The invention discloses a railway traffic system scheduling optimization method based on an automaton and reinforcement learning. The method comprises the following steps: S1, establishing a mathematical model Gi and a safety and activity control specification model Ej of a vehicle; s2, establishing an automaton model G of a railway traffic system scheduling problem; solving a target model T of a railway traffic system scheduling problem; s3, giving corresponding execution cost to the event in the target model T in combination with the cost required for event occurrence and the control cost of the event; s4, solving a monitor model V = SupC (G, T) of a railway traffic system scheduling problem by using TCT software; and S5, converting the monitor model V in the step S4 into a deterministic Markov decision process MDP, solving a railway traffic system scheduling problem by using a Q learning algorithm, and performing an experiment and result analysis. According to the railway traffic system scheduling optimization method based on the automaton and reinforcement learning, the optimal scheduling scheme of the railway traffic system is obtained, and the vehicle scheduling cost is effectively reduced.

    本发明公开了一种基于自动机和强化学习的铁路交通系统调度优化方法,包括以下步骤:S1、建立车辆的数学模型Gi,安全性和活性控制规范模型Ej;S2、建立铁路交通系统调度问题的自动机模型G;求解出铁路交通系统调度问题的目标模型T;S3、结合事件发生所需的成本和事件的控制成本,为目标模型T中的事件赋予相应的执行成本;S4、利用TCT软件求解出铁路交通系统调度问题的监控器模型V=SupC(G,T);S5、将S4中的监控器模型V转换为确定性马尔可夫决策过程MDP,利用Q学习算法求解铁路交通系统调度问题,实验并进行结果分析。本发明采用上述基于自动机和强化学习的铁路交通系统调度优化方法,得到铁路交通系统的最优调度方案,有效降低车辆调度成本。


    Access

    Download


    Export, share and cite



    Title :

    Railway traffic system scheduling optimization method based on automaton and reinforcement learning


    Additional title:

    一种基于自动机和强化学习的铁路交通系统调度优化方法


    Contributors:
    WANG DEGUANG (author) / HU YUHONG (author) / YANG MING (author)

    Publication date :

    2023-04-25


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B61L Leiten des Eisenbahnverkehrs , GUIDING RAILWAY TRAFFIC / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen





    Cellular Automaton-Based Traffic Flow Simulation Model for Traffic Incidents

    Zhao, Kang-jia / Chen, Shu-yan / Lao, Ye-chun | ASCE | 2015


    Train operation scheduling optimization method based on deep reinforcement learning

    LI LIJUAN / YANG XUE / WANG HUAN et al. | European Patent Office | 2023

    Free access

    OPTIMIZATION IN RAILWAY SCHEDULING

    Salido, M. A. / Abril, M. / Barber, F. et al. | British Library Conference Proceedings | 2005