Controlling wind farm wake interactions is crucial for enhancing power generation efficiency, especially under the challenge of fluctuating wind conditions. This study tackles this imperative by leveraging deep reinforcement learning (DRL) to refine yaw control strategies. The approach innovatively segments wind conditions into discrete intervals, each governed by a customized DRL control policy, adeptly handling variability to bolster the system's adaptive capability and power generation efficiency. The comparative analysis incorporates traditional greedy control, differential evolution optimal control, model predictive control, and the DRL-based strategy, with evaluations grounded in extensive simulations and wind tunnel tests. The experiments conducted represent a notable step forward, providing empirical evidence of the DRL strategy's effectiveness in practical applications for the first time. The DRL approach, characterized by its model-free adaptability across diverse wind scenarios, achieves a notable 9.27% enhancement in total power output compared to greedy control during gust events. This underscores the strategy's capacity to not only maintain but also surpass total power output benchmarks under varying wind conditions, while concurrently mitigating mechanical stress on turbines. The DRL-controlled policy's robust adaptation to wake steering and alignment, sans explicit models, optimizes total power production and underscores its practical applicability in real-world contexts.
REFERENCES
1.
T.
Zhang
, D.
Yuan
, Q.
Guo
, F.
Qiu
, D.
Yang
, and Z.
Ou
, “Preparation of a renewable biomass carbon aerogel reinforced with sisal for oil spillage clean-up: Inspired by green leaves to green
,” Food Bioprod. Process.
114
, 154
–162
(2019
).2.
R.
Osae
, G.
Essilfie
, R. N.
Alolga
, E.
Bonah
, H.
Ma
, and C.
Zhou
, “Drying of ginger slices—Evaluation of quality attributes, energy consumption, and kinetics study
,” J. Food Process Eng.
43
(2
), e13348
(2020
).3.
L.
Huang
, W.
Zhang
, J.
Cheng
, and Z.
Lu
, “Antioxidant and physicochemical properties of soluble dietary fiber from garlic straw as treated by energy-gathered ultrasound
,” Int. J. Food Prop.
22
(1
), 678
–688
(2019
).4.
M. A.
Khan
, A.
Javed
, S.
Shakir
, and A. H.
Syed
, “Optimization of a wind farm by coupled actuator disk and mesoscale models to mitigate neighboring wind farm wake interference from repowering perspective
,” Appl. Energy
298
, 117229
(2021
).5.
S.
Asadollah
, R.
Zhu
, and M.
Liserre
, “Analysis of voltage control strategies for wind farms
,” IEEE Trans. Sustainable Energy
11
(2
), 1002
–1012
(2020
).6.
W.
Longyan
et al, “Spatiotemporal wake field reconstruction of wind turbine coupled with wind speed measurements
,” J. Drain. Irrig. Mach. Eng.
43
(3
), 260
–267
(2025
).7.
L.
Keding
et al, “Atmospheric stability based on mesoscale simulations and it′s impact on operational characteristics of wind farms
,” J. Drain. Irrig. Mach. Eng.
43
(1
), 87
–93
(2025
).8.
H.
Dong
, J.
Xie
, and X.
Zhao
, “Wind farm control technologies: From classical control to reinforcement learning
,” Prog. Energy
4
(3
), 032006
(2022
).9.
J. G.
Njiri
, N.
Beganovic
, M. H.
Do
, and D.
Söffker
, “Consideration of lifetime and fatigue load in wind turbine control
,” Renewable Energy
131
, 818
–828
(2019
).10.
L.
Woolcock
, V.
Liu
, A.
Witherby
, R.
Schmid
, and A.
Mahdizadeh
, “Comparison of REWS and LIDAR-based feedforward control for fatigue load mitigation in wind turbines
,” Control Eng. Pract.
138
, 105477
(2023
).11.
K.
Yang
, G.
Kwak
, K.
Cho
, and J.
Huh
, “Wind farm layout optimization for wake effect uniformity
,” Energy
183
, 983
–995
(2019
).12.
L.
Cao
, M.
Ge
, X.
Gao
, B.
Du
, B.
Li
, Z.
Huang
, and Y.
Liu
, “Wind farm layout optimization to minimize the wake induced turbulence effect on wind turbines
,” Appl. Energy
323
, 119599
(2022
).13.
D.
van der Hoek
, S.
Kanev
, J.
