Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks

	Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks
	Wang, Jianhong 1; Xu, Wangkun 1; Gu, Yunjie 2; Song, Wenbin3 ; Green, Tim C.1
	2021
会议录名称	ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS
ISSN	1049-5258
卷号	5
页码	3271-3284
摘要	This paper presents a problem in power networks that creates an exciting and yet challenging real-world scenario for application of multi-agent reinforcement learning (MARL). The emerging trend of decarbonisation is placing excessive stress on power distribution networks. Active voltage control is seen as a promising solution to relieve power congestion and improve voltage quality without extra hardware investment, taking advantage of the controllable apparatuses in the network, such as roof-top photovoltaics (PVs) and static var compensators (SVCs). These controllable apparatuses appear in a vast number and are distributed in a wide geographic area, making MARL a natural candidate. This paper formulates the active voltage control problem in the framework of Dec-POMDP and establishes an open-source environment. It aims to bridge the gap between the power community and the MARL community and be a drive force towards real-world applications of MARL algorithms. Finally, we analyse the special characteristics of the active voltage control problems that cause challenges (e.g. interpretability) for state-of-the-art MARL approaches, and summarise the potential directions. © 2021 Neural information processing systems foundation. All rights reserved.
关键词	Electric network analysis Electric power system control Electric power transmission networks Multi agent systems Reinforcement learning Static Var compensators Voltage control Active voltage controls Control problems Decarbonisation Emerging trends Multi-agent reinforcement learning Power congestions Power distribution network Power networks Real-world scenario Voltage quality
会议名称	35th Conference on Neural Information Processing Systems, NeurIPS 2021
会议地点	Virtual, Online
会议日期	December 6, 2021 - December 14, 2021
收录类别	EI
语种	英语
出版者	Neural information processing systems foundation
EI入藏号	20222412231314
EI主题词	Quality control
EI分类号	703.1.1 Electric Network Analysis ; 704.2 Electric Equipment ; 706.1 Electric Power Systems ; 706.1.1 Electric Power Transmission ; 706.2 Electric Power Lines and Equipment ; 723.4 Artificial Intelligence ; 731.2 Control System Applications ; 731.3 Specific Variables Control ; 913.3 Quality Assurance and Control
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/251933
专题	信息科学与技术学院_硕士生
作者单位	1.Imperial College London, United Kingdom; 2.University of Bath, United Kingdom; 3.Shanghaitech University, China
推荐引用方式 GB/T 7714	Wang, Jianhong,Xu, Wangkun,Gu, Yunjie,et al. Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks[C]:Neural information processing systems foundation,2021:3271-3284.