems, the ubiquitous power Internet of Things proposed by the State Grid is more systematic. CSGC regards UPIoT as a strategic technology that is as important as the smart grid. It has specific directions and objectives, not just the application of IoT in small subareas of the power system.

Second, they have different backgrounds. As analyzed in the third paragraph of the manuscript, UPIoT is proposed in this context: with the reform of the electricity price system, and the development trend of large-scale high-density access to new energy, the power grid is facing three big challenges now. On the one hand, the reliability of social power supply is required to be higher; uncertainty disturbance sources are increasing day by day and the power grid configuration caused by power electronic equipment makes the power grid safe and stable operation under great pressure. On the other hand, influenced by the liberalization of the power market, the reduction of electricity transmission and distribution price, and the deceleration of electricity growth, the operation of power grid enterprises has encountered great challenges. Besides, the changes in the forms of the social economy such as Internet economy and digital economy have brought great challenges to the traditional power industry.

Third, the problems they can solve are different. UPIoT can solve the following four challenges:

  • Enterprise operation: the barriers between disciplines and specialties are prominent, so the data are not effectively connected and shared. There is a big gap with the goal that all kinds of collected data can be used everywhere once acquired. The cross-professional process is not coherent, the goal is not coordinated, and the operation is not standardized. The participation and satisfaction in the process of customer-friendly electricity consumption and supply demand interaction need to be improved.

  • Power grid operation: the data are incoherent; the real-time sharing is not good enough; the value of data in improving the safe operation level, efficiency of power grids, and the quality of work are not fully played, and no obvious effect has been achieved. The capacity of large-scale energy optimal allocation is not fully reflected. The lack of a flexible interprovincial clearance trading mechanism for clean energy and the interprovincial barriers are prominent.

  • Emerging business: it has not yet formed a large-scale and systematic development trend; lacking market-oriented management mode and Internet thinking; and difficult to respond quickly to changes in customer needs; weak social resource integration ability, inadequate open and sharing cooperation, and the driving role of the industrial chain is not obvious.

  • Infrastructure: the coverage of terminal acquisition and monitoring is insufficient, lacking unified planning, design, and standards, and failing to achieve unified material link management; the coverage of the communication access network is insufficient; the utilization rate of platform software and hardware resources is not high, the flexibility of data storage, processing, and application is not strong, and the ability of rapid response to demand changes is insufficient.

Fourth, their goals are different. UPIoT develops in the four directions of ubiquity, intelligence, sharing and platform in connection, terminal, data, and service. The ultimate goal is to fully apply modern information technologies such as mobile internet and artificial intelligence, and advanced communication technologies to achieve the interconnection and human-computer interaction around all the aspects of the power system, and go hand in hand with SG to complement each other and finally form a smart service system with comprehensive state perception, efficient information processing, and convenient and flexible application. As Yusheng Xue, a member of the Chinese Academy of Engineering, said, “the convergence of SG and UPIoT will be an indispensable support for energy transformation.”11 

Our research on key technologies of UPIoT-aided SG is different from previous research on IoT, SG, and IoT-aided SG. First, we introduce the concept of UPIoT proposed by China State Grid Corporation. Second, we introduce the communication technology and information technology of UPIoT in detail from the perspective of the framework of UPIoT. There are a large number of attempts in the literature which covered IoT and IoT-aided SG. In this section, we present the previous works on IoT and IoT-aided SG, to justify how we are different from them. Our contributions are also included.

1. Researches on IoT

IoT is defined as a network that connects any object to the Internet for monitoring, tracking, management, and location identification based on the exchange of information and communication protocols between various smart devices.12 In Refs. 13–16, the authors focused on the review, architectures, vision, applications, and challenges of the IoT. In Refs. 17 and 18, the authors argued that social IoT has become a hot topic. The security issue is a big issue that must be considered for IoT applications. In Refs. 19–21, the authors introduced the threats of various aspects of IoT, and successfully detected various DDoS/DoS attacks with a neural network method with an accuracy of 99.4%. In Refs. 22–24, the authors summarized the standardization of the IoT. Besides, some scholars have studied the software-defined network (SDN) of IoT,25 data mining,26 uplink scheduling of LTE (Long Term Evolution),27 and context-aware computing.28 

2. Reviews on IoT-aided SG

In today's energy ecosystem management system, IoT has a huge impact on the development of SG.29 The deployment of IoT in SG has several advantages:

  • Enhance reliability, flexibility, adaptability, and energy efficiency;30 

  • reduce the number of communication protocols;31 

  • improve control of household appliances;32 

  • achieve on-demand information access and end-to-end service provision;32 

  • enhance scalability and interoperability.33 

There are some articles about the combination of SG and IoT. Figure 1 shows a complete understanding of the SG with the help of IoT in the future. In Ref. 34, the author introduced the application of IoT in SG and briefly outlines opportunities, challenges, and future directions. However, the author did not analyze the related technologies of IoT-aided SG systems. In Ref. 35, the author focused on the application of IoT in power and energy systems from the value and importance of IoT in the power grid, and evaluated the role, impact, and challenges of IoT in transforming power and energy systems. The survey36 analyzes how IoT can assist SG, including the existing architecture, applications, and prototypes of the IoT-assisted SG system. Besides, the authors highlight the unresolved issues, challenges, and future research directions of the IoT-aided SG system. In Refs. 37 and 38, the authors analyzed the security of the Internet of Things-assisted SG. In Ref. 38, the author proposed a software-defined network (SDN), network behavior analysis (NBA), deep learning model, and deep packet inspection (DPI) attack confirmation. A conceptual security monitoring framework for a concept forensics-driven security monitoring framework is also included.

FIG. 1.

Future smart grid with the help of IoT.29 Reproduced with permission from S. S. Reka and T. Dragicevic, Renewable Sustainable Energy Rev. 91, 90–108 (2018). Copyright 2019 Elsevier B.V.

FIG. 1.

Future smart grid with the help of IoT.29 Reproduced with permission from S. S. Reka and T. Dragicevic, Renewable Sustainable Energy Rev. 91, 90–108 (2018). Copyright 2019 Elsevier B.V.

Close modal

There are some existing applications of IoT-aided SG systems such as electric vehicle information management system, demand-side management, smart distribution, advanced metering infrastructure (AMI), online monitoring of power transmission, etc.36 In the rest of this section, we describe the existing applications of IoT-aided SG systems.

a. Electric vehicle information management system

The charging system of an electric vehicle is composed of a power supply system, a charging device, and a monitoring system. The power supply system is responsible for the output and management of electricity. The charging device contains AC and DC chargers that charge and discharge the electric vehicle. AC chargers charge at a slower rate, while DC charging is much faster than AC. The monitoring system is responsible for monitoring the charging system in real-time to ensure its safe operation. The entire monitoring system is supported by IoT, which enables the power supply and real-time monitoring system to transmit information to the control station, so that a GPS-equipped electric vehicle can locate the nearest suitable charging station for charging. A large number of electric vehicles will have a huge impact on the distribution network after they are put into operation.39,40 The mobility and energy storage characteristics of electric vehicles bring great opportunities for the realization of new energy sources41,42 and load management43 during peak and trough periods on the load side. Of course, they are inseparable from IoT technology.

b. Demand side management (DSM)

DSM programs are composed of conservation and energy efficiency programs, fuel substitution programs, demand response programs, and residential or commercial load management programs.44 The objectives of residential or commercial load management programs are to reduce or shift consumption (by guiding users to use less electricity during peak power demand periods and to use more electricity during low valleys).45 It aims to minimize the cost of consumers, reduce the operating costs and energy losses of the power grid, and shift the peak load to the trough; thus, the stable operation of the power grid can be ensured.46 IoT devices collect energy requirements for various household appliances and transmit them to the home control unit. The control unit then adjusts the energy consumption of the home appliance based on the user's preferences. The home energy management system (HEMS) is one of the best applications for DSM. In Ref. 47, the author outlines the information and communication technologies required for HEMS and load scheduling techniques. Similarly, in Ref. 48, Hussain Sharee et al. also reviewed the research related to HEMS and introduced the application of artificial intelligence in load scheduling.

c. Smart distribution

Smart distribution technology is one of the largest applications of IoT in the power grid. It is based on the traditional transmission and distribution system, combining modern power technology, modern measurement and control technology, computer technology, communication technology, and power electronics technology.49 The intelligent distribution has the following advantages:50 (1) strong interaction ability and support for interaction with users. (2) Strong self-healing ability. (3) High power quality and system reliability. (4) Good compatibility and support of a large amount of access to distributed energy. (5) Higher asset utilization. With IoT technology, smart distribution can identify and resolve failures. At present, some smart distribution projects have been launched, for example, the Henan Hebi IoT Demonstration Project in Hebi, China.51 

d. Advanced metering infrastructure (AMI)

Traditionally, utility companies have manually collected power consumption information at the site at specific time intervals. This method is not only inconvenient, but also time-consuming and labor-intensive. These issues can be addressed by the technology of AMI. AMI is a complete network and system for measuring, collecting, storing, analyzing, and using user's electricity information. It is composed of a smart meter installed in the customer, a measurement data management system located in the power company, and a communication system connecting them. A typical smart metering system is composed of metering and communication infrastructures. The communication infrastructures include network, home area network (HAN), wide area network (WAN), and control infrastructure. Metering infrastructures consist of time of use pricing, data management system, and advanced meter reading. With the help of IoT technology, AMI enables two-way communication between consumers and utility companies because AMI cannot only measure energy consumption information, but also transmit energy and electricity price information of utility companies to consumers,52 so that consumers can adjust their power needs.

e. Online monitoring of power transmission lines

The power transmission line is one of the important components of the power grid. Therefore, its normal operation is one of the important conditions for ensuring safe and stable operation of the power system. On-line monitoring of transmission lines is one of the important technologies for transmission line protection and diagnosis.53 Factors affecting the safety of transmission lines include extreme weather, the surrounding environment (such as temperature), and man-made damage. Therefore, the transmission system needs to have the ability to quickly handle faults to ensure the reliability of the power grid. Based on online monitoring, we can quickly locate the fault and fix it. Wireless sensor networks are characterized by low cost, easy installation, and large-scale coverage. They are an important and promising technology for online monitoring of power transmission lines. The sensors are mainly installed in the transmission line between the transmission towers (monitoring the state of the transmission lines) and the transmission towers (monitoring the status and environmental parameters of the transmission towers), and the communication between them is realized by IoT.

3. Novelty and contributions

We have presented the surveys on IoT and IoT-aided SG; however, as presented above and to the best of our knowledge, none of the above attempts have introduced the concept of UPIoT proposed by China State Grid Corporation, technology architecture, and related technologies. Our effort and intention are to provide a survey that covers the concept, architecture, related technologies, and challenges for UPIoT.

The contributions of this article are as follows:

  • An overview of the application of IoT in SG;

  • an introduction of the concepts and characteristics of UPIoT;

  • a detailed introduction to the technologies required for UPIoT, combined with current advanced information and communication technologies;

  • descriptions of some challenges of UPIoT.

The rest of this paper is organized as follows: the second part briefly introduces the concept and characteristics of UPIoT. The third section describes key communication technologies and information technologies in detail. The fourth part analyzes the technical challenges of UPIoT. The conclusions of this paper are included in the last section.

UPIoT refers to the interconnection and interaction of their respective devices and people between power generation companies, power electric power companies, suppliers, and power users, that is, the “ubiquity” of information and data. It can be interpreted from three aspects: “ubiquitous network,” “power network,” and “Internet of Things”:54 Internet of Things is a concrete manifestation of UPIoT. “Power network” is a specific application object of Internet of Things technology; the ubiquitous network describes the basic characteristics of the future UPIoT systems, that is, smooth communication can be achieved at any time, any place, and anything.

With the help of modern information technologies such as mobile internet and artificial intelligence and advanced communication technologies, UPIoT can realize the physical interconnection, information interconnection, and commercial interconnection of different energy systems. It features holistic perception, ubiquitous connectivity, open sharing, and integration innovation.

  • Holistic perception: operational status and environmental information from power plants, distribution networks, load side, and energy storage equipment are acquired dynamically by using a variety of sensing technologies, such as sensors and radio frequency identification (RFID).

  • Ubiquitous connectivity: the use of proprietary networks or mobile IoT technology to realize full space-time connection of related information and data of equipment of the power system and users, that is, the realization of information transmission everywhere and all the time.

  • Integration and innovation: massive data are transmitted to a unified platform through communication technology for sharing and unified management, realizing real-time interaction of data, making data truly effective, and exploiting its maximum value.

  • Opening and sharing: through the creative integration of various innovative elements, the information in different times and space of different equipment and users can be interconnected. Thus, the whole business can be realized online, the power grid can be safely and stably operated, the intelligent integrated energy service platform can be built, the power market can be developed, and the transformation of the power grid can be promoted.