Allin
, D.
Bieniek
, and N.
Mittelmeier
, “Effects of axial induction control on wind farm energy production - A field test
,” Renewable Energy
140
, 994
–1003
(2019
).14.
G.
Armengol Barcos
and F.
Porté-Agel
, “Enhancing wind farm performance through axial induction and tilt control: Insights from wind tunnel experiments
,” Energies
17
(1
), 203
(2023
).15.
Z.
Lin
, Z.
Chen
, Q.
Wu
, S.
Yang
, and H.
Meng
, “Coordinated pitch & torque control of large-scale wind turbine based on Pareto efficiency analysis
,” Energy
147
, 812
–825
(2018
).16.
R.
He
, H.
Yang
, and L.
Lu
, “Optimal yaw strategy and fatigue analysis of wind turbines under the combined effects of wake and yaw control
,” Appl. Energy
337
, 120878
(2023
).17.
M.
Lin
and F.
Porté-Agel
, “Wake meandering of wind turbines under dynamic yaw control and impacts on power and fatigue
,” Renewable Energy
223
, 120003
(2024
).18.
T.
Tao
, Y.
Yang
, T.
Yang
, S.
Liu
, X.
Guo
, H.
Wang
, Z.
Liu
, W.
Chen
, C.
Liang
, K.
Long
, and M.
Chen
, “Time-domain fatigue damage assessment for wind turbine tower bolts under yaw optimization control at offshore wind farm
,” Ocean Eng.
303
, 117706
(2024
).19.
R.
Nash
, R.
Nouri
, and A.
Vasel-Be-Hagh
, “Wind turbine wake control strategies: A review and concept proposal
,” Energy Convers. Manage.
245
, 114581
(2021
).20.
M.
Barzegar-Kalashani
, M.
Seyedmahmoudian
, S.
Mekhilef
, A.
Stojcevski
, and B.
Horan
, “Small-scale wind turbine control in high-speed wind conditions: A review
,” Sustainable Energy Technol.
60
, 103577
(2023
).21.
A. C.
Kheirabadi
and R.
Nagamune
, “A quantitative review of wind farm control with the objective of wind farm power maximization
,” J. Wind Eng. Ind. Aerodyn.
192
, 45
–73
(2019
).22.
C.
Huang
and J.
Zhuang
, “Active disturbance rejection control and multi-objective optimization for wind turbine active power regulation
,” Control Eng. Pract.
141
, 105709
(2023
).23.
M.
Bourhis
, M.
Pereira
, and F.
Ravelet
, “Experimental investigation of the effects of the Reynolds number on the performance and near wake of a wind turbine
,” Renewable Energy
209
, 63
–70
(2023
).24.
Y.
Huang
and X.
Zhao
, “Reinforcement Learning-Based Multiobjective Control of Grid-Connected Wind Farms
,” IEEE Trans. Ind. Inf.
20
(5
), 7380
–7390
(2024
).25.
Y.
Zhang
, X.
Chen
, S.
Gong
, and J.
Chen
, “Collective large-scale wind farm multivariate power output control based on hierarchical communication multi-agent proximal policy optimization
,” Renewable Energy
219
, 119479
(2023
).26.
B. M.
Doekemeijer
, D.
van der Hoek
, and J.-W.
van Wingerden
, “Closed-loop model-based wind farm control using FLORIS under time-varying inflow conditions
,” Renewable Energy
156
, 719
–730
(2020
).27.
D.
Song
, J.
Liu
, Y.
Yang
, J.
Yang
, M.
Su
, Y.
Wang
, N.
Gui
, X.
Yang
, L.
Huang
, and Y.
Hoon Joo
, “Maximum wind energy extraction of large-scale wind turbines using nonlinear model predictive control via Yin-Yang grey wolf optimization algorithm
,” Energy
221
, 119866
(2021
).28.
D.
Song
, Q.
Chang
, S.
Zheng
, S.
Yang
, J.
Yang
, and Y. H.
Joo
, “Adaptive model predictive control for yaw system of variable-speed wind turbines
,” J. Mod. Power Syst. Clean Energy
9
(1
), 219
–224
(2021
).29.
X.
Liu
, Y.
Zhang
, and K. Y.
Lee
, “Coordinated distributed MPC for load frequency control of power system with wind farms
,” IEEE Trans. Ind. Electron.
