With the increasement of urban rail transit operation density, the power consumption of metro system is also rising sharply. Meanwhile the proportion for urban rail transit of power consumption is increasing, so this problem needs more and more attention. In order to reduce the power consumption of rail transit, this research mainly focuses on the renewable energy utilization of train, which means that the train will make the best of the regenerative braking energy. For this purpose, the flywheel energy storage device is used as on-board device, then the regenerative braking strategy of the train is optimized based on reinforcement learning algorithm. Ultimately, the optimized train speed curve by the dynamic planning and Q-learning can achieve more than 5% energy recovery of the total energy consumption. The results show that this research can save the power consumption of rail transit by recycling the braking energy, which is of great significance for significance for energy saving and green transportation


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Train Regenerative Braking Strategy Optimization Based on Reinforcement Learning


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Zeng, Xiaoqing (Herausgeber:in) / Xie, Xiongyao (Herausgeber:in) / Sun, Jian (Herausgeber:in) / Ma, Limin (Herausgeber:in) / Chen, Yinong (Herausgeber:in) / Zeng, Xiaoqing (Autor:in) / Liu, Liqun (Autor:in) / Yuan, Tengfei (Autor:in)

    Kongress:

    International Symposium for Intelligent Transportation and Smart City ; 2022 May 20, 2022 - May 21, 2022



    Erscheinungsdatum :

    2023-04-28


    Format / Umfang :

    12 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch