基于强化学习策略的电网负荷频率控制

Abstract
Figure/Table
References
Related Citation (1)

Download: PDF (1240 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To achieve precise control of load frequency in new power systems and effectively address the challenges of nonlinearity, randomness, and uncertainty caused by the integration of large-scale renewable energy, an Actor-Critic deep reinforcement learning algorithm based on radial basis function (RBF) network is adopted to construct an load frequency control (LFC) strategy with adaptive proportional-integral-derivative (PID) control. First, the stable control structure of the power system and the dilemmas faced by LFC are analyzed. The advantages of intelligent control strategies are expounded, and modeling is completed, followed by the design of an adaptive optimization system. Through Matlab simulation, the controller is compared and analyzed with the particle swarm optimization (PSO)-tuned controller. The results show that the proposed controller significantly reduces the four error parameters of area control error (ACE) in the two areas, demonstrates stronger performance in minimizing ACE and reducing deviations, effectively improves the adaptability and robustness of LFC, and provides a new method with both theoretical and engineering values for the construction of new power systems.

Key words： load frequency control adaptive system reinforcement learning Actor-Critic algorithm

Received: 01 September 2025

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	GE Yafei
	ZENG Jiaqian
	SONG Qifan
	ZHANG Lu

Cite this article:

GE Yafei,ZENG Jiaqian,SONG Qifan等. Power grid load frequency control based on reinforcement learning strategies[J]. Electrical Engineering, 2026, 27(5): 20-27.

URL:

https://dqjs.cesmedia.cn/EN/Y2026/V27/I5/20

[1] 张智刚, 康重庆. 碳中和目标下构建新型电力系统的挑战与展望[J]. 中国电机工程学报, 2022, 42(8): 2806-2818.
[2] 丁俊, 王欣怡, 邵烨楠, 等. 新型电力系统的影响因素分析[J]. 电气技术, 2022, 23(7): 42-45.
[3] 周孝信, 陈树勇, 鲁宗相, 等. 能源转型中我国新一代电力系统的技术特征[J]. 中国电机工程学报, 2018, 38(7): 1893-1904, 2205.
[4] 杨超, 姚伟, 文劲宇. 基于事件驱动的含风电互联电网负荷频率鲁棒控制[J]. 电力系统自动化, 2018, 42(16): 57-64.
[5] 韩云昊, 马超, 朱银珠, 等. 考虑风能渗透的电力系统的负荷频率控制研究[J]. 控制工程, 2018, 25(11): 2046-2051.
[6] 鲁宗相, 李海波, 乔颖. 含高比例可再生能源电力系统灵活性规划及挑战[J]. 电力系统自动化, 2016, 40(13): 147-158.
[7] 郝学智. 含风储电力系统负荷频率控制策略研究[D]. 上海: 上海电力学院, 2018.
[8] 王政豪. 基于滑模控制的多区域互联电力系统负荷频率控制方法研究[D]. 上海: 上海电机学院, 2022.
[9] 彭晓楠. 欧洲大停电事件敲响能源转型警钟[J]. 生态经济, 2025, 41(7): 1-4.
[10] 曾辉, 孙峰, 李铁, 等. 澳大利亚“9·28”大停电事故分析及对中国启示[J]. 电力系统自动化, 2017, 41(13): 1-6.
[11] 陈宗遥, 卜旭辉, 郭金丽. 基于神经网络的数据驱动互联电力系统负荷频率控制[J]. 电工技术学报, 2022, 37(21): 5451-5461.
[12] 黄志华, 江鹿, 黄志飞, 等. 基于GUI的电力负荷频率控制仿真系统设计研究[J]. 电气技术与经济, 2024(12): 43-45.
[13] 顾雪平, 魏佳俊, 白岩松, 等. 基于分层模型预测控制的含风电电力系统恢复在线决策方法[J]. 电工技术学报, 2025, 40(5): 1471-1486.
[14] 赵兴勇. 含分布式新能源的微电网实验系统建设及应用[J]. 电气技术, 2018, 19(5): 33-38.
[15] 王宏东, 邓桂瑶. 基于荷电状态的多储能微电网改进下垂控制策略[J]. 电气技术, 2025, 26(4): 29-36.
[16] 张自东, 邱才明, 张东霞, 等. 基于深度强化学习的微电网复合储能协调控制方法[J]. 电网技术, 2019, 43(6): 1914-1921.
[17] 高冠中, 杨胜春, 郭晓蕊, 等. 深度强化学习在含分布式柔性资源的电网优化调度中的应用研究综述[J]. 中国电机工程学报, 2024, 44(16): 6385-6404.
[18] 张有兵, 林一航, 黄冠弘, 等. 深度强化学习在微电网系统调控中的应用综述[J]. 电网技术, 2023, 47(7): 2774-2788.
[19] 李鹏, 钟瀚明, 马红伟, 等. 基于深度强化学习的有源配电网多时间尺度源荷储协同优化调控[J]. 电工技术学报, 2025, 40(5): 1487-1502.
[20] 杨博, 陈义军, 姚伟, 等. 基于新一代人工智能技术的电力系统稳定评估与决策综述[J]. 电力系统自动化, 2022, 46(22): 200-223.
[21] Zhang Zidong, Zhang Dongxia, Qiu R C.Deep reinforcement learning for power system applications: an overview[J]. CSEE Journal of Power and Energy Systems, 2020, 6(1): 213-225.
[22] Grondman I, Busoniu L, Lopes G A D, et al. A survey of actor-critic reinforcement learning: standard and natural policy gradients[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 2012, 42(6): 1291-1307.
[23] Tan Wen.Unified tuning of PID load frequency controller for power systems via IMC[J]. IEEE Transactions on Power Systems, 2010, 25(1): 341-350.
[24] 孙林军. 智能PID控制研究[D]. 杭州: 浙江工业大学, 2003.
[25] 边泳名. PID控制器参数自整定的优化方法[D]. 青岛: 青岛科技大学, 2024.
[26] 王永骥, 涂健. 神经元网络控制[M]. 北京: 机械工业出版社, 1998: 68-85.
[27] Shangguan Xingchen, He Yong, Zhang Chuanke, et al.Sampled-data based discrete and fast load frequency control for power systems with wind power[J]. Applied Energy, 2020, 259: 114202.
[28] Guo Wentao, Liu Feng, Si J, et al.Online supplementary ADP learning controller design and application to power system frequency control with large-scale wind energy integration[J]. IEEE Trans- actions on Neural Networks and Learning Systems, 2016, 27(8): 1748-1761.