64
(6
), 5140
–5150
(2017
).30.
J. J. P.
Martinez
and J.
Coussy
, “Wake steering experiments in onshore and offshore wind farms
,” J. Phys: Conf. Ser.
2767
(9
), 092090
(2024
).31.
J. d J.
Monjardín-Gámez
, R.
Campos-Amezcua
, R.
Gómez-Martínez
, R.
Sánchez-García
, A.
Campos-Amezcua
, L. G.
Trujillo-Franco
, and H. F.
Abundis-Fong
, “Large eddy simulation and experimental study of the turbulence on wind turbines
,” Energy
273
, 127234
(2023
).32.
M.
Sun
, C.
Feng
, and J.
Zhang
, “Conditional aggregated probabilistic wind power forecasting based on spatio-temporal correlation
,” Appl. Energy
256
, 113842
(2019
).33.
S.
Vijayshankar
, P.
Stanfel
, J.
King
, E.
Spyrou
, and K.
Johnson
, “Deep reinforcement learning for automatic generation control of wind farms
,” in 2021 American Control Conference (ACC)
(IEEE
, 2021
), pp. 1796
–1802
.34.
B.
He
, H.
Zhao
, G.
Liang
, J.
Zhao
, J.
Qiu
, and Z. Y.
Dong
, “Ensemble-based Deep Reinforcement Learning for robust cooperative wind farm control
,” Int. J. Electr. Power Energy Syst.
143
, 108406
(2022
).35.
T.
Kim
, C.
Kim
, J.
Song
, and D.
You
, “Optimal control of a wind farm in time-varying wind using deep reinforcement learning
,” Energy
303
, 131950
(2024
).36.
J.
Liew
, T.
Göçmen
, W. H.
Lio
, and G. Chr.
Larsen
, “Model-free closed-loop wind farm control using reinforcement learning with recursive least squares
,” Wind Energy
27
(11
), 1173
–1187
(2024
).37.
S.
Peng
and Q.
Feng
, “Data-driven optimal control of wind turbines using reinforcement learning with function approximation
,” Comput. Ind. Eng.
176
, 108934
(2023
).38.
Z.
Deng
, C.
Xu
, X.
Han
, Z.
Cheng
, and F.
Xue
, “Decentralized yaw optimization for maximizing wind farm production based on deep reinforcement learning
,” Energy Convers. Manage.
286
, 117031
(2023
).39.
H.
Zhao
, J.
Zhao
, J.
Qiu
, G.
Liang
, and Z. Y.
Dong
, “Cooperative wind farm control with deep reinforcement learning and knowledge-assisted learning
,” IEEE Trans. Ind. Inf.
16
(11
), 6912
–6921
(2020
).40.
J.
Xie
, H.
Dong
, X.
Zhao
, and A.
Karcanias
, “Wind farm power generation control via double-network-based deep reinforcement learning
,” IEEE Trans. Ind. Inf.
18
(4
), 2321
–2330
(2022
).41.
D. U.
Yunchao
et al, “Effect of wind direction changing speed on power and speed of wind turbine
,” J. Drain. Irrig. Mach. Eng.
41
(2
), 167
–172
(2023
).42.
G.
Tao
et al, “Influence of dynamic wind direction on evolution law of wind turbine wake
,” J. Drain. Irrig. Mach. Eng.
41
(12
), 1255
–1260
(2023
).43.
L.
Yan
et al, “Numerical simulation of starting performance of vertical axis wind turbine with B-Spline curve wind gathering devices
,” J. Drain. Irrig. Mach. Eng.
42
(3
), 265
–272
(2024
).44.
L.
Zhen
et al, “Experimental study on influence of dynamic change of crosswind angle on strain of wind turbine blades
,” J. Drain. Irrig. Mach. Eng.
41
(5
), 499
–504
(2023
).45.
W.
Jianwen
et al, “Experimental study on dynamic stress of blades with different materials under wind direction change
,” J. Drain. Irrig. Mach. Eng.
42
(3
), 273
–281
(2024
).46.
L.
Yan
et al, “Numerical simulation of aerodynamic characteristics of straight-bladed vertical axis wind turbine with large solidities
,” J. Drain. Irrig. Mach. Eng.
40
(7
), 701
–706
(2022
).47.
M. H.
Ahmed
, A.
AboHussien
, A.
El-Shafei
, A. M.