The hierarchical structure (three or four layers) is a very common structure in the IoT architecture,55 such as the sensing layer, the network layer, and the application layer. The sensing layer deploys various IoT smart devices to monitor device status. The network layer collects device information through various communication technologies and connected smart devices, and then IoT collects information about devices with the help of various communication technologies and the connected intelligent devices of IoT. The application layer controls the SG56 through the application interface. In Ref. 57, the author proposed the “terminal-field network-remote communication-master station system layer” architecture based on the characteristics of SG and communication system. The terminal and the field network correspond to the sensing layer in the three-layer architecture, the remote communication corresponds to the network layer, and the master station system layer corresponds to the application layer. However, these architectures only consider the individual characteristics of IoT or SG, and are not scalable, so they are not suitable for large-scale deployment.58 In Ref. 59, CSGC proposed the architecture of “sensing layer-network layer-platform layer-application layer” from the four elements of UPIoT (namely, the acquisition of terminal equipment information and the intelligence of terminal devices, data transmission, integration, and analysis of data, and application of information). At present, it is recognized by many research scholars.60,61 as shown in Fig. 2. To the best of my knowledge, there is no other architecture for UPIoT, that is, it is the first ever architecture proposed for UPIoT. In fact, the architecture UPIoT is proposed based on the architecture sensing layer-network layer-application layer for Internet of Things.62 Compared with the architecture for Internet of Things, “platform layer” was added to the architecture for UPIoT to realize the “Integrated” cloud platform, the unified data center for all business, and other functions, and finally realize the ultimate goal of forming a smart service system with comprehensive state perception, efficient information processing, and convenient and flexible application.

FIG. 2.

The technical architecture of UPIoT. The architecture contains four layers: sensing layer, network layer, platform layer, and application layer. The sensing layer includes various information sensing devices (such as sensors, RFID, video devices, and so on) and intelligent sensing systems in the area of SG. The network layer mainly contains various networks and their transmission devices. The platform layer consists of the advanced information technology (such as big data, artificial intelligence, and so on). The application layer mainly includes customer service, enterprise operation, power grid operation, and emerging business.

FIG. 2.

The technical architecture of UPIoT. The architecture contains four layers: sensing layer, network layer, platform layer, and application layer. The sensing layer includes various information sensing devices (such as sensors, RFID, video devices, and so on) and intelligent sensing systems in the area of SG. The network layer mainly contains various networks and their transmission devices. The platform layer consists of the advanced information technology (such as big data, artificial intelligence, and so on). The application layer mainly includes customer service, enterprise operation, power grid operation, and emerging business.

Close modal

Sensing layer: in the sensing layer, real-time collection and local signal processing of terminal information (including physical quantity, state quantity, electrical quantity, environmental quantity, electrical quantity, etc.) can be realized by using cognitive and recognition technologies such as smart chips and smart sensors and so on. Besides, edge computing can be used to process some regional computing tasks at the gateway, to reduce the computational pressure of the platform layer server cluster,63 or to perform edge calculation locally, to achieve intelligent terminal devices and complete local automation.64 

There are three requirements for the perception layer. The first one is the realization of standardization and unified access for terminals. The term “standardization” exactly refers to the standardization of the operating system. The second one is sharing of resources such as communication and computing. The third one is the realization of data fusion and edge intelligence at the source end to reduce the pressure to the server cluster. Using edge computing to process some regional computing tasks at the gateway is a good way to reduce the computational pressure of the platform layer server cluster.

Network layer: the network layer uses the existing Internet, mobile communication network, satellite communication network, and other basic network facilities to achieve full coverage of power in all aspects of “generation-transmission-distribution-consumption.” The information of the sensing layer is accessed and transmitted at the network layer.65 

There are no specific requirements for the network layer because the network layer has clear specifications regardless of the communication protocol. Transmission methods are divided into wired and wireless, a total of more than a dozen. The most commonly used wired ways include RS485 and power line carrier communication, and wireless includes ZigBee, LoRa, Narrowband IoT (NB-IoT), and LTE. They are likely to be used in the Ubiquitous Internet of Things. The specific form of transmission needs to be selected according to the distance, function, and power consumption requirements of the device and the platform or gateway.

Platform layer: in the platform layer, the data processing capability and the synergy capability of the cloud computing (CC) and edge computing can be greatly improved with the help of the IoT management center and the data center.66 Massive information resources can be integrated into a large interoperable network through computing ability,67 to solve the problems of data storage, retrieval, using mining, and security privacy protection.68 In this way, all kinds of collected data can be used everywhere once acquired.

Application layer: after the platform layer sends the information to the application layer, the application layer processes the received information and makes a decision. The application layer feeds back the decision information to the platform layer and the network layer to control the terminal device of the sensing layer. In this way, the application layer can realize state monitoring,69 fault self-healing,70 asset evaluation, etc., to promote the safe and stable operation of the power grid, and build a smart integrated energy Internet.

Compared with smart grids, UPIoT is more concerned with data interconnection and information sharing between different devices. In essence, the elements of UPIoT can be divided into four parts: terminal device data collection and terminal intelligence, data transmission, data integration and analysis, and information application. In this section, we will introduce the key technologies of UPIoT in detail based on the analysis of the second part.

With the continuous access of power equipment, the types, quantities, and ranges of sensing objects will be greatly expanded, and the requirements for volume, energy consumption, and performance of sensing devices will also continue to increase. The smart chip can make the terminal intelligent through edge computing. Chip technology can be widely used in power transmission, substation, distribution, and electricity sales. It is used in large-area applications of control devices and security modules, so that the physical data, state data, environmental data, electrical data, and other information of the power grid equipment can be obtained in real-time, quickly and safely, and processed locally. In the future, sensing technology will continue to develop in the direction of miniaturization, integration, high security, and anti-interference.

Smart sensors communicate bidirectionally with external systems for acquiring, processing, and exchanging information, and receiving and processing external commands. In addition, smart sensors have the function of self-calibration, self-compensation, and self-diagnosis.71,72 Compared with general sensors, smart sensors have the following three advantages: (1) high-precision information acquisition can be achieved through software technology and at low cost, (2) be provided with certain programming automation capabilities and (3) functional diversification. Therefore, smart sensors have been widely used in power systems. In Ref. 73, the author introduced the application, opportunities, and challenges of wireless sensors in SG. Another survey74 has focused on the role of wireless sensor networks in energy efficiency in residential energy management. A high-speed sensor that is used as a synchronous phasor or phasor measurement unit (PMU) can be used to simultaneously measure the real-time phasors of voltage and current to achieve monitoring, protection, and control of the power system.75 

Radio frequency identification (RFID) is a wireless communication technology that can identify specific targets by radio signals without mechanical or optical contact (i.e., noncontact identification) between the system and a specific target, i.e., noncontact identification. RFID has three functions of monitoring, tracking, and supervision.76 RFID can work in a variety of harsh environments and has the advantages of fast recognition speed, large data capacity, long service life, and dynamic real-time communication.77 In Ref. 78, the author analyzed the application and challenges of RFID in IoT.

Advanced communication technology is an important part of the development of UPIoT. The communication services in the power system are divided into three types of services: power grid terminal control, information collection, and mobile application. As shown in Fig. 3, different communication services will have different communication requirements. These requirements are briefly described below.

FIG. 3.

Types of communication services. The communication services in the power system are divided into three types of services: power grid terminal control, information collection, and mobile application. Different communication services will have different communication requirements (such as reliability, rate, and so on). The methods of communication consist of three categories: IoT-Wireless Technologies, Non-IoT Wireless Technologies, and Non-IoT Wired Technologies.

FIG. 3.

Types of communication services. The communication services in the power system are divided into three types of services: power grid terminal control, information collection, and mobile application. Different communication services will have different communication requirements (such as reliability, rate, and so on). The methods of communication consist of three categories: IoT-Wireless Technologies, Non-IoT Wireless Technologies, and Non-IoT Wired Technologies.

Close modal

Latency: the latency requirements are different for different applications. Some key technologies require fast information transfer with strict latency constraints, such as distribution automation in the substation (within 4 ms). For applications that are as high as some latency requirements, higher network latency can be tolerated, such as smart meters in AMI (sending their readings every 15 min).

Data rate: different applications in the SG will have different data rate requirements. Some applications for transmitting video and audio data require high data rates to transmit information, such as situational awareness systems. The bandwidth used by smart meters, PMUs, etc., is between 10 kbps and 100 kbps.79 

Reliability: communication reliability is a critical important indicator of the power grid. It is an important factor to ensure the stable and reliable operation of the power grid. Network fault is one of the most important factors affecting communication reliability, which will seriously affect the reliability of the power grid. Network failures include many aspects, such as links (node failures), overloads, and so on. Critical applications require very high reliability for data communications and should always ensure continuity of communication, such as distribution automation.

Security: security is the highest priority for SG applications.80 As a key infrastructure, the power grid needs to be able to withstand attacks and failures. Therefore, the communication infrastructure requires strict security requirements in terms of restoring after cyber attacks and protecting customer privacy,81 especially for some critical applications. Authentication, encryption, and intrusion detection are some of the important security mechanisms in the power grid that prevent, detect, and mitigate such network attacks.82 

Scalability: countless devices (such as smart meters, smart sensors, renewable energy, etc.) are involved in SG. Therefore, scalability is a very intuitive requirement in SG communications. Therefore, scalability should be handled through the integration of advanced Web services, reliable protocols, and advanced features such as self-configuration and security.

The methods of communication are divided into three categories: IoT-Wireless Technologies, Non-IoT Wireless Technologies, and Non-IoT Wired Technologies. The three major types of communication technologies will be specifically described below.

1. IoT wireless technologies

a. ZigBee

ZigBee is a wireless communication technology which features low-cost, low-power, low-complexity, and low-data-rate. It is applicable to microgrid,83 home automation,84,85 energy monitoring,86,87 and automatic meter reading88 in SG. ZigBee is considered by the National Institute of Standards and Technology (NIST) to be the most suitable communication technology for home area networks (HAN).89 Many vendors for AMI, such as Itron, Elster, and Landis Gyr, integrate ZigBee with smart meters to control IoT devices in home appliances65 or inform users of real-time energy consumption information.

b. 5G

5G is regarded as the foundation of the development of IoT. It has many advantages, such as large connection density, small end-to-end delay, strong mobility, high peak rate, and so on. It is widely used in distributed monitoring and control,90,91 and plays an important role in the realization of UPIoT. The main types of 5G slices are Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC), and Ultrareliable and Low Latency (uRLLC). Applying different 5G slice (as Table I shows) to different scenarios is the key to realize holistic perception and ubiquitous connection of power systems. In the future, the construction of UPIoT is inseparable from the participation of 5G. For all its advantages, security and privacy issues still need to be addressed.

TABLE I.

Application types of 5G slices.

Scenarios Status monitoring, unmanned inspection, etc. Intelligent charging station/pile, distributed power access, etc. Voice information such as power dispatching and emergency communications Low-latency information such as distributed distribution automation and load control 
Related slice eMBB video slicee mMTC mass access slice mMTC mass access slice mMTC mass access slice 
Scenarios Status monitoring, unmanned inspection, etc. Intelligent charging station/pile, distributed power access, etc. Voice information such as power dispatching and emergency communications Low-latency information such as distributed distribution automation and load control 
Related slice eMBB video slicee mMTC mass access slice mMTC mass access slice mMTC mass access slice 
c. LoRAWAN

LoRAWAN is a low power wide area network (LPWAN) communication technology for wireless battery-powered devices92 in IoT. The coverage range of LPWAN is wide (15 km in urban environments and 2–3 km in suburban environments93), so it is widely used in neighborhood networks (NAN) and wide area networks (WAN). Also, LoRAWAN features mobile and interoperable for secure two-way communication and localization services. The data rates of LoRAWAN range from 0.3 Kbps to 50 Kbps, but in most cases, it will be set to the maximum. The LoRaWAN network server can adjust the radio frequency (RF) output and data rate of each IoT device through the adaptive data rate to increase the network capacity and battery life of IoT devices.92 

d. Z-Wave

Z-Wave is a low-power radio frequency (RF) communication technology. With a data rate of 100 Kbps and a coverage of 30 m, Z-Wave is widely used in home automation.94 It does not interfere with WiFi and other wireless technologies working in the 2.4 GHz band, such as ZigBee. With high scalability, Z-Wave is capable of controlling 232 devices95 and supporting the entire mesh network without using any coordinator.

e. Narrowband IoT

Narrowband IoT (NB-IoT) is a low power cellular technology that provides extensive indoor coverage for thousands of low data rate and low power devices.96 The NB-IoT technology operates primarily in the 900–1800 MHz band and covers a range of up to 35 km for Home Area Networks (HAN) and NAN, such as home automation and AMI.97 Besides, low cost (as low as $5) makes it an excellent choice for large-scale applications in SG.

Table II summarizes the comparison of each IoT Wireless Technologies, including their advantages, disadvantages, and applications.

TABLE II.

Comparison of wireless technologies.

