A Data-Driven Iterative Learning Approach for Optimizing the Train Control Strategy

doi:10.1109/TII.2022.3195888

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	A Data-Driven Iterative Learning Approach for Optimizing the Train Control Strategy
	Su, Shuai 3,4; Zhu, Qingyang 3,4; Liu, Junqing 3,4; Tang, Tao 3,4; Wei, Qinglai 1,2; Cao, Yuan 3,4
刊名	IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
	2023-07-01
卷号	19 期号:7 页码:7885-7893
关键词	Deep reinforcement learning (RL) driving strategy energy-efficient train control (EETC) soft actorcritic (SAC)
ISSN号	1551-3203
DOI	10.1109/TII.2022.3195888
通讯作者	Cao, Yuan(ycao@bjtu.edu.cn)
英文摘要	The energy-efficient train control (EETC) problem is investigated in this article. And a soft actor-critic (SAC)-based method is proposed to optimize the train driving strategy. First, EETC problem is converted to the inverse problem, i.e., minimizing the trip time of the journey with constant energy consumption. Based on the conversion, the EETC problem is reformulated as a finite Markov decision process, which can be solved by deep reinforcement learning algorithms. Second, an optimization method based on the SAC method is designed to calculate the optimal driving strategy of the train with introducing the reservoir sampling method. Finally, some case studies are conducted to verify the effectiveness and performance of the proposed method. Simulation results demonstrate that a good energy-saving performance can be achieved. In single interval, the SAC-based method can reduce about 1.65% of the energy consumption compared with numerical method. And the energy consumption reduction can be extended to be 6.49% when the proposed approach is applied in multiple intervals.
资助项目	National Natural Science Foundation of China[52172322] ; National Natural Science Foundation of China[U22A2046] ; Beijing Natural Science Foundation[L191015] ; Beijing Natural Science Foundation[L201004] ; State Key Laboratory of Rail Traffic Control and Safety[RCS2022ZZ003]
WOS关键词	SYSTEM ; SUBWAY ; OPTIMIZATION
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001020261500004
资助机构	National Natural Science Foundation of China ; Beijing Natural Science Foundation ; State Key Laboratory of Rail Traffic Control and Safety
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53798]
专题	多模态人工智能系统全国重点实验室
通讯作者	Cao, Yuan
作者单位	1.Univ Chinese Acad Sci, Inst Automat, Chinese Acad Sci, Sch Artificial Intelligence,Key Lab Management & C, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100049, Peoples R China 3.Beijing Jiaotong Univ, State Key Lab Rail Traff Control & Safety, Beijing 100044, Peoples R China 4.Beijing Jiaotong Univ, Frontiers Sci Ctr Smart High speed Railway Syst, Beijing 100044, Peoples R China
推荐引用方式 GB/T 7714	Su, Shuai,Zhu, Qingyang,Liu, Junqing,et al. A Data-Driven Iterative Learning Approach for Optimizing the Train Control Strategy[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2023,19(7):7885-7893.
APA	Su, Shuai,Zhu, Qingyang,Liu, Junqing,Tang, Tao,Wei, Qinglai,&Cao, Yuan.(2023).A Data-Driven Iterative Learning Approach for Optimizing the Train Control Strategy.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,19(7),7885-7893.
MLA	Su, Shuai,et al."A Data-Driven Iterative Learning Approach for Optimizing the Train Control Strategy".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 19.7(2023):7885-7893.