AC REINFORCEMENT LEARNING DYNAMIC OPTIMIZATION OF PHOTOVOLTAIC SYSTEM ACTIVE DISTURBANCE REJECTION POWER TRACKING CONTROL

Zhou Xuesong; Geng Shengyi; Ma Youjie; Chen Yunfei; Ma Licong; Li Shuang

doi:10.19912/j.0254-0096.tynxb.2025-0335

PDF(2393 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (7) : 427-438. DOI: 10.19912/j.0254-0096.tynxb.2025-0335

AC REINFORCEMENT LEARNING DYNAMIC OPTIMIZATION OF PHOTOVOLTAIC SYSTEM ACTIVE DISTURBANCE REJECTION POWER TRACKING CONTROL

Zhou Xuesong, Geng Shengyi, Ma Youjie, Chen Yunfei, Ma Licong, Li Shuang

Author information +

History +

Abstract

Due to the influence of external conditions such as irradiance, the maximum power point of the photovoltaic system fluctuates frequently, and the traditional adjustment method is slow in tracking speed, poor anti-interference ability, and parameters that are difficult to adjust parameters, resulting in violent power fluctuations in the power of the photovoltaic power generation system. Therefore, This paper proposes an AC reinforcement learning dynamic optimization for active disturbance rejection power tracking control of photovoltaic systems. Firstly, variable step size P&O is used to achieve MPPT control, and then linear active disturbance rejection control（LADRC） is designed to achieve decoupling. Then, the AC reinforcement learning algorithm is combined to dynamically adjust the parameters of the linear tracking differentiator （LTD）, so that the active power output of the photovoltaic power generation system can be quickly tracked to the maximum power point. Finally, the system model is built in the digital simulation platform, and through comparative analysis, it is verified that AC-LADRC control can significantly improve the response speed, achieve no overshoot-free control, and greatly improve the tracking accuracy, up to 99.8%, showing good tracking performance when the external environment changes dramatically.

Key words

photovoltaic power generation / ADRC / tracking accuracy / reinforcement learning / power oscillation / extended state observer

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhou Xuesong, Geng Shengyi, Ma Youjie, Chen Yunfei, Ma Licong, Li Shuang. AC REINFORCEMENT LEARNING DYNAMIC OPTIMIZATION OF PHOTOVOLTAIC SYSTEM ACTIVE DISTURBANCE REJECTION POWER TRACKING CONTROL[J]. Acta Energiae Solaris Sinica. 2026, 47(7): 427-438 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0335