TechnologyMain features and applications
ZigBee Data rate: 50 kbps, coverage range: 10–100 m 
Latency: 15 ms, cost: low 
Advantages: low power usage; low complexity; low deployment cost 
Disadvantages: low data rates; limited energy of battery; low processing capabilities; short-range 
Application areas: energy monitoring; smart lightning; home automation; automatic meter reading 
5G Data rate: up to 20 Gbps, Coverage range: 10–100 m (depending upon cell size) 
Latency: <1 ms, cost: high 
Advantages: low latency; high reliability; high bandwidth; high speed; capability of handling a large number of devices 
Disadvantages: low range; high infrastructure setup cost; security and privacy issues 
Application areas: distributed monitoring and control 
LoRaWAN Data rate: 0.3–50 kbps, Coverage range: 3–8 km (urban), 15–22 km (rural), 15–45 km (flat) 
Latency: average 2 s, Cost: low 
Advantages: low-power; long-range; no interference with different data rates; low cost secure bidirectional communication 
Disadvantages: – 
Application areas: management of operation and equipment; online monitoring of power transmission lines and tower 
Z-Wave Data rate: 9.6–40 kbps, Coverage range: 30 m (indoor) 100 m (outdoor) 
Latency: 100 ms, Cost: low 
Advantages: no interference with other wireless technologies; reliable; low latency; scalable 
Disadvantages: not suitable for NAN and WAN; short-range 
Application areas: home automation 
Narrowband Internet of Things (NB-IoT) Data rate: uplink: <250 kbps, downlink: <230 kbps, coverage range: <35 km 
Latency: <10s, cost: low 
Advantages: ultralow power consumption; low cost; low complexity 
Disadvantages: latency 
Application areas: home automation; AMI 
TechnologyMain features and applications
ZigBee Data rate: 50 kbps, coverage range: 10–100 m 
Latency: 15 ms, cost: low 
Advantages: low power usage; low complexity; low deployment cost 
Disadvantages: low data rates; limited energy of battery; low processing capabilities; short-range 
Application areas: energy monitoring; smart lightning; home automation; automatic meter reading 
5G Data rate: up to 20 Gbps, Coverage range: 10–100 m (depending upon cell size) 
Latency: <1 ms, cost: high 
Advantages: low latency; high reliability; high bandwidth; high speed; capability of handling a large number of devices 
Disadvantages: low range; high infrastructure setup cost; security and privacy issues 
Application areas: distributed monitoring and control 
LoRaWAN Data rate: 0.3–50 kbps, Coverage range: 3–8 km (urban), 15–22 km (rural), 15–45 km (flat) 
Latency: average 2 s, Cost: low 
Advantages: low-power; long-range; no interference with different data rates; low cost secure bidirectional communication 
Disadvantages: – 
Application areas: management of operation and equipment; online monitoring of power transmission lines and tower 
Z-Wave Data rate: 9.6–40 kbps, Coverage range: 30 m (indoor) 100 m (outdoor) 
Latency: 100 ms, Cost: low 
Advantages: no interference with other wireless technologies; reliable; low latency; scalable 
Disadvantages: not suitable for NAN and WAN; short-range 
Application areas: home automation 
Narrowband Internet of Things (NB-IoT) Data rate: uplink: <250 kbps, downlink: <230 kbps, coverage range: <35 km 
Latency: <10s, cost: low 
Advantages: ultralow power consumption; low cost; low complexity 
Disadvantages: latency 
Application areas: home automation; AMI 

2. Non-IoT wireless technologies

a. Wireless mesh

A wireless mesh network is a flexible network of nodes, where new nodes can join the group and each node acts as a standalone router. The high scalability, self-organization, and self-healing properties of this topology greatly improve the reliability of the network, which can improve network performance, balance network load, and expand network coverage.98 The wireless mesh can achieve wide coverage (both urban and suburban areas) and large capacity because of the multihop routing technique. However, the density of smart meters is not sufficient to cover the entire communication network, so wireless mesh networks are difficult to implement in rural areas, which once again illustrates the importance of achieving UPIoT.

b. Power wireless broadband private network (PWBPN)

Power wireless broadband private network (PWBPN) is designed based on the dedicated frequency band, which can provide ubiquitous, reliable, efficient, and secure access for the transmission and distribution of the power grid. The technical advantage of PWBPN is that it can coordinate various service requirements, build a unified access platform that the terminal services can be accessed flexibly, efficiently, and quickly. Therefore, PWBPN features expanding the end devices, improving the access capability of power grid service, ensuring the transmission quality, and enhancing the service security.

c. Beidou satellite navigation system

The Beidou satellite navigation system is a technology of Chinese independent innovation and has now achieved regional coverage including the entire territory of China. In the aspects of power generation, transmission, substation, and power distribution, the Beidou satellite navigation system can be used for high-precision positioning,99 short message communication, and high precise-time78 to meet the requirements of precise positioning of power equipment and collection of power information in remote areas. In this manner, the management level, ubiquitous connectivity, and synchronization reliability can be improved. Based on the Beidou satellite navigation system technology, a menu-based service for the power industry has been developed.100 These services consist of four parts: (1) online monitoring of power assets; (2) precise running time service module; (3) data of remote monitoring and management of power sales and operation; (4) personnel safety for operation and maintenance and emergency communication module.

3. Non-IoT wired technologies

a. Fiber-optic communication

Fiber-optic communication features high data rates of up to 40 Gbps, ultralow latency, and high reliability. It is often used to connect the backbone of substations and control centers to transmit large amounts of real-time information over long distances, playing an important role in SG. There are three advantages for fiber optic communication: (1) it is capable of transmitting data packets over long distances (approximately several kilometers) up to tens of giga bits per second. (2) It is robust to resist radio and electromagnetic interference, making it an ideal choice for high voltage environments. (3) The combination of the characteristics of optical and ground communication enables optical power ground wire (OPGW) for long distance transmission at high data rates. Therefore, the OPGW can be used to construct transmission and distribution lines.101 However, the deployment of fiber optic equipment and terminal units is costly and they are difficult to update.

b. Power line communication

Power line communication (PLC) reduces the installation cost of communication infrastructure by using existing power lines to transmit high-speed data of approximately 2–3 Mbps from one device to another. The data of the smart meter can be transmitted to the data concentrator via the PLC, and then transmitted to the utility control center using other wireless communication technologies (such as cellular networks) since the smart meter is directly connected to the concentrator.102 The PLC infrastructure covers a wide range of urban areas within the service of utility companies, so it is suitable for SG applications in urban areas. However, due to the harsh signal propagation environment of the PLC and the high noise, and data transmission through the power line may be unreliable.

In the sensing layer, the equipment in the “energy production end-energy delivery end-energy consumption end” has generated amounts of data. These data are difficult to be used efficiently due to different sources, different types, and different lengths. Therefore, it is necessary to establish a unified data platform standard,103 to achieve terminal standardization and unified access of data to improve data quality and real-time sharing.

After the massive data of the power system are transmitted to the integrated data platform of the power system, information technology such as big data, cloud computing, and artificial intelligence can make reasonable analysis and deep mining of these massive data to realize the effective use of power information.

1. Cloud computing (CC)

CC is a computing model that provides on-demand access to configurable resources such as computing, networks, servers, storage, applications, services, and software. CC is divided into three categories, namely, Infrastructure as a Service (Iass), Platform as a Service (Paas), and Software as a Service (Sass).180 Iass means that users can get services from a complete computer infrastructure over the Internet; Paas can provide users with full or partial application development; Sass provides a complete, ready-to-use application.181 In addition, CC can also be classified into the private cloud, public cloud, and hybrid cloud by operation mode, as shown in Table III.

TABLE III.

Classification of cloud computing.

ClassificationTypesDefinitionTypical example
Classification by operation mode Private cloud Often owned by the enterprise or organization, specific cloud service functions are not directly open to the outside world. eBay 
Public cloud Enterprises or institutions use external clouds to serve users outside the enterprise or institution, i.e., enterprises or institutions outsource cloud services to public cloud providers. This can reduce the cost of construct cloud computing facilities. Amazon, Google Apps, Windows Azure 
Hybrid cloud Includes hybrid applications of private and public clouds. Guarantee control over parts such as sensitive data through private clouds while reducing costs through outsourcing. There are few practical applications 
Classification by service mode IaaS Enhanced virtualization capabilities are achieved by providing or managing IT infrastructure for customers. Infrastructure mainly refers to physical resources such as computing, storage, data, and network equipment resources. Amazon S3, SQL Azure Amazon EC2, Zimory, ElasticHosts 
PaaS Provide a platform to support the development of applications and services. The platform mainly refers to the operating system in the cloud computing environment. Force.com, Google App Engine, Windows Azure (Platform) 
SaaS Provide software and application services with specific business functions and processes for customers. Google Docs, Salesforce CRM, SAP Business by Design 
ClassificationTypesDefinitionTypical example
Classification by operation mode Private cloud Often owned by the enterprise or organization, specific cloud service functions are not directly open to the outside world. eBay 
Public cloud Enterprises or institutions use external clouds to serve users outside the enterprise or institution, i.e., enterprises or institutions outsource cloud services to public cloud providers. This can reduce the cost of construct cloud computing facilities. Amazon, Google Apps, Windows Azure 
Hybrid cloud Includes hybrid applications of private and public clouds. Guarantee control over parts such as sensitive data through private clouds while reducing costs through outsourcing. There are few practical applications 
Classification by service mode IaaS Enhanced virtualization capabilities are achieved by providing or managing IT infrastructure for customers. Infrastructure mainly refers to physical resources such as computing, storage, data, and network equipment resources. Amazon S3, SQL Azure Amazon EC2, Zimory, ElasticHosts 
PaaS Provide a platform to support the development of applications and services. The platform mainly refers to the operating system in the cloud computing environment. Force.com, Google App Engine, Windows Azure (Platform) 
SaaS Provide software and application services with specific business functions and processes for customers. Google Docs, Salesforce CRM, SAP Business by Design 

CC provides three deployment models of public cloud, private cloud, and hybrid cloud for implementing SG. The public cloud is the main model of the CC, in which users pay for using the SG service. A private cloud is an on-premises deployment that works like a private network. If a basic private cloud is used in the SG, each SG utility has its own data center and provides its services, ensuring reliability and confidentiality. The private cloud is more secure than the public cloud, but the public cloud has far more computing resources than the private cloud. In this case, the hybrid cloud solves this problem. It features the security of the private cloud to save important internal data in the local data center, and the public cloud computing resources to complete the work more efficiently and efficiently, which is more complete than the private cloud or the public cloud.

The cloud computing system consists of four parts: cloud platform, cloud storage, cloud terminal, and cloud security. The cloud platform is composed of cloud infrastructure, cloud platform components, cloud service center, and cloud security suite. It manages a large number of hardware resources such as central processing unit (CPU), memory, and switches, and integrates one data center or multiple data centers with virtualization technology. At present, there are many applications based on cloud computing services for SG, as shown in Table IV.

TABLE IV.

Some applications of cloud computing in SG.

ApplicationBranchesBrief introductionReferences
Energy management DSM To meet the scalability and economic efficiency of DSM; Cost-oriented optimization model for a cloud-based ICT infrastructure to allocate cloud computing resources in a flexible and cost-efficient way. 104  
  To satisfy the requirements of large-scale real-time computing capabilities to handle the communication and the storage of huge transferable data; Providing a cloud computing framework for a group of smart energy hubs. 105  
  To improve the energy utilization efficiency in a smart community; A cloud-based user-side integrated energy management; A two-level model is proposed that relies on an energy hub and load aggregators. 106  
 Microgrid management A control model with the hierarchical structure based on cloud computing architecture; Resource allocation and management can be realized in an economically efficient manner; Integrating the past and present data to make the collected information more accurate and provides more flexible service for users. 107  
 Dynamic pricing Proposing a real-time dynamic pricing model for electric vehicles charging and discharging service and building energy management, in order to reduce the peak loads; A decentralized cloud computing architecture based on software-defined networking technology and function virtualization. 108  
Information management Information management cloudward Different domains for cost-effective information management cloudward; Propose a cloud-based SG information management model and present a cloud and network resource optimization framework to solve the cost reduction problem in cloud-based SG information storage and computation. 109  
 Cloud-based demand response (CDR) Demand response program based on the distributed optimization model; Solving the problem of the existence of an ideal communication network; Defining a cloud-based demand response (CDR) model which is implemented as a two-tier cloud computing platform. 110  
 State estimation (SE) State estimation (SE); Proposing and validating a Cloud-IoT-based architectural solution for SE in SG that combines cloud capabilities and edge computing advantages and uses virtualization technologies to decouple the handling of measurement data from the underlying devices. 111  
ApplicationBranchesBrief introductionReferences
Energy management DSM To meet the scalability and economic efficiency of DSM; Cost-oriented optimization model for a cloud-based ICT infrastructure to allocate cloud computing resources in a flexible and cost-efficient way. 104  
  To satisfy the requirements of large-scale real-time computing capabilities to handle the communication and the storage of huge transferable data; Providing a cloud computing framework for a group of smart energy hubs. 105  
  To improve the energy utilization efficiency in a smart community; A cloud-based user-side integrated energy management; A two-level model is proposed that relies on an energy hub and load aggregators. 106  
 Microgrid management A control model with the hierarchical structure based on cloud computing architecture; Resource allocation and management can be realized in an economically efficient manner; Integrating the past and present data to make the collected information more accurate and provides more flexible service for users. 107  
 Dynamic pricing Proposing a real-time dynamic pricing model for electric vehicles charging and discharging service and building energy management, in order to reduce the peak loads; A decentralized cloud computing architecture based on software-defined networking technology and function virtualization. 108  
Information management Information management cloudward Different domains for cost-effective information management cloudward; Propose a cloud-based SG information management model and present a cloud and network resource optimization framework to solve the cost reduction problem in cloud-based SG information storage and computation. 109  
 Cloud-based demand response (CDR) Demand response program based on the distributed optimization model; Solving the problem of the existence of an ideal communication network; Defining a cloud-based demand response (CDR) model which is implemented as a two-tier cloud computing platform. 110  
 State estimation (SE) State estimation (SE); Proposing and validating a Cloud-IoT-based architectural solution for SE in SG that combines cloud capabilities and edge computing advantages and uses virtualization technologies to decouple the handling of measurement data from the underlying devices. 111  

2. Fog computing (FC)

With the large increase in the number of smart devices connected to the IoT, it is impractical to transmit all data to the cloud for processing because of the high cost and high delay requirements.182 FC extends CC to the edge of the network. It is characterized by low latency and location awareness, extensive geographic distribution, mobility, a very large number of nodes, and heterogeneity.183Table V compares the characteristics of FC and CC. As shown in Table V, compared with CC, FC has great advantages in many aspects. It can solve the applications and services that are not suitable for CC, including the following aspects: very low and predictable latency is required, geographically dispersed, fast-moving, and so on. The literature184 introduces the representative application scenarios of FC, analyzes the problems that may be encountered in designing and implementing FC systems, and discusses the opportunities and challenges of FC. In Ref. 185, the author studied which can be solved by cloud computing in SG, which subdomains and services need to be solved by fog computing, and introduced the opportunities and challenges of fog computing in SG.

