Optimal Elevator Group Control via Deep Asynchronous Actor-Critic Learning | |
Wei, Qinglai1,2,6; Wang, Lingxiao1,2,6; Liu, Yu5; Polycarpou, Marios M.3,4 | |
刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
2020-12-01 | |
卷号 | 31期号:12页码:5245-5256 |
关键词 | Elevators Optimal control Backpropagation Machine learning Neural networks Learning (artificial intelligence) Actor –critic adaptive dynamic programming deep learning (DL) elevator group control (EGC) optimal control reinforcement learning (RL) |
ISSN号 | 2162-237X |
DOI | 10.1109/TNNLS.2020.2965208 |
英文摘要 | In this article, a new deep reinforcement learning (RL) method, called asynchronous advantage actor-critic (A3C) method, is developed to solve the optimal control problem of elevator group control systems (EGCSs). The main contribution of this article is that the optimal control law of EGCSs is designed via a new deep RL method, such that the elevator system sends passengers to the desired destination floors as soon as possible. Deep convolutional and recurrent neural networks, which can update themselves during applications, are designed to dispatch elevators. Then, the structure of the A3C method is developed, and the training phase for the learning optimal law is discussed. Finally, simulation results illustrate that the developed method effectively reduces the average waiting time in a complex building environment. Comparisons with traditional algorithms further verify the effectiveness of the developed method. |
资助项目 | National Natural Science Foundation of China[61722312] ; National Natural Science Foundation of China[61673054] ; National Natural Science Foundation of China[61533017] ; National Natural Science Foundation of China[U1501251] ; European Union[739551] |
WOS关键词 | GROUP CONTROL-SYSTEM |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000595533300017 |
资助机构 | National Natural Science Foundation of China ; European Union |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/42752] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_智能化团队 |
通讯作者 | Wei, Qinglai |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Univ Cyprus, Dept Elect & Comp Engn, CY-1678 Nicosia, Cyprus 4.Univ Cyprus, KIOS Res & Innovat Ctr Excellence, CY-1678 Nicosia, Cyprus 5.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 6.Qingdao Acad Intelligent Ind, Qingdao 266109, Peoples R China |
推荐引用方式 GB/T 7714 | Wei, Qinglai,Wang, Lingxiao,Liu, Yu,et al. Optimal Elevator Group Control via Deep Asynchronous Actor-Critic Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2020,31(12):5245-5256. |
APA | Wei, Qinglai,Wang, Lingxiao,Liu, Yu,&Polycarpou, Marios M..(2020).Optimal Elevator Group Control via Deep Asynchronous Actor-Critic Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,31(12),5245-5256. |
MLA | Wei, Qinglai,et al."Optimal Elevator Group Control via Deep Asynchronous Actor-Critic Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 31.12(2020):5245-5256. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论