The social economy and rail transit of China had tremendous growth over recent years, the energy consumption of transportation has increased. Aiming at the problem of energy-saving driving strategy, this paper proposes a train energy-saving driving strategy based on PPO (Proximal Policy Optimization) algorithm. By constructing a Markov decision-making process model and training parameters, this paper combines driving strategy with deep reinforcement learning algorithm. According to train running conditions and energy consumption evaluation model, considering that the train needs to follow the requirements of the timetable, this paper combines punctuality with energy consumption to make up the reward function. At last, this paper takes the parameters of actual transmission lines, from Chibibei to Changshanan of Wuhan to Guangzhou railway line for passenger traffic as example to verify the effectiveness of the method. The simulation results show that this algorithm has advantages in optimizing train traction energy consumption, it also has reference suggestions for the development of Green Transport.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Optimization of Energy-Saving Driving Strategy of High-Speed Train Based on PPO


    Contributors:
    Liu, Xinhong (author) / Zhang, Yadong (author) / Guo, Jin (author)


    Publication date :

    2023-03-24


    Size :

    1669962 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Train energy-saving speed trajectory optimization method based on dynamic programming

    LU SHAOFENG / CHEN FUWANG / PENG YANG | European Patent Office | 2024

    Free access


    High-speed railway train energy-saving operation optimization method considering optical storage access

    LI XIN / ZHU CHENGKUN / LI RUOQIONG et al. | European Patent Office | 2023

    Free access