TABLE V.

Comparison of FC and CC.

Cloud computingFog computing
Location of service Within the internet At the edge of local network 
Location awareness No Yes 
Number of computing nodes Few Very large 
Location of service Within the internet At the edge of local network 
Geodistribution Centralized Distributed 
Latency High Low 
Security Undefined Can be defined 
Attack on data enroute High probability Very low probability 
Support for mobility Limited Supported 
Distance between client and server Multiple hops One hop 
Cloud computingFog computing
Location of service Within the internet At the edge of local network 
Location awareness No Yes 
Number of computing nodes Few Very large 
Location of service Within the internet At the edge of local network 
Geodistribution Centralized Distributed 
Latency High Low 
Security Undefined Can be defined 
Attack on data enroute High probability Very low probability 
Support for mobility Limited Supported 
Distance between client and server Multiple hops One hop 

3. Big data

With the explosive growth of data in all segments of the smart grid, we have ushered in the era of big data. In SG, AMI is the primary source of data.186 When 1 million metering devices collect data every 15 min, the total amount of data will reach 2920 Tb. However, in addition to the data in the AMI, there are many other smart devices, such as sensors, thermostats, etc., in the entire SG, which are also collecting large amounts of data.

To fully exploit the potential value of these data and using effectively, big data technology has become an indispensable part of information technology in the realization of UPIoT. China State Grid Corporation established the Big Data Center on May 21, 2019 to lay the foundation for the realization of UPIoT and provide digital support for energy Internet companies.187 

In fact, big data analytics technology has developed very well in SG, which plays a critical role in SG making decision, as shown in Fig. 4. In the SG environment, the applications based on big data mainly include five aspects, namely, electric vehicles (EV), power generation, renewable energy, asset management, and collaborative and demand side management.

FIG. 4.

Application of big data in SG making decision.

FIG. 4.

Application of big data in SG making decision.

Close modal

With the increasing number of electric vehicles (EVs), many problems such as energy management, battery capacity, and EV's state get great concerns from researchers. EVs are one of the typical applications of big data technologies. Many of the issues above can be handled with big data technologies. For example, in Ref. 112, the author proposed an estimation of distribution algorithm (EDA) based on big data technologies to realize the intelligent allocation of electric energy to EVs. In Ref. 113, the author presented a methodology based on Monte Carlo Simulation (MCS) to estimate the possible EV state (i.e., their locations and periods of connection in power systems). In Ref. 114, the author proposed a data-driving queuing model for EV charging demand with the help of big data analysis on smart measurements.

On the power generation side, the role of big data analysis is mainly reflected in the power generation planning115–118,120 and economic load schduling.121–131 Their data source includes technology cost and performance data, generating cost data, budget, and capacity constraint data, Ramp-rate limit data, load demand, operating zones data, and so on; combining big data analytics technologies and energy collected through ubiquitous IoT technology can significantly improve energy efficiency and reduce production costs.

Renewable energy is a significant part of modern energy systems. The main renewable energy sources in the SG are wind and solar, but their output power is extremely unstable and is mainly affected by the weather. This uncertainty poses a great challenge to the balance of supply and demand in the power system. The introduction of big data analysis technology has given a solution to this problem. Based on large-scale weather data analysis, wind power prediction,132–134 solar power generation prediction,135,136 hybrid wind-solar power generation prediction,137,138 microgrid optimal load distribution,139,140 etc., can greatly improve the stability of the power system.

Asset management (such as resource sharing, inventory management, etc.) is a major challenge for power generation companies and electric power companies. Big data analysis plays a major role in improving the efficiency of asset management. Using big data analytics technology, data can be shared throughout production, transmission, transformation, distribution, and consumption processes to optimize resource allocation and increase resource utilization.141–143 The combination of large amounts of data collected by sensors with big data analysis techniques and visualization techniques enables real-time monitoring and fault diagnosis of power systems.144,188

Demand-side management is one of the most widely used areas of big data analytics technology.189 Through monitoring and analyzing energy consumption data in real-time, electric power companies can perform load forecasting, load classification and dynamic pricing. Several methods of load prediction are proposed in Refs. 145–148, including neural networks approach, support vector regression, particle swarm optimization (PSO) based methods and ant colony optimization. Load classification uses different clustering methods to group different load profiles, which can be used to identify energy consumption patterns of different users. With load classification, different energy saving schemes can be developed for different users.151–153 Dynamic pricing refers to the electric power companies to guide customers to use electricity according to the user's power consumption information to set different electricity prices to reduce the peak-to-average ratio (PAR) in load demand.190 In Refs. 149 and 150, the authors used the methods of least squares support vector machine (SVM) and economic modeling to realize the concept.

4. Artificial intelligence

Artificial intelligence has strong optimization processing power and strong learning ability in dealing with high-dimensional, time-varying, and nonlinear problems in computational intelligence, perceptual intelligence, and cognitive intelligence. Artificial intelligence (AI) has strong optimization processing power and strong learning ability in dealing with high dimensional, time-varying, and nonlinear problems in computational intelligence, perceptual intelligence, and cognitive intelligence. They can learn from examples, and with the ability of fault tolerance as they can handle noisy or incomplete data. Also, they can do with nonlinear problems and once trained can perform prediction and generalization at high speed.191 

The application of artificial intelligence technology in power systems can realize the combination of intelligent sensing and physical state, data driving and simulation model auxiliary decision and operation control, thus solving various challenges faced by power system systems, and improving the security and reliability of system operations. Table VI summarizes the application of artificial intelligence in energy forecasting (including wind energy,154–157 photovoltaic and solar power158–161), load forecasting,162–165 managing electric vehicles (including congestion management,166,167 load balancing,168,169 and electricity markets170–172), fault diagnosis,173–175 cyber security,176 and power generation planning.177–179 It is worth noting that AI technology is inseparable from big data, and the two complement each other and work together.

TABLE VI.

Some research on the application of big data in SG.

ApplicationsBranchesCharacteristicsReferences
Electric vehicles Energy management Charging and discharging data; An Estimation of Distribution Algorithm (EDA); Optimally manage a large number of EV's charging 112  
Ev's state A methodology based on Monte Carlo Simulation (MCS); Estimate the possible Ev's states about locations and periods of connection 113  
Battery capacity Smart meter measurements; A data-driven queuing model; EV charging demand 114  
Power generation Power generation planning Technology cost and performance data; Constraint programming and compromised modeling 115,116  
 Generating cost data, budget and capacity constraints data etc.; Portfolio-theory, dynamic programming 117,118  
 Generating units data, carbon emission data; Constraint programming, fuzzy possibilistic model 119,120  
Economic load dispatch (ELD) Ramp-rate limits data, load demand, operating zones data; Differential evolution based methods 121–123  
 Transmission loss, generator parameters, Load demand; Biogeography-based optimization (BBO) algorithm 124,125  
 Generator parameters, load demand; Harmony search based methods 126–128  
 Operating zones data, transmission loss, Load demand; Particle swarm optimization (PSO) based methods 129–131  
Renewable energy Wind power forecasting Past power measurements, wind speed, and direction; Time series models, support vector machine (SVM), artificial neural network, quantile regression, Self-organized map 132–134  
Solar power forecasting Meteorological forecasts of solar irradiance, past power measurements, relative humidity and temperature; Artificial neural network, autoregressive (AR) models 135,136  
Hybrid wind-solar power generation Energy storage data, wind, and solar power generation, load demand; Operational management, time series analysis 137,138  
Microgrid optimal load distribution Distributed generator parameters, load demand; Multiobjective optimization, single-objective optimization 139,140  
Asset management and collaborative operations Operation and control Operation conditions data, substation data; Random fuzzy model, automated analysis 141  
Asset management Operating observations, network data, component reliability data; Service-oriented architecture, condition assessment techniques 142,143  
System reliability Improvement Equipment data, load data, failure data; Fault tree analysis, risk importance measures 144  
Demand side management Load forecasting Wind speed, cloud cover, temperature information, historical load data; Neural networks approach, support vector regression, PSO based methods, ant colony optimization 145–148  
Dynamic pricing Variable pricing or real-time pricing, user behavior data, power supply data, load demand; Least-squares SVM, economic modeling 149,150  
Classification (load and consumers) Consumption data, load profiles; K-means clustering, Fuzzy c-means (FCM) clustering, Hierarchical clustering 151–153  
ApplicationsBranchesCharacteristicsReferences
Electric vehicles Energy management Charging and discharging data; An Estimation of Distribution Algorithm (EDA); Optimally manage a large number of EV's charging 112  
Ev's state A methodology based on Monte Carlo Simulation (MCS); Estimate the possible Ev's states about locations and periods of connection 113  
Battery capacity Smart meter measurements; A data-driven queuing model; EV charging demand 114  
Power generation Power generation planning Technology cost and performance data; Constraint programming and compromised modeling 115,116  
 Generating cost data, budget and capacity constraints data etc.; Portfolio-theory, dynamic programming 117,118  
 Generating units data, carbon emission data; Constraint programming, fuzzy possibilistic model 119,120  
Economic load dispatch (ELD) Ramp-rate limits data, load demand, operating zones data; Differential evolution based methods 121–123  
 Transmission loss, generator parameters, Load demand; Biogeography-based optimization (BBO) algorithm 124,125  
 Generator parameters, load demand; Harmony search based methods 126–128  
 Operating zones data, transmission loss, Load demand; Particle swarm optimization (PSO) based methods 129–131  
Renewable energy Wind power forecasting Past power measurements, wind speed, and direction; Time series models, support vector machine (SVM), artificial neural network, quantile regression, Self-organized map 132–134  
Solar power forecasting Meteorological forecasts of solar irradiance, past power measurements, relative humidity and temperature; Artificial neural network, autoregressive (AR) models 135,136  
Hybrid wind-solar power generation Energy storage data, wind, and solar power generation, load demand; Operational management, time series analysis 137,138  
Microgrid optimal load distribution Distributed generator parameters, load demand; Multiobjective optimization, single-objective optimization 139,140  
Asset management and collaborative operations Operation and control Operation conditions data, substation data; Random fuzzy model, automated analysis 141  
Asset management Operating observations, network data, component reliability data; Service-oriented architecture, condition assessment techniques 142,143  
System reliability Improvement Equipment data, load data, failure data; Fault tree analysis, risk importance measures 144  
Demand side management Load forecasting Wind speed, cloud cover, temperature information, historical load data; Neural networks approach, support vector regression, PSO based methods, ant colony optimization 145–148  
Dynamic pricing Variable pricing or real-time pricing, user behavior data, power supply data, load demand; Least-squares SVM, economic modeling 149,150  
Classification (load and consumers) Consumption data, load profiles; K-means clustering, Fuzzy c-means (FCM) clustering, Hierarchical clustering 151–153  

Professor Sun Hongbin of Tsinghua University believes that the mission of UPIoT is to break down barriers between different energy sources such as cold, heat, gas, and electricity that hinder the formation of an open shared energy ecosystem.192,193 It is necessary to be broken through from the perspective of an integrated energy system. Each department of the power grid has independent systems and services. Each branch of the power grid has its own system and business. Therefore, it is one of the challenges to be tackled that how to conduct unified analysis and complementary integration of massive data, so as to achieve operational maintenance, measurement, finance, and other services.

After more than 10 years of development, the Internet of things has made great progress in the application of SG. However, there are still some shortcomings in the sensing layer, the network layer, and the platform layer, mainly in the following aspects:

  • At the sensing layer, IoT has insufficient coverage at the power generation side, distribution side and other terminals (i.e., many terminal devices are not yet connected to the Internet); the level of terminal intelligence and bidirectional interaction is low, and the ability of edge computing and intelligent processing is not available yet; there is a lack of unified planning design and standards.

  • At the network layer, the communication access network (i.e., all devices between the backbone network and terminal user) has insufficient coverage; there is a lack of end-to-end ubiquitous communication network solutions and the ability of network resource allocation is insufficient.

  • At the platform level, there is a lack of cross-professional IoT management, and open sharing for IoT applications is insufficient.