References

[1] 方宇晨, 杜尔顺, 余扬昊, 等. 太阳能光热发电并网的综合效益量化评估方法[J]. 中国电机工程学报, 2024, 44(13): 5135-5147.
Fang Y C, Du E S, Yu Y H, et al.Comprehensive Benefit analytical evaluation of gird-connected concentrating solar power[J]. Proceedings of the CSEE,2024,44(13):5135-5147.
[2] 俞鸿飞, 王韵楚, 吕瑞扬, 等. 考虑灵活爬坡产品的虚拟电厂两阶段分布鲁棒优化运营策略[J]. 电力系统自动化, 2024, 48(14): 16-27.
Yu H F, Wang Y C, Lyu R Y, et al.Two-stage distributionally robust optimization operation strategy of virtual power plants considering flexible ramping products[J]. Automation of Electric Power Systems, 2024, 48(14): 16-27.
[3] 郭威, 孙胜博, 陶鹏, 等. 基于多元变分模态分解和混合深度神经网络的短期光伏功率预测[J]. 太阳能学报, 2024, 45(4): 489-499.
Guo W, Sun S B, Tao P, et al.Short-term photovoltaic power forecasting based on multivariate variational mode decomposition and hybrid deep neural network[J]. Acta Energiae Solaris Sinica, 2024, 45(4): 489-499.
[4] 樊立萍, 陈其鹏. 基于萤火虫优化模糊P&O的微生物燃料电池最大功率点跟踪[J]. 太阳能学报, 2024, 45(4): 373-381.
Fan L P, Chen Q P.Maximum power point tracking of microbial fuel cell based on firefly optimization fuzzy P & O[J]. Acta Energiae Solaris Sinica, 2024, 45(4): 373-381.
[5] 张东宁. 基于改进电导增量法的光伏最大功率点跟踪策略研究[J]. 太阳能学报, 2022, 43(8): 82-90.
Zhang D N.Research on photovoltaic maximum power point tracking strategy based on improved conductance increment method[J]. Acta Energiae Solaris Sinica, 2022, 43(8): 82-90.
[6] Abdelsalam A K, Massoud A M, Ahmed S, et al.High-performance adaptive perturb and observe MPPT technique for photovoltaic-based microgrids[J]. IEEE Transactions on Power Electronics, 2011, 26(4): 1010-1021.
[7] 刘瑞阳, 薛云灿, 冯宝玥, 等. 光伏发电系统模糊分段变步长算法最大功率点跟踪策略[J]. 热力发电, 2016, 45(5): 48-53.
Liu R Y, Xue Y C, Feng B Y, et al.A new control strategy for MPPT in photovoltaic system based on fuzzy and variable step size algorithm[J]. Thermal Power Generation, 2016, 45(5): 48-53.
[8] Rai A K, Kaushika N D, Singh B, et al.Simulation model of ANN based maximum power point tracking controller for solar PV system[J]. Solar Energy Materials and Solar Cells, 2011, 95(2): 773-778.
[9] 张增辉, 邓宇豪, 李春卫, 等. 基于改进灰狼优化算法的光伏MPPT方法[J]. 电测与仪表, 2022, 59(7): 100-105.
Zhang Z H, Deng Y H, Li C W, et al.Photovoltaic MPPT method based on improved grey wolf optimization algorithm[J]. Electrical Measurement & Instrumentation, 2022, 59(7): 100-105.
[10] Kofinas P, Doltsinis S, Dounis A I, et al.A reinforcement learning approach for MPPT control method of photovoltaic sources[J]. Renewable Energy, 2017, 108: 461-473.
[11] 张世欣, 皇金锋, 杨艺. 基于平坦理论的直流微电网双向DC-DC变换器改进滑模自抗扰控制[J]. 电力系统保护与控制, 2023, 51(5): 107-116.
Zhang S X, Huang J F, Yang Y.Improved sliding mode and active disturbance rejection control based on flatness theory for a bi-directional DC-DC converter in a DC microgrid[J]. Power System Protection and Control, 2023, 51(5): 107-116.
[12] 高志强, 李松, 周雪松, 等. 线性自抗扰在光伏发电系统MPPT中的应用[J]. 电力系统保护与控制, 2018, 46(15): 52-59.
Gao Z Q, Li S, Zhou X S, et al.Design of MPPT controller for photovoltaic generation system based on LADRC[J]. Power System Protection and Control, 2018, 46(15): 52-59.
[13] 马幼捷, 韩志国, 周雪松. 结合模糊自抗扰策略的光伏MPPT控制技术[J]. 电工技术, 2022(24): 168-171.
Ma Y J, Han Z G, Zhou X S.Photovoltaic MPPT control technology combined with fuzzy active disturbance rejection strategy[J]. Electric Engineering, 2022(24): 168-171.
[14] 李练兵, 王兰超, 朱乐, 等. 自适应免疫粒子群算法在光伏MPPT中的应用[J]. 电源技术, 2024, 48(4): 749-754.
Li L B, Wang L C, Zhu L, et al.Application of adaptive immune particle swarm optimization in photovoltaic MPPT[J]. Chinese Journal of Power Sources, 2024, 48(4): 749-754.
[15] 王有张. 光伏发电系统MPPT控制策略研究[D]. 兰州: 兰州理工大学, 2023.
Wang Y Z.Research on MPPT control strategy of photovoltaic power generation system[D]. Lanzhou: Lanzhou University of Technology, 2023.
[16] 赵靖. 基于变步长增量电导法的光伏发电系统MPPT控制[D]. 重庆: 重庆大学, 2014.
Zhao J.MPPT of PV generation system based on variable step-size INC method[D]. Chongqing: Chongqing University, 2014.
[17] 马幼捷, 袁业沧, 周雪松, 等. 模型信息联合校正型自抗扰控制策略[J]. 太阳能学报, 2024, 45(3): 389-398.
Ma Y J, Yuan Y C, Zhou X S, et al.Model information combined correction active disturbance rejection voltage stabilizing control strategy[J]. Acta Energiae Solaris Sinica, 2024, 45(3): 389-398.
[18] 徐晓宁, 周雪松, 马幼捷, 等. 基于自抗扰控制技术的微网运行控制器[J]. 高电压技术, 2016, 42(10): 3336-3346.
Xu X N, Zhou X S, Ma Y J, et al.Micro grid operation controller based on ADRC[J]. High Voltage Engineering, 2016, 42(10): 3336-3346.
[19] 马良玉, 王月, 马进. 基于PI参数的二阶线性自抗扰控制参数整定[J]. 控制工程, 2024, 31(10): 1761-1767.
Ma L Y, Wang Y, Ma J.Parameter tuning of second-order linear active disturbance rejection control based on PI parameters[J]. Control Engineering of China, 2024, 31(10): 1761-1767.
[20] 孟凡东. 自抗扰控制器的设计与应用研究[D]. 哈尔滨: 哈尔滨理工大学, 2009.
Meng F D.Study of design and application for the active disturbance rejection controller[D]. Harbin: Harbin University of Science and Technology, 2009.
[21] Wang Y C, Fang S H, Hu J X.Active disturbance rejection control based on deep reinforcement learning of PMSM for more electric aircraft[J]. IEEE Transactions on Power Electronics, 2023, 38(1): 406-416.
[22] Xie X W.PSS control of multi machine power system using reinforcement learning[C]//2021 5th International Conference on Robotics and Automation Sciences (ICRAS). Wuhan, China, 2021: 132-135.
[23] 吴学礼, 宋凯, 史思远, 等. 基于改进马尔可夫随机场探地雷达有效信号提取方法[J]. 科学技术与工程, 2023, 23(30): 13031-13039.
Wu X L, Song K, Shi S Y, et al.Effective signal extraction method of ground-penetrating radar based on improved Markov random field[J]. Science Technology and Engineering, 2023, 23(30): 13031-13039.
[24] Sehgal A, La H, Louis S, et al.Deep reinforcement learning using genetic algorithm for parameter optimization[C]//2019 Third IEEE International Conference on Robotic Computing (IRC). Naples, Italy, 2019: 596-601.
[25] 尚立, 蔡硕, 崔俊彬, 等. 基于软件定义网络的电网边缘计算资源分配[J]. 电力系统保护与控制, 2021, 49(20): 136-143.
Shang L, Cai S, CuI J B, et al. SDN-based MEC resource allocation of a power grid[J]. Power System Protection and Control, 2021, 49(20): 136-143.
[26] 刘全, 翟建伟, 章宗长, 等. 深度强化学习综述[J]. 计算机学报, 2018, 41(1): 1-27.
Liu Q, Zhai J W, Zhang Z C, et al.A survey on deep reinforcement learning[J]. Chinese Journal of Computers, 2018, 41(1): 1-27.