Public transportation scheduling problem is a complex problem considering various influencing factors (such as passenger flow, etc.). However, the effect is not ideal when using the traditional machine learning method. Therefore,this paper aims to propose a Deep Reinforcement Learning Proximal Policy Optimization (DRL-PPO) algorithm for public transport scheduling according to different actual passenger flow. At the end of the paper, we make bus arrival time records and passenger OD data of Guangzhou route 560, for three months from July 1, 2019, to September 30, 2019 for training. Compared with GA algorithm, PPO algorithm is better than GA in convergence speed and final effect, which verifies the effectiveness of PPO in bus scheduling with complex passenger flow characteristics.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Deep Reinforcement Learning for Bus Scheduling Considering Complex Passenger Flow


    Contributors:
    Fu, Hui (author) / Chen, Niu (author) / Yao, Yipeng (author) / Han, Shuang (author) / Wang, Yefei (author)

    Conference:

    22nd COTA International Conference of Transportation Professionals ; 2022 ; Changsha, Hunan Province, China


    Published in:

    CICTP 2022 ; 326-335


    Publication date :

    2022-09-08




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Deep Reinforcement Learning for Bus Scheduling Considering Complex Passenger Flow

    Fu, Hui / Chen, Niu / Yao, Yipeng et al. | TIBKAT | 2022


    Optimization of Bus Scheduling Model Considering Unstable Passenger Flow

    Han, Zhangyu / Ci, Yusheng / Jiang, Peiyu | TIBKAT | 2020


    Vehicle Scheduling Optimization considering the Passenger Waiting Cost

    Huayan Shang / Yanping Liu / Haijun Huang et al. | DOAJ | 2019

    Free access


    Passenger delay minimization signal control method based on deep reinforcement learning

    WU ZONGYUAN / LI SHIMING / DING SHENZHEN et al. | European Patent Office | 2023

    Free access