In view of the above deficiencies, they can be improved from the following directions: first, improve the holistic sensing ability to achieve the function of energy transmission, conversion, utilization, and the equipment and user status of each link can be fully perceived; second, improve ubiquitous connectivity to achieve real-time connectivity of internal devices, users and data. Third, improve the ability of integration and innovation, and then promote the deep integration and data integration of SG and UPIoT.

Security issues are major challenges in building UPIoT. For example, when UPIoT runs on the open Internet, attackers may potentially affect the real-time balance between energy production and consumption by manipulating data generated by smart objects or sent from utilities. It could cause considerable financial losses for utilities and power assets.194 In the process of transmitting massive data to the unified platform, it is the second challenge in building UPIoT to be addressed that how to prevent data leakage, resist network attacks to ensure reliable and fast transmission of data.

Another challenge in achieving UPIoT is privacy. The energy efficiency can be improved by frequent data collection and analysis. The smart meter collects a large amount of information from the household appliances at the required time interval. Therefore, this method comes at the cost of privacy. In the context of the Internet of Everything, how to protect the privacy of users becomes extremely important and difficult.

At present, there is still a large number of electrical instruments in SG that are not connected to the Internet yet, and a large amount of basic data are still not acquired due to various difficulties. It is an inevitable tendency that applying ubiquitous IoT technology to power systems to achieve UPIoT. At present, China is setting off a research boom in UPIoT. The importance of UPIoT is self-evident. The operation of “strong smart grid” and “the ubiquitous power Internet of Things” is an important material basis for building a world-class energy Internet enterprise, and a new strategy for the development of power informatization in the new era (Table VII).

TABLE VII.

Some research on the application of Artificial Intelligence in SG.

ApplicationsBranchesCharacteristicsReferences
Energy forecasting Wind energy Short-term wind power forecasting, neural networks, and wavelet transform; spatial estimation of wind speed in a coastal region, artificial neural networks; wind speed forecasting, time-series 154–157  
 Photovoltaic and solar power Long-term ahead Photovoltaic (PV) power output correction, insolation prediction with fuzzy and applying neural network; Short-term solar power prediction, support vector machine, artificial neural networks; Prediction of daily global solar irradiation data, Bayesian neural network 158–161  
Load forecasting … Support vector machine and ant colony optimization; Hybrid PSO-SVM; Recurrent support vector machines with genetic algorithms; Wavelet neural networks with data prefiltering 162–165  
Managing electric vehicles Congestion management Stochastic optimization, Graph-based search, and mathematical programming, and probabilities theory; Decentralized or centralized 166,167  
 Load balancing Mathematical programming, utility-based agent coordination; Decentralized or centralized 168,169  
 Electricity markets Mathematical programming, auctions, and stochastic optimization, game-theoretic analysis; Decentralized or centralized 170–172  
Fault diagnosis … Self-evolving neural network, artificial neural networks, fault prognosis in wind turbine, photovoltaic systems; 173–175  
Cyber security … Contextual anomaly detection, use in the discovery of malicious voltage control actions in the low voltage distribution grid; Artificial neural network model 176  
Power generation planning … Power Generation Expansion Planning With Emission Controls, power distribution system planning; Genetic algorithm (GA)-Benders' decomposition, a nonlinear model and a GA-based heuristic, artificial neural networks 177–179  
ApplicationsBranchesCharacteristicsReferences
Energy forecasting Wind energy Short-term wind power forecasting, neural networks, and wavelet transform; spatial estimation of wind speed in a coastal region, artificial neural networks; wind speed forecasting, time-series 154–157  
 Photovoltaic and solar power Long-term ahead Photovoltaic (PV) power output correction, insolation prediction with fuzzy and applying neural network; Short-term solar power prediction, support vector machine, artificial neural networks; Prediction of daily global solar irradiation data, Bayesian neural network 158–161  
Load forecasting … Support vector machine and ant colony optimization; Hybrid PSO-SVM; Recurrent support vector machines with genetic algorithms; Wavelet neural networks with data prefiltering 162–165  
Managing electric vehicles Congestion management Stochastic optimization, Graph-based search, and mathematical programming, and probabilities theory; Decentralized or centralized 166,167  
 Load balancing Mathematical programming, utility-based agent coordination; Decentralized or centralized 168,169  
 Electricity markets Mathematical programming, auctions, and stochastic optimization, game-theoretic analysis; Decentralized or centralized 170–172  
Fault diagnosis … Self-evolving neural network, artificial neural networks, fault prognosis in wind turbine, photovoltaic systems; 173–175  
Cyber security … Contextual anomaly detection, use in the discovery of malicious voltage control actions in the low voltage distribution grid; Artificial neural network model 176  
Power generation planning … Power Generation Expansion Planning With Emission Controls, power distribution system planning; Genetic algorithm (GA)-Benders' decomposition, a nonlinear model and a GA-based heuristic, artificial neural networks 177–179  

In this paper, the concept, architecture, and key technologies are analyzed in detail; and the challenges of UPIoT in UPIoT are briefly introduced. At present, UPIoT is in the initial development, and there are a few related studies. We have introduced the important work that has been done in the field of UPIoT-aided SG systems, but there is still more work to achieve a better and complete implementation of the UPIoT-aided SG system. In the future, our research work will be devoted to the extensive application of UPIoT, such as the application in the distribution network.

This work was supported by the National Science Foundation of China No. 51667004.

