As a new type of vehicle power system with zero emission and renewable energy, fuel cell has high research value. In this paper, a fuel cell energy management strategy based on deep reinforcement learning is proposed for high-speed traffic scenarios. A bus working condition with real high-speed traffic scenarios is obtained through NGSIM's real high-speed road segment data set screening. The energy management strategy effectively reduces the hydrogen consumption by 4.21% and the power fluctuation by 17.2%, which effectively improves the durability of fuel cells.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fuel cell bus energy management based on deep reinforcement learning in NGSIM high-speed traffic scenario


    Contributors:
    Shen, Yang (author) / Yi, Fengyan (author) / Fan, Yi (author) / Chen, Weiqi (author) / Zhou, Jiaming (author) / Peng, Jiankun (author)


    Publication date :

    2022-10-28


    Size :

    4827589 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Making NGSIM Data Usable for Studies on Traffic Flow Theory

    Montanino, Marcello / Punzo, Vincenzo | Transportation Research Record | 2013


    Developing extended trajectory database for heterogeneous traffic like NGSIM database

    Raju, Narayana / Arkatkar, Shriniwas / Easa, Said et al. | Taylor & Francis Verlag | 2022


    Calibration of an interrupted traffic flow system using NGSIM trajectory data sets

    Fang, Yaling / Shi, Zhongke / Cao, Jinliang | IEEE | 2014


    Use of Speed Measurements for Highway Traffic State Estimation: Case Studies on NGSIM Data and Highway A20, Netherlands

    Roncoli, Claudio / Bekiaris-Liberis, Nikolaos / Papageorgiou, Markos | Transportation Research Record | 2016


    Highway traffic state estimation using speed measurements: case studies on NGSIM data and highway A20 in the Netherlands

    Roncoli, Claudio / Bekiaris-Liberis, Nikolaos / Papageorgiou, Markos | ArXiv | 2015

    Free access