Darwish
, and A. H.
Abdel-Gawad
, “Active control of flexible rotors using deep reinforcement learning with application of multi-actor-critic deep deterministic policy gradient
,” Eng. Appl. Artif. Intell.
124
, 106593
(2023
).48.
P.
Yang
and H.
Najafi
, “The effect of using different wake models on wind farm layout optimization: A comparative study
,” J. Energy Res. Technol.
144
(070904
), 070904
(2022
).49.
J.
King
, P.
Fleming
, R.
King
, L. A.
Martínez-Tossas
, C. J.
Bay
, R.
Mudafort
, and E.
Simley
, “Control-oriented model for secondary effects of wake steering
,” Wind Energy Sci.
6
(3
), 701
–714
(2021
).50.
P. M.
Anderson
and A.
Bose
, “Stability simulation of wind turbine systems
,” IEEE Trans. Power Appar. Syst.
PAS-102
(12
), 3791
–3795
(1983
).51.
M.
Bastankhah
and F.
Porté-Agel
, “A new miniature wind turbine for wind tunnel experiments. Part I: Design and performance
,” Energies
10
(7
), 908
(2017
).52.
S.
Jeon
, B.
Kim
, and J.
Huh
, “Comparison and verification of wake models in an onshore wind farm considering single wake condition of the 2 MW wind turbine
,” Energy
93
, 1769
–1777
(2015
).53.
K.
Shibuya
and T.
Uchida
, “Wake asymmetry of yaw state wind turbines induced by interference with wind towers
,” Energy
280
, 128091
(2023
).54.
Z.
Wang
, W.
Tian
, and H.
Hu
, “A Comparative study on the aeromechanic performances of upwind and downwind horizontal-axis wind turbines
,” Energy Convers. Manage.
163
, 100
–110
(2018
).55.
B.
Zhang
, W.
Luo
, Z.
Luo
, J.
Xu
, and L.
Wang
, “Effectiveness of wake control optimization for multiple in-line wind turbines by combinatorial machine learning wake model
,” Proc. Inst. Mech. Eng., Part C: J. Mech. Eng. Sci.
238
(5
), 1280
–1294
(2024
).56.
B.
Zhang
, J.
Xu
, W.
Luo
, Z.
Luo
, and L.
Wang
, “Study of cooperative wake control for multiple wind turbines under variable wind speeds/directions
,” Proc. Inst. Mech. Eng., Part A: J. Power Energy
237
(7
), 1615
–1627
(2023
).57.
C.
Wang
, J.
Zhang
, A.
Wang
, Z.
Wang
, N.
Yang
, Z.
Zhao
, C. S.
Lai
, and L. L.
Lai
, “Prioritized sum-tree experience replay TD3 DRL-based online energy management of a residential microgrid
,” Appl. Energy
368
, 123471
(2024
).58.
S.
Fujimoto
, H.
van Hoof
, and D.
Meger
, “Addressing function approximation error in actor-critic methods
,” in International Conference on Machine Learning
(2018
).59.
L.
Wang
, Q.
Dong
, Y.
Fu
, B.
Zhang
, M.
Chen
, J.
Xie
, J.
Xu
, and Z.
Luo
, “Effectiveness of cooperative yaw control based on reinforcement learning for in-line multiple wind turbines
,” Control Eng. Pract.
153
, 106124
(2024
).60.
L.
Wang
, W.
Luo
, J.
Xu
, J.
Xie
, Z.
Luo
, and A. C. C.
Tan
, “Comparative study of decentralized instantaneous and wind-interval-based controls for in-line two scale wind turbines
,” Renewable Energy
189
, 1218
–1233
(2022
).61.
L.
Wang
, J.
Xie
, W.
Luo
, Z.
Wang
, B.
Zhang
, M.
Chen
, and A. C. C.
Tan
, “Effectiveness of data-driven wind turbine wake models developed by machine/deep learning with spatial-segmentation technique
,” Sustainable Energy Technol. Assess.
53
, 102499
(2022
).62.
M. F.
Howland
, S. K.
Lele
, and J. O.
Dabiri
, “Wind farm power optimization through wake steering
,” Proc. Natl. Acad. Sci. USA
116
(29
), 14495
–14500
(2019
).© 2025 Author(s). Published under an exclusive license by AIP Publishing.
2025
Author(s)
You do not currently have access to this content.