1.
S. E.
Collier
, “
The emerging enernet: Convergence of the smart grid with the internet of things
,”
IEEE Ind. Appl. Mag.
23
,
12
16
(
2017
).
2.
R.
Deng
,
Z.
Yang
,
M.-Y.
Chow
, and
J.
Chen
, “
A survey on demand response in smart grids: Mathematical models and approaches
,”
IEEE Trans. Ind. Inf.
11
,
570
582
(
2015
).
3.
Ş.
Temel
,
V. Ç.
Gungor
, and
T.
Koçak
, “
Routing protocol design guidelines for smart grid environments
,”
Comput. Networks
60
,
160
170
(
2014
).
4.
R.
Ma
,
H.-H.
Chen
,
Y.-R.
Huang
, and
W.
Meng
, “
Smart grid communication: Its challenges and opportunities
,”
IEEE Trans. Smart Grid
4
,
36
46
(
2013
).
5.
W.
Wang
,
Y.
Xu
, and
M.
Khanna
, “
A survey on the communication architectures in smart grid
,”
Comput. Networks
55
,
3604
3629
(
2011
).
6.
E.
Yaacoub
and
A.
Abu-Dayya
, “
Automatic meter reading in the smart grid using contention based random access over the free cellular spectrum
,”
Comput. Networks
59
,
171
183
(
2014
).
7.
A.
Čolaković
and
M.
Hadžialić
, “
Internet of Things (IoT): A review of enabling technologies, challenges, and open research issues
,”
Comput. Networks
144
,
17
39
(
2018
).
8.
X.
Yuan
,
S.
Cheng
, and
J.
Hu
Multi-time scale voltage and power angle dynamics in power electronics dominated large power systems
,” in
Proceedings of the CSEE
(
2016
), pp.
5145
5154
.
9.
L.
Jun
, “
Implementing innovation-driven development strategy and supporting the company's ‘three types, two networks’ construction
,”
State Grid News
2
,
1
2
(
2019
).
10.
W.
Zhengtao
, “
Promotes the innovation and support of ICT in the construction of the internet of things
,”
State Grid Daily
2
,
1
2
(
2019
).
11.
See http://www.bjpsb.com/dwjs/50074.html for “
B. Power Network, The Integration of Smart Grid and Ubiquitous Power Internet of Things is an Indispensable Support for Energy Transformation
” (last accessed May 8,
2019
).
12.
J.
Lin
,
W.
Yu
,
N.
Zhang
,
X.
Yang
,
H.
Zhang
, and
W.
Zhao
, “
A survey on internet of things: Architecture, enabling technologies, security and privacy, and applications
,”
IEEE Internet Things J.
4
,
1125
1142
(
2017
).
13.
A.
Al-Fuqaha
,
M.
Guizani
,
M.
Mohammadi
,
M.
Aledhari
, and
M.
Ayyash
, “
Internet of things: A survey on enabling technologies, protocols, and applications
,”
IEEE Commun. Surv. Tutorials
17
,
2347
2376
(
2015
).
14.
E.
Borgia
, “
The Internet of Things vision: Key features, applications and open issues
,”
Comput. Commun.
54
,
1
31
(
2014
).
15.
I.
Mashal
,
O.
Alsaryrah
,
T.-Y.
Chung
,
C.-Z.
Yang
,
W.-H.
Kuo
, and
D. P.
Agrawal
, “
Choices for interaction with things on internet and underlying issues
,”
Ad Hoc Networks
28
,
68
90
(
2015
).
16.
M.
Nitti
,
V.
Pilloni
,
G.
Colistra
, and
L.
Atzori
, “
The virtual object as a major element of the internet of things: A survey
,”
IEEE Commun. Surv. Tutorials
18
,
1228
1240
(
2015
).
17.
L.
Atzori
,
A.
Iera
,
G.
Morabito
, and
M.
Nitti
, “
The social internet of things (SIoT)–when social networks meet the internet of things: Concept, architecture and network characterization
,”
Comput. Networks
56
,
3594
3608
(
2012
).
18.
A. M.
Ortiz
,
D.
Hussein
,
S.
Park
,
S. N.
Han
, and
N.
Crespi
, “
The cluster between internet of things and social networks: Review and research challenges
,”
IEEE Internet Things J.
1
,
206
215
(
2014
).
19.
I.
You
,
C.
Fung
,
J.
Baek
, and
V. C.
Leung
, “
IEEE access special section editorial: Security and privacy in applications and services for future internet of things
,”
IEEE Access
6
,
39398
39400
(
2018
).
20.
S.
Sicari
,
A.
Rizzardi
,
L. A.
Grieco
, and
A.
Coen-Porisini
, “
Security, privacy and trust in internet of things: The road ahead
,”
Comput. Networks
76
,
146
164
(
2015
).
21.
J.
Granjal
,
E.
Monteiro
, and
J. S.
Silva
, “
Security for the internet of things: A survey of existing protocols and open research issues
,”
IEEE Commun. Surv. Tutorials
17
,
1294
1312
(
2015
).
22.
M. R.
Palattella
,
N.
Accettura
,
X.
Vilajosana
,
T.
Watteyne
,
L. A.
Grieco
,
G.
Boggia
, and
M.
Dohler
, “
Standardized protocol stack for the internet of (important) things
,”
IEEE Commun. Surv. Tutorials
15
,
1389
1406
(
2013
).
23.
Z.
Sheng
,
S.
Yang
,
Y.
Yu
,
A. V.
Vasilakos
,
J. A.
McCann
, and
K. K.
Leung
, “
A survey on the IETF protocol suite for the internet of things: Standards, challenges, and opportunities
,”
IEEE Wireless Commun.
20
,
91
98
(
2013
).
24.
J.
Granjal
,
E.
Monteiro
, and
J. S.
Silva
, “
Security in the integration of low-power wireless sensor networks with the internet: A survey
,”
Ad Hoc Networks
24
,
264
287
(
2015
).
25.
K.
Sood
,
S.
Yu
, and
Y.
Xiang
, “
Software-defined wireless networking opportunities and challenges for internet-of-things: A review
,”
IEEE Internet Things J.
3
,
453
463
(
2016
).
26.
C.-W.
Tsai
,
C.-F.
Lai
,
M.-C.
Chiang
, and
L. T.
Yang
, “
Data mining for internet of things: A survey
,”
IEEE Commun. Surv. Tutorials
16
,
77
97
(
2014
).
27.
M. A.
Mehaseb
,
Y.
Gadallah
,
A.
Elhamy
, and
H.
Elhennawy
, “
Classification of LTE uplink scheduling techniques: An M2M perspective
,”
IEEE Commun. Surv. Tutorials
18
,
1310
1335
(
2016
).
28.
C.
Perera
,
A.
Zaslavsky
,
P.
Christen
, and
D.
Georgakopoulos
, “
Context aware computing for the internet of things: A survey
,”
IEEE Commun. Surv. Tutorials
16
,
414
454
(
2013
).
29.
S. S.
Reka
and
T.
Dragicevic
, “
Future effectual role of energy delivery: A comprehensive review of internet of things and smart grid
,”
Renewable Sustainable Energy Rev.
91
,
90
108
(
2018
).
30.
L.
Atzori
,
A.
Iera
, and
G.
Morabito
, “
The Internet of Things: A survey
,”
Comput. Networks
54
,
2787
2805
(
2010
).
31.
A.
Al-Ali
and
R.
Aburukba
, “
Role of internet of things in the smart grid technology
,”
J. Comput. Commun.
3
,
229
(
2015
).
32.
J.
Gubbi
,
R.
Buyya
,
S.
Marusic
, and
M.
Palaniswami
, “
Internet of Things (IoT): A vision, architectural elements, and future directions
,”
Future Gener. Comput. Syst.
29
,
1645
1660
(
2013
).
33.
N.
Bui
,
A. P.
Castellani
,
P.
Casari
, and
M.
Zorzi
, “
The internet of energy: A web-enabled smart grid system
,”
IEEE Network
26
,
39
45
(
2012
).
34.
Q.
Yang
, “
Internet of things application in smart grid: A brief overview of challenges, opportunities, and future trends
,”
Smart Power Distribution Systems
(
Elsevier
,
2019
), pp.
267
283
.
35.
G.
Bedi
,
G. K.
Venayagamoorthy
,
R.
Singh
,
R. R.
Brooks
, and
K.-C.
Wang
, “
Review of Internet of Things (IoT) in electric power and energy systems
,”
IEEE Internet Things J.
5
,
847
870
(
2018
).
36.
Y.
Saleem
,
N.
Crespi
,
M. H.
Rehmani
, and
R.
Copeland
, “
Internet of things-aided smart grid: Technologies, architectures, applications, prototypes, and future research directions
,”
IEEE Access
7
,
62962
63003
(
2019
).
37.
A.
Gupta
,
A.
Anpalagan
,
G. H.
Carvalho
,
L.
Guan
, and
I.
Woungang
, “
Prevailing and emerging cyber threats and security practices in IoT-enabled smart grids: A survey
,”
J. Network Comput. Appl.
132
,
118
148
(
2019
).
38.
G.
De La Torre
,
P.
Rad
, and
K.-K. R.
Choo
, “
Implementation of deep packet inspection in smart grids and industrial internet of things: Challenges and opportunities
,”
J. Network Comput. Appl.
135
,
32
46
(
2019
).
39.
D.
Sbordone
,
I.
Bertini
,
B.
Di Pietra
,
M. C.
Falvo
,
A.
Genovese
, and
L.
Martirano
, “
EV fast charging stations and energy storage technologies: A real implementation in the smart micro grid paradigm
,”
Electr. Power Syst. Res.
120
,
96
108
(
2015
).
40.
S.
Habib
,
M.
Kamran
, and
U.
Rashid
, “
Impact analysis of vehicle-to-grid technology and charging strategies of electric vehicles on distribution networks–A review
,”
J. Power Sources
277
,
205
214
(
2015
).
41.
C.
Chellaswamy
and
R.
Ramesh
, “
Future renewable energy option for recharging full electric vehicles
,”
Renewable Sustainable Energy Rev.
76
,
824
838
(
2017
).
42.
A.
Zakariazadeh
,
S.
Jadid
, and
P.
Siano
, “
Integrated operation of electric vehicles and renewable generation in a smart distribution system
,”
Energy Convers. Manage.
89
,
99
110
(
2015
).
43.
M.
López
,
S.
De La Torre
,
S.
Martín
, and
J.
Aguado
, “
Demand-side management in smart grid operation considering electric vehicles load shifting and vehicle-to-grid support
,”
Int. J. Electr. Power Energy Syst.
64
,
689
698
(
2015
).
44.
A.-H.
Mohsenian-Rad
,
V. W.
Wong
,
J.
Jatskevich
,
R.
Schober
, and
A.
Leon-Garcia
, “
Autonomous demand-side management based on game-theoretic energy consumption scheduling for the future smart grid
,”
IEEE Trans. Smart Grid
1
,
320
331
(
2010
).
45.
L.
Tronchin
,
M.
Manfren
, and
B.
Nastasi
, “
Energy efficiency, demand side management and energy storage technologies–A critical analysis of possible paths of integration in the built environment
,”
Renewable Sustainable Energy Rev.
95
,
341
353
(
2018
).
46.
S.
Noor
,
W.
Yang
,
M.
Guo
,
K. H.
van Dam
, and
X.
Wang
, “
Energy demand side management within micro-grid networks enhanced by blockchain
,”
Appl. Energy
228
,
1385
1398
(
2018
).
47.
H. T.
Haider
,
O. H.
See
, and
W.
Elmenreich
, “
A review of residential demand response of smart grid
,”
Renewable Sustainable Energy Rev.
59
,
166
178
(
2016
).
48.
H.
Shareef
,
M. S.
Ahmed
,
A.
Mohamed
, and
E.
Al Hassan
, “
Review on home energy management system considering demand responses, smart technologies, and intelligent controllers
,”
IEEE Access
6
,
24498
24509
(
2018
).
49.
R.
Zafar
,
A.
Mahmood
,
S.
Razzaq
,
W.
Ali
,
U.
Naeem
, and
K.
Shehzad
, “
Prosumer based energy management and sharing in smart grid
,”
Renewable Sustainable Energy Rev.
82
,
1675
1684
(
2018
).
50.
N.
Mahmud
and
A.
Zahedi
, “
Review of control strategies for voltage regulation of the smart distribution network with high penetration of renewable distributed generation
,”
Renewable Sustainable Energy Rev.
64
,
582
595
(
2016
).
51.
Z.
Jingchao
,
H.
Jinhua
,
M.
Linchang
,
S.
Ningxi
, and
L.
Xiaolei
, “
The implementation of the internet of things technology in Henan smart distribution network demonstration project
,” in
2016 China International Conference on Electricity Distribution (CICED)
(
IEEE
,
2016
), pp.
1
5
.
52.
S. S. S. R.
Depuru
,
L.
Wang
,
V.
Devabhaktuni
, and
N.
Gudi
, “
Smart meters for power grid—Challenges, issues, advantages and status
,” in
2011 IEEE/PES Power Systems Conference and Exposition
(
IEEE
,
2011
), pp.
1
7
.
53.
Y.
Kabalci
, “
A survey on smart metering and smart grid communication
,”
Renewable Sustainable Energy Rev.
57
,
302
318
(
2016
).
54.
Z.
Ping
,
L. I.
Shilin
, and
H. U.
Zheng
, “
Enhanced-mobile ubiquitous smart environment—The super state of internet of things
,”
Chin. J. Internet Things
2
,
17
23
(
2018
).
55.
S.
Kraijak
and
P.
Tuwanut
, “
A survey on IoT architectures, protocols, applications, security, privacy, real-world implementation and future trends
,”
in 2015 11th International Conference on Wireless Communications, Networking and Mobile Computing (WiCOM 2015), pp. 1–6
.
56.
O.
Salman
,
I.
Elhajj
,
A.
Kayssi
, and
A.
Chehab
, “
Edge computing enabling the internet of things
,” in
2015 IEEE 2nd World Forum on Internet of Things (WF-IoT)
(
IEEE
,
2015
), pp.
603
608
.
57.
G.
Premsankar
,
M.
Di Francesco
, and
T.
Taleb
, “
Edge computing for the internet of things: A case study
,”
IEEE Internet Things J.
5
,
1275
1284
(
2018
).
58.
F.
Viani
,
F.
Robol
,
A.
Polo
,
P.
Rocca
,
G.
Oliveri
, and
A.
Massa
, “
Wireless architectures for heterogeneous sensing in smart home applications: Concepts and real implementation
,”
Proc. IEEE
101
,
2381
2396
(
2013
).
59.
SGCC. Department of Internet
Outliner the construction of ubiquitous power internet of things (excerpts)
,”
North China Power
45
,
20
29
(
2019
).
60.
C.
Haoyong
,
C.
Yongbo
,
W.
Xiaojuan
,
C.
Wutao
, and
L.
Zhihao
, “
Ubiquitous power internet of things based on LPWAN
,”
Power Syst. Prot. Control
47
,
1
8
(
2019
).
61.
J.
Xiuchen
,
L.
Yadong
, and
F.
Xiaofei
, “
Construction ideas and development trends of transmission and distribution equipment of the ubiquitous power internet of things
,”
High Voltage Eng.
45
,
1345
1351
(
2019
).
62.
Q.
Ou
,
Y.
Zhen
,
X.
Li
,
Y.
Zhang
, and
L.
Zeng
, “
Application of internet of things in smart grid power transmission
,” in
2012 Third FTRA International Conference on Mobile, Ubiquitous, and Intelligent Computing
(
IEEE
,
2012
), pp.
96
100
.
63.
Y.
Ai
,
M.
Peng
, and
K.
Zhang
, “
Edge computing technologies for internet of things: A primer
,”
Digital Commun. Networks
4
,
77
86
(
2018
).
64.
X.
Sun
and
N.
Ansari
, “
EdgeIoT: Mobile edge computing for the internet of things
,”
IEEE Commun. Mag.
54
,
22
29
(
2016
).
65.
