期刊文献+

基于多智能体增强学习的公交驻站控制方法 被引量:6

Bus holding control method in public transit systems with multiagent reinforcement learning
下载PDF
导出
摘要 车辆驻站是减少串车现象和改善公交服务可靠性的常用且有效控制策略,其执行过程需要在随机交互的系统环境中进行动态决策。考虑实时公交运营信息的可获得性,研究智能体完全合作环境下公交车辆驻站增强学习控制问题,建立基于多智能体系统的单线公交控制概念模型,描述学习框架下包括智能体状态、动作集、收益函数、协调机制等主要元素,采用hysteretic Q-learning算法求解问题。仿真实验结果表明该方法能有效防止串车现象并保持单线公交服务系统车头时距的均衡性。 Vehicle holding is a commonly used strategy among a variety of control strategies in transit operation for improving transit service reliability, whose implementation needs dynamic decision-making in an interactive and stochastic system environment. This paper introduces a novel use of a reinforcement learning framework to obtain vehicle holding autonomous control strategy in cooperative multi-agent system. Transit operation control model is developed based on multi-agent system. In the multi-agent reinforcement learning framework, each bus is modeled as an independent agent with learning abilities, for which the state, actions and reward are defined and a coordination mechanism for multiple bus agents is designed to obtain a joint holding actions. The hysteretic Q-learning algorithm is used to solve this holding problem. From the simulation experiments, the results illustrate that the proposed approach is able to prevent buses from bunching and regulate bus headway.
出处 《计算机工程与应用》 CSCD 北大核心 2015年第17期8-13,27,共7页 Computer Engineering and Applications
基金 国家自然科学基金(No.61203162) 湖南省哲学社会科学基金(No.13YBB153) 湖南省教育厅科学研究项目(No.14C0763)
关键词 驻站 多智能体增强学习 多智能体系统 控制策略 bus holding multi-agent reinforcement learning multi-agent system control strategy
  • 引文网络
  • 相关文献

参考文献29

  • 1Osuna E E,Newell G F.Control strategies for an ideali- zed public transportation system[J].Transportation Sci- ence, 1972,6( 1 ) : 52-72. 被引量:1
  • 2Barnett A.On controlling randomness in transit operations[J]. Transportation Science, 1974,8 (2) : 102-116. 被引量:1
  • 3Abkowitz M, Eiger A, Engelstein I.Opfimal control of head- way variation on transit routes[J].Joumal of Advanced Transportation, 1986,20( 1 ) : 73-88. 被引量:1
  • 4Eberlein X J,Wilson N H M, Bemstein D.The holding problem with real-time information available[J].Transpor- tation Science, 2001,35 ( 1 ) : l- 18. 被引量:1
  • 5Sun A, Hickman M.The holding problem at multiple hold- ing stations[M].Berlin, Heidelberg: Springer, 2008: 339-359. 被引量:1
  • 6Delgado F, Mufloz J C, Giesen R, et al.Real-time controlof buses in a transit corridor based on vehicle holding and boarding limits[J].Transportation Research Record: Journal of the Transportation Research Board, 2009: 59-67. 被引量:1
  • 7Chen Q, Adida E, Lin J.Implementation of an iterative headway-based bus holding strategy with real-time infor- mation[J].Public Transport,2013,4(3) : 165-186. 被引量:1
  • 8Mufloz J C,Cort6s C E,Giesen R,et al.Comparison of dynamic control strategies for transit operations[J].Trans- portation Research Part C : Emerging Technologies, 2013, 28:101-113. 被引量:1
  • 9黄溅华,葛芳,张国伍.公共交通实时控制模型研究[J].系统工程理论与实践,2001,21(5):129-131. 被引量:11
  • 10黄溅华,张国伍.公共交通实时放车调度方法研究[J].系统工程理论与实践,2001,21(3):107-111. 被引量:18

二级参考文献74

共引文献94

同被引文献10

引证文献6

二级引证文献10

;
使用帮助 返回顶部