As a renewable energy source, solar energy has become essential to alleviate traditional energy scarcity because of its environmentally friendly characteristics. The intermittence and instability of solar energy bring challenges to energy utilization. Accurate solar radiation prediction models are necessary for the economical and reliable operation of building energy systems. Most existing models predict solar radiation based solely on time-dependent features and neglect the influence of spatial information, resulting in inferior prediction results. A novel hybrid spatiotemporal prediction model based on the graph attention network and bi-directional gated recurrent unit (GAT-BiGRU) is proposed in this paper. The GAT-BiGRU algorithm innovatively adopts the GAT to explore the spatial dependence of solar radiation from the graph topology, while the BiGRU is being applied to capture the temporal dynamic features of solar radiation. Detailed prediction experiments were conducted for the solar radiation of 16 districts in Tianjin. Compared with the state-of-the-art algorithms, the results indicate that the proposed model has a more robust generalization ability and minor prediction errors. Thus, it is expected to provide an effective reference for the actual operation strategy of solar building energy systems.
Skip Nav Destination
Article navigation
January 2025
Research Article|
February 03 2025
A novel hybrid spatiotemporal prediction algorithm of solar radiation based on topology and deep learning models
Mengge Wu
;
Mengge Wu
(Methodology, Software, Writing – original draft)
1
School of Artificial Intelligence, Hebei University of Technology
, Tianjin 300401, China
Search for other works by this author on:
Guixiang Xue
;
Guixiang Xue
a)
(Conceptualization, Funding acquisition, Methodology, Writing – original draft)
2
School of Civil and Transportation Engineering, Hebei University of Technology
, Tianjin 300401, China
a)Author to whom correspondence should be addressed: [email protected]
Search for other works by this author on:
Jiancai Song
;
Jiancai Song
(Investigation, Methodology, Resources)
3
School of Information and Engineering, Tianjin University of Commerce
, Tianjin 300430, China
Search for other works by this author on:
Shixu Zuo;
Shixu Zuo
(Software)
1
School of Artificial Intelligence, Hebei University of Technology
, Tianjin 300401, China
Search for other works by this author on:
Ruomeng Li;
Ruomeng Li
(Validation, Visualization)
1
School of Artificial Intelligence, Hebei University of Technology
, Tianjin 300401, China
Search for other works by this author on:
Guowei Ma
Guowei Ma
(Funding acquisition, Project administration, Supervision)
2
School of Civil and Transportation Engineering, Hebei University of Technology
, Tianjin 300401, China
Search for other works by this author on:
a)Author to whom correspondence should be addressed: [email protected]
J. Renewable Sustainable Energy 17, 016103 (2025)
Article history
Received:
August 30 2024
Accepted:
January 19 2025
Citation
Mengge Wu, Guixiang Xue, Jiancai Song, Shixu Zuo, Ruomeng Li, Guowei Ma; A novel hybrid spatiotemporal prediction algorithm of solar radiation based on topology and deep learning models. J. Renewable Sustainable Energy 1 January 2025; 17 (1): 016103. https://doi.org/10.1063/5.0236144
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
3
Views
Citing articles via
Efficient wind farm layout optimization with the FLOWERS AEP model and analytic gradients
Michael J. LoCascio, Christopher J. Bay, et al.
Machine learning for modern power distribution systems: Progress and perspectives
Marija Marković, Matthew Bossart, et al.
Improving academic–industry collaboration: A case study of UK distribution system operators
Jamie M. Bright, Hilal Ozdemir, et al.
Related Content
Enhancing fluid identification via an innovative transformer model with bidirectional recurrent units network leveraging well logging data
Physics of Fluids (July 2024)
Assessment of hybrid bidirectional deep learning models for short-term global horizontal irradiance forecasting
AIP Conf. Proc. (November 2024)
Short-term multi-step forecasting of rooftop solar power generation using a combined data decomposition and deep learning model of EEMD-GRU
J. Renewable Sustainable Energy (January 2024)
Integrating spatio-positional series attention to deep network for multi-turbine short-term wind power prediction
J. Renewable Sustainable Energy (February 2024)
The identification of gas–liquid two-phase flow patterns in a centrifugal pump with an imbalanced sample and variable rotational speeds
Physics of Fluids (February 2024)