V. C.
Gungor
,
D.
Sahin
,
T.
Kocak
,
S.
Ergut
,
C.
Buccella
,
C.
Cecati
, and
G. P.
Hancke
, “
Smart grid technologies: Communication technologies and standards
,”
IEEE Trans. Ind. Inf.
7
,
529
539
(
2011
).
66.
G.
Suciu
,
V.
Suciu
,
A.
Martian
,
R.
Craciunescu
,
A.
Vulpe
,
I.
Marcu
,
S.
Halunga
, and
O.
Fratu
, “
Big data, internet of things and cloud convergence–An architecture for secure e-health applications
,”
J. Med. Syst.
39
,
141
(
2015
).
67.
Y.
Sun
,
H.
Song
,
A. J.
Jara
, and
R.
Bie
, “
Internet of things and big data analytics for smart and connected communities
,”
IEEE Access
4
,
766
773
(
2016
).
68.
C.
Tu
,
X.
He
,
Z.
Shuai
, and
F.
Jiang
, “
Big data issues in smart grid–A review
,”
Renewable Sustainable Energy Rev.
79
,
1099
1107
(
2017
).
69.
Y.
Guo
,
Z.
Yang
,
S.
Feng
, and
J.
Hu
, “
Complex power system status monitoring and evaluation using big data platform and machine learning algorithms: A review and a case study
,”
Complexity
2018
,
1
21
.
70.
R. S.
Pinto
,
C.
Unsihuay-Vila
, and
T. S.
Fernandes
, “
Multi-objective and multi-period distribution expansion planning considering reliability, distributed generation and self-healing
,”
IET Gener., Transm. Distrib.
13
,
219
228
(
2019
).
71.
Z.
Jiang
,
M.
Khalgui
,
A.
Al-Ahmari
,
Z.
Li
,
N.
Wu
, and
M.
Zhou
, “
Automatic supervisory control for the self-healing of smart grids based on colored petri nets
,”
IEEJ Trans. Electr. Electron. Eng.
13
,
1612
1623
(
2018
).
72.
B. S.
Torres
,
L. R.
Ferreira
, and
A. R.
Aoki
, “
Distributed intelligent system for self-healing in smart grids
,”
IEEE Trans. Power Delivery
33
,
2394
2403
(
2018
).
73.
L.
Li
,
H.
Xiaoguang
,
C.
Ke
, and
H.
Ketai
, “
The applications of WiFi-based wireless sensor network in internet of things and smart grid
,” in
2011 6th IEEE Conference on Industrial Electronics and Applications
(
IEEE
,
2011
), pp.
789
793
.
74.
M.
Erol-Kantarci
and
H. T.
Mouftah
, “
Wireless sensor networks for cost-efficient residential energy management in the smart grid
,”
IEEE Trans. Smart Grid
2
,
314
325
(
2011
).
75.
R. P.
Haridas
, “
Synchrophasor measurement technology in electrical power system
,”
Int. J. Eng. Res. Technol.
2
,
2063
2068
(
2013
).
76.
K.
Jung
and
S.
Lee
, “
A systematic review of RFID applications and diffusion: Key areas and public policy issues
,”
J. Open Innovation
1
,
9
(
2015
).
77.
K.
Domdouzis
,
B.
Kumar
, and
C.
Anumba
, “
Radio-frequency identification (RFID) applications: A brief introduction
,”
Adv. Eng. Inf.
21
,
350
355
(
2007
).
78.
C.
Han
,
Y.
Yang
, and
Z.
Cai
, “
Beidou navigation satellite system and its time scales
,”
Metrologia
48
,
S213
(
2011
).
79.
U. S. Department of Energy
, “
Communications requirements of smart grid technologies
,” US Department of Energy, Technical Report (
2010
), pp.
1
69
.
80.
H.
Li
,
L.
Lai
, and
W.
Zhang
, “
Communication requirement for reliable and secure state estimation and control in smart grid
,”
IEEE Trans. Smart Grid
2
,
476
486
(
2011
).
81.
H.
Khurana
,
M.
Hadley
,
N.
Lu
, and
D. A.
Frincke
, “
Smart-grid security issues
,”
IEEE Secur. Privacy
8
,
81
85
(
2010
).
82.
G. N.
Ericsson
, “
Cyber security and power system communication—Essential parts of a smart grid infrastructure
,”
IEEE Trans. Power Delivery
25
,
1501
1507
(
2010
).
83.
M. A.
Setiawan
,
F.
Shahnia
,
S.
Rajakaruna
, and
A.
Ghosh
, “
Zigbee-based communication system for data transfer within future microgrids
,”
IEEE Trans. Smart Grid
6
,
2343
2355
(
2015
).
84.
N.
Langhammer
and
R.
Kays
, “
Performance evaluation of wireless home automation networks in indoor scenarios
,”
IEEE Trans. Smart Grid
3
,
2252
2261
(
2012
).
85.
J.
Byun
,
B.
Jeon
,
J.
Noh
,
Y.
Kim
, and
S.
Park
, “
An intelligent self-adjusting sensor for smart home services based on zigbee communications
,”
IEEE Trans. Consum. Electron.
58
,
794
802
(
2012
).
86.
N. T.
Mahmood
and
E. I.
Abbas
, “
Wireless controlling and monitoring the consumption energy meter based on zigbee technology
,”
Int. J. Curr. Eng. Technol.
7
,
1
4
(
2017
).
87.
D.
Balsamo
,
G.
Gallo
,
D.
Brunelli
, and
L.
Benini
, “
Non-intrusive zigbee power meter for load monitoring in smart buildings
,” in
2015 IEEE Sensors Applications Symposium (SAS)
(
IEEE
,
2015
), pp.
1
6
.
88.
Y.
Zhang
,
S.
Yang
,
X.
Su
,
E.
Shi
, and
H.
Zhang
, “
Automatic reading of domestic electric meter: An intelligent device based on image processing and zigbee/ethernet communication
,”
J. Real-Time Image Process.
12
,
133
143
(
2016
).
89.
P.
Yi
,
A.
Iwayemi
, and
C.
Zhou
, “
Developing zigbee deployment guideline under WiFi interference for smart grid applications
,”
IEEE Trans. Smart Grid
2
,
110
120
(
2011
).
90.
M.
Garau
,
M.
Anedda
,
C.
Desogus
,
E.
Ghiani
,
M.
Murroni
, and
G.
Celli
, “
A 5G cellular technology for distributed monitoring and control in smart grid
,” in
2017 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)
(
IEEE
,
2017
), pp.
1
6
.
91.
M.
Cosovic
,
A.
Tsitsimelis
,
D.
Vukobratovic
,
J.
Matamoros
, and
C.
Anton-Haro
, “
5G mobile cellular networks: Enabling distributed state estimation for smart grids
,”
IEEE Commun. Mag.
55
,
62
69
(
2017
).
92.
A.
Augustin
,
J.
Yi
,
T.
Clausen
, and
W.
Townsley
, “
A study of LoRa: Long range & low power networks for the internet of things
,”
Sensors
16
,
1466
(
2016
).
93.
Y.
Song
,
J.
Lin
,
M.
Tang
, and
S.
Dong
, “
An internet of energy things based on wireless LPWAN
,”
Engineering
3
,
460
466
(
2017
).
94.
M.
Kuzlu
,
M.
Pipattanasomporn
, and
S.
Rahman
, “
Review of communication technologies for smart homes/building applications
,” in
2015 IEEE Innovative Smart Grid Technologies-Asia (ISGT ASIA)
(
IEEE
,
2015
), pp.
1
6
.
95.
M. Z.
Huq
and
S.
Islam
, “
Home area network technology assessment for demand response in smart grid environment
,” in
2010 20th Australasian Universities Power Engineering Conference
(
IEEE
,
2010
), pp.
1
6
.
96.
Y. D.
Beyene
,
R.
Jantti
,
K.
Ruttik
, and
S.
Iraji
, “
On the performance of narrow-band internet of things (NB-IoT)
,” in
2017 IEEE Wireless Communications and Networking Conference (WCNC)
(
IEEE
,
2017
), pp.
1
6
.
97.
Y.
Li
,
X.
Cheng
,
Y.
Cao
,
D.
Wang
, and
L.
Yang
, “
Smart choice for the smart grid: Narrowband internet of things (NB-IoT)
,”
IEEE Internet Things J.
5
,
1505
1515
(
2018
).
98.
A.
Yarali
, “
Wireless mesh networking technology for commercial and industrial customers
,” in
2008 Canadian Conference on Electrical and Computer Engineering
(
IEEE
,
2008
), pp.
000047
000052
.
99.
M.
Li
,
L.
Qu
,
Q.
Zhao
,
J.
Guo
,
X.
Su
, and
X.
Li
, “
Precise point positioning with the BeiDou navigation satellite system
,”
Sensors
14
,
927
943
(
2014
).
100.
See http://www.cpnn.com.cn/zdyw/201904/t20190404_1128211.html for “
MS, Innovation in Semiconductor Materials has Consolidated Industrial Supply Chains, Enabling Smart Phones and Automobiles
” (last accessed September 23,
2019
).
101.
E.
Ancillotti
,
R.
Bruno
, and
M.
Conti
, “
The role of communication systems in smart grids: Architectures, technical solutions and research challenges
,”
Comput. Commun.
36
,
1665
1697
(
2013
).
102.
V.
Gungor
,
D.
Sahin
,
T.
Kocak
, and
S.
Ergüt
,
Smart Grid Communications and Networking
(
Turk Telecom
,
2011
).
103.
V. C.
Gungor
,
B.
Lu
, and
G. P.
Hancke
, “
Opportunities and challenges of wireless sensor networks in smart grid
,”
IEEE Trans. Ind. Electron.
57
,
3557
3564
(
2010
).
104.
Z.
Cao
,
J.
Lin
,
C.
Wan
,
Y.
Song
,
Y.
Zhang
, and
X.
Wang
, “
Optimal cloud computing resource allocation for demand side management in smart grid
,”
IEEE Trans. Smart Grid
8
,
1943
1955
(2017).
105.
A.
Sheikhi
,
M.
Rayati
,
S.
Bahrami
,
A. M.
Ranjbar
, and
S.
Sattari
, “
A cloud computing framework on demand side management game in smart energy hubs
,”
Int. J. Electr. Power Energy Syst.
64
,
1007
1016
(
2015
).
106.
N.
Tian
,
T.
Ding
,
Y.
Yang
,
Q.
Guo
,
H.
Sun
, and
F.
Blaabjerg
, “
Confidentiality preservation in user-side integrated energy system management for cloud computing
,”
Appl. Energy
231
,
1230
1245
(
2018
).
107.
T.
Rajeev
and
S.
Ashok
, “
A cloud computing approach for power management of microgrids
,” in
ISGT2011-India
(
IEEE
,
2011
), pp.
49
52
.
108.
D. A.
Chekired
,
L.
Khoukhi
, and
H. T.
Mouftah
, “
Decentralized cloud-SDN architecture in smart grid: A dynamic pricing model
,”
IEEE Trans. Ind. Inf.
14
,
1220
1231
(
2018
).
109.
X.
Fang
,
D.
Yang
, and
G.
Xue
, “
Evolving smart grid information management cloudward: A cloud optimization perspective
,”
IEEE Trans. Smart Grid
4
,
111
119
(
2013
).
110.
M. H.
Yaghmaee
,
A.
Leon-Garcia
, and
M.
Moghaddassian
, “
On the performance of distributed and cloud-based demand response in smart grid
,”
IEEE Trans. Smart Grid
9
,
5403
5417
(
2018
).
111.
A.
Meloni
,
P. A.
Pegoraro
,
L.
Atzori
,
A.
Benigni
, and
S.
Sulis
, “
Cloud-based IoT solution for state estimation in smart grids: Exploiting virtualization and edge-intelligence technologies
,”
Comput. Networks
130
,
156
165
(
2018
).
112.
W.
Su
and
M.-Y.
Chow
, “
Performance evaluation of an EDA-based large-scale plug-in hybrid electric vehicle charging algorithm
,”
IEEE Trans. Smart Grid
3
,
308
315
(
2012
).
113.
J.
Soares
,
N.
Borges
,
B.
Canizes
, and
Z.
Vale
, “
Probabilistic estimation of the state of electric vehicles for smart grid applications in big data context
,” in
2015 IEEE Power and Energy Society General Meeting
(
IEEE
,
2015
), pp.
1
5
.
114.
X.
Zhang
and
S.
Grijalva
, “
An advanced data driven model for residential electric vehicle charging demand
,” in
2015 IEEE Power and Energy Society General Meeting
(
IEEE
,
2015
), pp.
1
5
.
115.
Q.
Chen
,
C.
Kang
,
Q.
Xia
, and
J.
Zhong
, “
Power generation expansion planning model towards low-carbon economy and its application in china
,”
IEEE Trans. Power Syst.
25
,
1117
1125
(
2010
).
116.
C. H.
Antunes
,
A. G.
Martins
, and
I. S.
Brito
, “
A multiple objective mixed integer linear programming model for power generation expansion planning
,”
Energy
29
,
613
627
(
2004
).
117.
S.
Awerbuch
, “
Portfolio-based electricity generation planning: Policy implications for renewables and energy security
,”
Mitigation Adapt. Strategies Global Change
11
,
693
710
(
2006
).
118.
C.-H.
Wang
and
K. J.
Min
, “
Electric power generation planning for interrelated projects: A real options approach
,”
IEEE Trans. Eng. Manage.
53
,
312
322
(
2006
).
119.
N.
Han
,
X.
Tang
, and
W.
Pei
, “
Research of power generator planning based on low-carbon targets
,” in
2011 Third Pacific-Asia Conference on Circuits, Communications and System (PACCS)
(
IEEE
,
2011
), pp.
1
4
.
120.
E.
Muela
,
G.
Schweickardt
, and
F.
Garces
, “
Fuzzy possibilistic model for medium-term power generation planning with environmental criteria
,”
Energy Policy
35
,
5643
5655
(
2007
).
121.
N.
Noman
and
H.
Iba
, “
Differential evolution for economic load dispatch problems
,”
Electric Power Syst. Res.
78
,
1322
1331
(
2008
).
122.
A.
Bhattacharya
and
P. K.
Chattopadhyay
, “
Hybrid differential evolution with biogeography-based optimization for solution of economic load dispatch
,”
IEEE Trans. Power Syst.
25
,
1955
1964
(
2010
).
123.
J.
Jasper
and
T. A. A.
Victoire
, “
Variable neighborhood search guided differential evolution for non-convex economic load dispatch
,” in
International Conference on Advanced Computing, Networking and Security
(
Springer
,
2011
), pp.
253
262
.
124.
A.
Bhattacharya
and
P. K.
Chattopadhyay
, “
Biogeography-based optimization for different economic load dispatch problems
,”
IEEE Trans. Power Syst.
25
,
1064
1077
(
2010
).
125.
A.
Bhattacharya
and
P. K.
Chattopadhyay
, “
Solving complex economic load dispatch problems using biogeography-based optimization
,”
Expert Syst. Appl.
37
,
3605
3615
(
2010
).
126.
L.
Wang
and
L.-P.
Li
, “
An effective differential harmony search algorithm for the solving non-convex economic load dispatch problems
,”
Int. J. Electr. Power Energy Syst.
44
,
832
843
(
2013
).
127.
A.
Chatterjee
,
S.
Ghoshal
, and
V.
Mukherjee
, “
Solution of combined economic and emission dispatch problems of power systems by an opposition-based harmony search algorithm
,”
Int. J. Electr. Power Energy Syst.
39
,
9
20
(
2012
).
128.
B.
Jeddi
and
V.
Vahidinasab
, “
A modified harmony search method for environmental/economic load dispatch of real-world power systems
,”
Energy Convers. Manage.
78
,
661
675
(
2014
).
129.
S.
Chakraborty
,
T.
Senjyu
,
A.
Yona
,
A.
Saber
, and
T.
Funabashi
, “
Solving economic load dispatch problem with valve-point effects using a hybrid quantum mechanics inspired particle swarm optimisation
,”
IET Gener., Transm. Distrib.
