Supervised assisted deep reinforcement learning for emergency voltage control of power systems

doi:10.1016/j.neucom.2021.12.043

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	Supervised assisted deep reinforcement learning for emergency voltage control of power systems
	Li, Xiaoshuang 2,5; Wang, Xiao 3,5; Zheng, Xinhu 4; Dai, Yuxin 6; Yu, Zhihong 1; Zhang, Jun Jason 6; Bu, Guangquan 1; Wang, Fei-Yue 5
刊名	NEUROCOMPUTING
	2022-02-28
卷号	475 页码:69-79
关键词	Deep reinforcement learning Behavioral cloning Dynamic demonstration Emergency control
ISSN号	0925-2312
DOI	10.1016/j.neucom.2021.12.043
通讯作者	Wang, Fei-Yue(feiyue.wang@ia.ac.cn)
英文摘要	The increasing complexity of power systems makes existing deep reinforcement learning-based emergency voltage control methods face challenges in learning speed and data utilization efficiency. Meanwhile, the accumulated data containing expert experience and domain knowledge has not been fully utilized to improve the performance of the deep reinforcement learning methods. To address the above issues, a novel hybrid emergency voltage control method that combines expert experience and machine intelligence is proposed in this paper. Specifically, the expert experience in the off-line demonstration is extracted through a behavioral cloning model and the deep reinforcement learning method is applied to discover and learn new knowledge autonomously. A special supervised expert loss is designed to utilize the pre-trained behavioral cloning model to assist the self-learning process. The demonstration is dynamically updated during the training process such that the behavioral cloning model and the deep reinforcement learning model can facilitate each other continuously. Experiments are conducted on the open-source RLGC platform to validate the performance and the experimental results show that the proposed method can effectively improve the learning speed and the applicability of the model to different test situations. (c) 2021 Elsevier B.V. All rights reserved.
资助项目	National Key R&D Program of China[2018AAA0101500] ; National Key R&D Program of China[2018AAA0101502]
WOS关键词	GAME ; GO
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000761797700006
资助机构	National Key R&D Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48047]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Wang, Fei-Yue
作者单位	1.China Elect Power Res Inst, State Key Lab Power Grid Safety & Energy Conserva, Beijing 100192, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Qingdao Acad Intelligent Ind, Parallel Intelligence Res Ctr, Qingdao 266109, Peoples R China 4.Univ Minnesota, Dept Elect & Comp Engn, Minneapolis, MN 55455 USA 5.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 6.Wuhan Univ, Sch Elect Engn & Automat, Wuhan 430072, Peoples R China
推荐引用方式 GB/T 7714	Li, Xiaoshuang,Wang, Xiao,Zheng, Xinhu,et al. Supervised assisted deep reinforcement learning for emergency voltage control of power systems[J]. NEUROCOMPUTING,2022,475:69-79.
APA	Li, Xiaoshuang.,Wang, Xiao.,Zheng, Xinhu.,Dai, Yuxin.,Yu, Zhihong.,...&Wang, Fei-Yue.(2022).Supervised assisted deep reinforcement learning for emergency voltage control of power systems.NEUROCOMPUTING,475,69-79.
MLA	Li, Xiaoshuang,et al."Supervised assisted deep reinforcement learning for emergency voltage control of power systems".NEUROCOMPUTING 475(2022):69-79.