Information Release Strategy of Urban Rail Transit Based on Reinforcement Learning

被引：0

作者：

Jia F.-F. ^{[1
,2
]}

Jiang X. ^{[1
]}

Li H.-Y. ^{[1
]}

Yu X.-Q. ^{[3
]}

机构：

[1] State Key Lab of Rail Traffic Control & Safety, Beijing Jiaotong University, Beijing

[2] School of Traffic and Transportation, Beijing Jiaotong University, Beijing

[3] Institute of Transportation and Economy, China Academy of Railway Sciences Corporation Limited, Beijing

来源：

Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | 2020年 / 20卷 / 05期

关键词：

Information release; Intelligent transportation; Passenger flow guidance; Q-learning; Reinforcement learning;

D O I：

10.16097/j.cnki.1009-6744.2020.05.011

中图分类号：

学科分类号：

摘要：

Guidance information can change the choice behavior of passengers and thus network passenger flow distribution. Information release is one of the key measures to alleviate the congestion problem from demand ideas. A method is proposed to generate an information release strategy based on reinforcement learning. The system state is extracted based on the load rate of passenger flow in each section in the network. The information release action is composed of the recommended paths of each OD. The reward value of implementing an information release action is evaluated according to system state change. By an urban rail transit dynamic passenger flow simulation system, the [Q-learning] algorithm is employed to obtain optimal information release strategy. A practical network is taken as an example to verify the proposed method. It was found that network congestion can be alleviated by using the proposed information release strategy. Copyright © 2020 by Science Press.

引用

页码：72 / 78

页数：6

共 8 条

[1] CHEN F, ZHANG W H, DING H, Et al., Research on VMS inducing strategy based on the route selection behavior of travels, System Engineering-Theory & Practice, 38, 5, pp. 1263-1276, (2018)
[2] SUN Z Y, LU H P, ZHANG X L, Et al., Bi-level programming model for cooperation of urban traffic control and traffic flow guidance, Journal of Southeast University (Natural Science Edition), 46, 2, pp. 450-456, (2016)
[3] CAO S H, YUAN Z Z, LI Y H, Et al., A model for road network stochastic user equilibrium based on bilevel programming under the action of traffic flow guidance sytem, Journal of Transportation System Engineering and Information Technology, 7, 4, pp. 36-42, (2007)
[4] YANG Y, HU Z A., Optimal path routing simulation research on urban traffic network with traffic management and control strategies, Computer Simulation, 7, pp. 155-158, (2013)
[5] YIN H, WU J, LIU Z, Et al., Optimizing the release of passenger flow guidance information in urban rail transit network via agent-based simulation, Applied Mathematical Modelling, 72, pp. 337-355, (2019)
[6] WATKINS, CHRISTOPHER J C H, DAYANPETER, Q-learning, Machine Learning, 8, 3, pp. 279-292, (1992)
[7] VAN ESSEN M, THOMAS T, VAN BERKUM E, Et al., Travelers' compliance with social routing advice: Evidence from SP and RP experiments, Transportation, 47, 3, pp. 1047-1070, (2020)
[8] JIANG X, FENG J P, JIA F F, Et al., Modeling and simulation of passenger flow distribution in large-scale urban rail transit network, Journal of the China Railway Society, 40, 11, pp. 13-22, (2018)

← 1 →