5
,
1042
1052
(
2011
).
130.
A.
Safari
and
H.
Shayeghi
, “
Iteration particle swarm optimization procedure for economic load dispatch with generator constraints
,”
Expert Syst. Appl.
38
,
6043
6048
(
2011
).
131.
Z.
Zhisheng
, “
Quantum-behaved particle swarm optimization algorithm for economic load dispatch of power system
,”
Expert Syst. Appl.
37
,
1800
1803
(
2010
).
132.
A. M.
Foley
,
P. G.
Leahy
,
A.
Marvuglia
, and
E. J.
McKeogh
, “
Current methods and advances in forecasting of wind power generation
,”
Renewable Energy
37
,
1
8
(
2012
).
133.
M.
Lei
,
L.
Shiyan
,
J.
Chuanwen
,
L.
Hongling
, and
Z.
Yan
, “
A review on the forecasting of wind speed and generated power
,”
Renewable Sustainable Energy Rev.
13
,
915
920
(
2009
).
134.
A.
Kusiak
,
H.
Zheng
, and
Z.
Song
, “
Short-term prediction of wind farm power: A data mining approach
,”
IEEE Trans. Energy Convers.
24
,
125
136
(
2009
).
135.
C.
Chen
,
S.
Duan
,
T.
Cai
, and
B.
Liu
, “
Online 24-h solar power forecasting based on weather type classification using artificial neural network
,”
Sol. Energy
85
,
2856
2870
(
2011
).
136.
H. T.
Pedro
and
C. F.
Coimbra
, “
Assessment of forecasting techniques for solar power production with no exogenous inputs
,”
Sol. Energy
86
,
2017
2028
(
2012
).
137.
T.
Hirose
and
H.
Matsuo
, “
Standalone hybrid wind-solar power generation system applying dump power control without dump load
,”
IEEE Trans. Ind. Electron.
59
,
988
997
(
2012
).
138.
D.
Heide
,
L.
Von Bremen
,
M.
Greiner
,
C.
Hoffmann
,
M.
Speckmann
, and
S.
Bofinger
, “
Seasonal optimal mix of wind and solar power in a future, highly renewable Europe
,”
Renewable Energy
35
,
2483
2489
(
2010
).
139.
K.
Zhou
,
S.
Yang
,
Z.
Chen
, and
S.
Ding
, “
Optimal load distribution model of microgrid in the smart grid environment
,”
Renewable Sustainable Energy Rev.
35
,
304
310
(
2014
).
140.
F. A.
Mohamed
and
H. N.
Koivo
, “
System modelling and online optimal management of microgrid using multiobjective optimization
,” in
2007 International Conference on Clean Electrical Power
(
IEEE
,
2007
), pp.
148
153
.
141.
Y.
Feng
,
W.
Wu
,
B.
Zhang
, and
W.
Li
, “
Power system operation risk assessment using credibility theory
,”
IEEE Trans. Power Syst.
23
,
1309
1318
(
2008
).
142.
A. E.
Abu-Elanien
and
M.
Salama
, “
Asset management techniques for transformers
,”
Electric Power Syst. Res.
80
,
456
464
(
2010
).
143.
J.
Pathak
,
Y.
Li
,
V.
Honavar
, and
J.
McCalley
, “
A service-oriented architecture for electric power transmission system asset management
,” in
International Conference on Service-Oriented Computing
(
Springer
,
2006
), pp.
26
37
.
144.
A.
Volkanovski
,
M.
Čepin
, and
B.
Mavko
, “
Application of the fault tree analysis for assessment of power system reliability
,”
Reliab. Eng. Syst. Saf.
94
,
1116
1127
(
2009
).
145.
N.
Amjady
and
F.
Keynia
, “
A new neural network approach to short term load forecasting of electrical power systems
,”
Energies
4
,
488
503
(
2011
).
146.
W.-C.
Hong
, “
Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm
,”
Energy
36
,
5568
5578
(
2011
).
147.
M.
AlRashidi
and
K.
El-Naggar
, “
Long term electric load forecasting based on particle swarm optimization
,”
Appl. Energy
87
,
320
326
(
2010
).
148.
W.-C.
Hong
, “
Application of chaotic ant swarm optimization in electric load forecasting
,”
Energy Policy
38
,
5830
5839
(
2010
).
149.
H.-P.
Chao
, “
Efficient pricing and investment in electricity markets with intermittent resources
,”
Energy Policy
39
,
3945
3953
(
2011
).
150.
F.
Oldewurtel
,
A.
Ulbig
,
A.
Parisio
,
G.
Andersson
, and
M.
Morari
, “
Reducing peak electricity demand in building climate control using real-time pricing and model predictive control
,” in
49th IEEE Conference on Decision and Control (CDC)
(
IEEE
,
2010
), pp.
1927
1932
.
151.
J. J.
López
,
J. A.
Aguado
,
F.
Martín
,
F.
Munoz
,
A.
Rodríguez
, and
J. E.
Ruiz
, “
Hopfield–k-means clustering algorithm: A proposal for the segmentation of electricity customers
,”
Electr. Power Syst. Res.
81
,
716
724
(
2011
).
152.
K.-L.
Zhou
and
S.-L.
Yang
, “
An improved fuzzy c-means algorithm for power load characteristics classification
,”
Power Syst. Prot. Control
40
,
58
63
(
2012
).
153.
P. R.
Jota
,
V. R.
Silva
, and
F. G.
Jota
, “
Building load management using cluster and statistical analyses
,”
Int. J. Electr. Power Energy Syst.
33
,
1498
1505
(
2011
).
154.
J. P. D. S.
Catalão
,
H. M. I.
Pousinho
, and
V. M. F.
Mendes
, “
Short-term wind power forecasting in Portugal by neural networks and wavelet transform
,”
Renewable Energy
36
,
1245
1251
(
2011
).
155.
K.
Philippopoulos
and
D.
Deligiorgi
, “
Application of artificial neural networks for the spatial estimation of wind speed in a coastal region with complex topography
,”
Renewable Energy
38
,
75
82
(
2012
).
156.
Y.-S.
Xiao
,
W.-Q.
Wang
, and
X.-P.
Huo
, “
Study on the time-series wind speed forecasting of the wind farm based on neural networks
,”
Energy Conserv. Technol.
25
,
106
108
(
2007
).
157.
M. C.
Mabel
and
E.
Fernandez
, “
Analysis of wind power generation and prediction using ANN: A case study
,”
Renewable Energy
33
,
986
992
(
2008
).
158.
A.
Yona
,
T.
Senjyu
,
T.
Funabashi
, and
C.-H.
Kim
, “
Determination method of insolation prediction with fuzzy and applying neural network for long-term ahead PV power output correction
,”
IEEE Trans. Sustainable Energy
4
,
527
533
(
2013
).
159.
J.
Zeng
and
W.
Qiao
, “
Short-term solar power prediction using a support vector machine
,”
Renewable Energy
52
,
118
127
(
2013
).
160.
E.
Izgi
,
A.
Öztopal
,
B.
Yerli
,
M. K.
Kaymak
, and
A. D.
Şahin
, “
Short-mid-term solar power prediction by using artificial neural networks
,”
Sol. Energy
86
,
725
733
(
2012
).
161.
R.
Yacef
,
M.
Benghanem
, and
A.
Mellit
, “
Prediction of daily global solar irradiation data using Bayesian neural network: A comparative study
,”
Renewable Energy
48
,
146
154
(
2012
).
162.
D.
Niu
,
Y.
Wang
, and
D. D.
Wu
, “
Power load forecasting using support vector machine and ant colony optimization
,”
Expert Syst. Appl.
37
,
2531
2539
(
2010
).
163.
A.
Selakov
,
D.
Cvijetinović
,
L.
Milović
,
S.
Mellon
, and
D.
Bekut
, “
Hybrid PSO–SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank
,”
Appl. Soft Comput.
16
,
80
88
(
2014
).
164.
P.-F.
Pai
and
W.-C.
Hong
, “
Forecasting regional electricity load based on recurrent support vector machines with genetic algorithms
,”
Electr. Power Syst. Res.
74
,
417
425
(
2005
).
165.
C.
Guan
,
P. B.
Luh
,
L. D.
Michel
,
Y.
Wang
, and
P. B.
Friedland
, “
Very short-term load forecasting: Wavelet neural networks with data pre-filtering
,”
IEEE Trans. Power Syst.
28
,
30
41
(
2013
).
166.
M. M.
de Weerdt
,
E. H.
Gerding
,
S.
Stein
,
V.
Robu
, and
N. R.
Jennings
, “
Intention-aware routing to minimise delays at electric vehicle charging stations
,” in
Twenty-Third International Joint Conference on Artificial Intelligence
(
2013
).
167.
I. S.
Bayram
,
G.
Michailidis
, and
M.
Devetsikiotis
, “
Electric power resource provisioning for large scale public EV charging facilities
,” in
2013 IEEE International Conference on Smart Grid Communications (SmartGridComm)
(
IEEE
,
2013
), pp.
133
138
.
168.
I. S.
Bayram
,
G.
Michailidis
,
M.
Devetsikiotis
, and
F.
Granelli
, “
Electric power allocation in a network of fast charging stations
,”
IEEE J. Sel. Areas Commun.
31
,
1235
1246
(
2013
).
169.
S.
Vandael
,
N.
Boucké
,
T.
Holvoet
,
K.
De Craemer
, and
G.
Deconinck
, “
Decentralized coordination of plug-in hybrid vehicles for imbalance reduction in a smart grid
,” in
the 10th International Conference on Autonomous Agents and Multiagent Systems
(
International Foundation for Autonomous Agents and Multiagent Systems
,
2011
), Vol.
2
, pp.
803
810
.
170.
J. M.
Foster
and
M. C.
Caramanis
, “
Optimal power market participation of plug-in electric vehicles pooled by distribution feeder
,”
IEEE Trans. Power Syst.
28
,
2065
2076
(
2013
).
171.
M. G.
Vayá
and
G.
Andersson
, “
Locational marginal pricing based smart charging of plug-in hybrid vehicle fleets
,” in
Smart Energy Strategies Conference
(
CiteSeerX
,
2011
), pp.
21
23
.
172.
W.
Tushar
,
W.
Saad
,
H. V.
Poor
, and
D. B.
Smith
, “
Economics of electric vehicle charging: A game theoretic approach
,”
IEEE Trans. Smart Grid
3
,
1767
1778
(
2012
).
173.
P.
Bangalore
and
L. B.
Tjernberg
, “
An approach for self-evolving neural network based algorithm for fault prognosis in wind turbine
,” in
2013 IEEE Grenoble Conference
(
IEEE
,
2013
), pp.
1
6
.
174.
W.
Chine
,
A.
Mellit
,
V.
Lughi
,
A.
Malek
,
G.
Sulligoi
, and
A. M.
Pavan
, “
A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks
,”
Renewable Energy
90
,
501
512
(
2016
).
175.
P.
Bangalore
and
L. B.
Tjernberg
, “
An artificial neural network approach for early fault detection of gearbox bearings
,”
IEEE Trans. Smart Grid
6
,
980
987
(
2015
).
176.
A. M.
Kosek
, “
Contextual anomaly detection for cyber-physical security in smart grids based on an artificial neural network model
,” in
2016 Joint Workshop on Cyber-Physical Security and Resilience in Smart Grids (CPSR-SG)
(
IEEE
,
2016
), pp.
1
6
.
177.
J.
Sirikum
,
A.
Techanitisawad
, and
V.
Kachitvichyanukul
, “
A new efficient ga-benders' decomposition method: For power generation expansion planning with emission controls
,”
IEEE Trans. Power Syst.
22
,
1092
1100
(
2007
).
178.
J.
Sirikum
and
A.
Techanitisawad
, “
Power generation expansion planning with emission control: A nonlinear model and a GA-based heuristic approach
,”
Int. J. Energy Res.
30
,
81
99
(
2006
).
179.
Y. S.
Qudaih
and
Y.
Mitani
, “
Power distribution system planning for smart grid applications using ANN
,”
Energy Procedia
12
,
3
9
(
2011
).
180.
D.
Freet
,
R.
Agrawal
,
S.
John
, and
J. J.
Walker
, “
Cloud forensics challenges from a service model standpoint: IAAS, PAAS and SAAS
,” in
Proceedings of the 7th International Conference on Management of Computational and Collective Intelligence in Digital EcoSystems
(
ACM
,
2015
), pp.
148
155
.
181.
M.
Yigit
,
V. C.
Gungor
, and
S.
Baktir
, “
Cloud computing for smart grid applications
,”
Comput. Networks
70
,
312
329
(
2014
).
182.
S.
Yi
,
C.
Li
, and
Q.
Li
, “
A survey of fog computing: Concepts, applications and issues
,” in
Proceedings of the 2015 Workshop on Mobile Big Data
(
ACM
,
2015
), pp.
37
42
.
183.
M.
Hussain
,
M. S.
Alam
,
M.
Beg
 et al, “
Fog computing in IoT aided smart grid transition-requirements, prospects, status quos and challenges
,” CoRR abs/1802.01818,
1
13
(
2018
).
184.
M.
Marjani
,
F.
Nasaruddin
,
A.
Gani
,
A.
Karim
,
I. A. T.
Hashem
,
A.
Siddiqa
, and
I.
Yaqoob
, “
Big IoT data analytics: Architecture, opportunities, and open research challenges
,”
IEEE Access
5
,
5247
5261
(
2017
).
185.
E.
Ahmed
,
I.
Yaqoob
,
I. A. T.
Hashem
,
I.
Khan
,
A. I. A.
Ahmed
,
M.
Imran
, and
A. V.
Vasilakos
, “
The role of big data analytics in internet of things
,”
Comput. Networks
129
,
459
471
(
2017
).
186.
C.
Bennett
and
D.
Highfill
, “
Networking AMI smart meters
,” in
2008 IEEE Energy 2030 Conference
(
IEEE
,
2008
), pp.
1
8
.
187.
See http://www.sgcc.com.cn/html/sgcc_mobile/col2019042502/2019-05/22/20190522115939966121496_1.shtml for “
L. China State Grid Co
., Ltd., Big Data Center was Established” (last accessed May 22,
2019
).
188.
R. H.
Salim
,
K. R. C.
de Oliveira
,
A. D.
Filomena
,
M.
Resener
, and
A. S.
Bretas
, “
Hybrid fault diagnosis scheme implementation for power distribution systems automation
,”
IEEE Trans. Power Delivery
23
,
1846
1856
(
2008
).
189.
K.
Zhou
and
S.
Yang
, “
Demand side management in china: The context of china's power industry reform
,”
Renewable Sustainable Energy Rev.
47
,
954
965
(
2015
).
190.
S. S.
Reka
and
V.
Ramesh
, “
Demand side management scheme in smart grid with cloud computing approach using stochastic dynamic programming
,”
Perspect. Sci.
8
,
169
171
(
2016
).
191.
A.
Mellit
and
S. A.
Kalogirou
, “
Artificial intelligence techniques for photovoltaic applications: A review
,”
Prog. Energy Combust. Sci.
34
,
574
632
(
2008
).
192.
S.
Hongbin
, see http://www.cpnn.com.cn/zdyw/201904/t20190404_1128211.html for “
Ubiquitous Power Internet of Things Will Become an Important Practice of Energy Internet
” (last accessed April 21,
2019
).
193.
H.
Sun
,
Q.
Guo
,
B.
Zhang
,
W.
Wu
,
B.
Wang
,
X.
Shen
, and
J.
Wang
, “
Integrated energy management system: Concept, design, and demonstration in China
,”
IEEE Electr. Mag.
6
,
42
50
(
2018
).
194.
W.
Mesbah
, “
Securing smart electricity meters against customer attacks
,”
IEEE Trans. Smart Grid
9
,
101
110
(2018).