The invention discloses a distributed charging station scheduling method and device based on multi-agent reinforcement learning, and the method comprises the steps: distributing a charging request to at least two charging stations, and receiving a charging score formed by each charging station based on the charging request; and a recommended charging station corresponding to the charging request is determined based on all the received charging scores, and the recommended charging station is fed back to the electric vehicle. According to the method, the charging stations deployed with the reinforcement learning strategy network serve as the distributed nodes, the charging scores of completing the charging request are determined by deploying the reinforcement learning strategy network, and the electric vehicles are scheduled based on the charging scores, so that charging demand fluctuation in different regions and time periods can be flexibly coped with, and the charging efficiency is improved. The risk of overload of a power grid is reduced, and the overall charging efficiency is improved. And meanwhile, the deployment of the reinforcement learning strategy network can be finely adjusted based on scheduling sample data formed by historical charging requests, so that the model performance of the deployment of the reinforcement learning strategy network is ensured.

    本申请公开了一种基于多智能体强化学习的分布式充电站调度方法及设备,所述方法包括将充电请求分发给至少两个充电站,并接收每个充电站基于充电请求所形成的充电评分;基于接收到的所有充电评分确定充电请求对应的推荐充电站,并将所述推荐充电站反馈给所述电动汽车。本申请通过将部署强化学习策略网络的充电站作为分布式节点,通过部署强化学习策略网络确定自身完成该充电请求的充电评分,并基于各充电评分来调度电动汽车,这样可以灵活应对不同区域和时段的充电需求波动,减少电网负荷过载的风险,并提高整体充电效率。同时,部署强化学习策略网络会基于历史充电请求形成的调度样本数据进行微调,保证部署强化学习策略网络的模型性能。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Distributed charging station scheduling method and device based on multi-agent reinforcement learning


    Weitere Titelangaben:

    基于多智能体强化学习的分布式充电站调度方法及设备


    Beteiligte:
    LEI TIAN (Autor:in) / WANG ZHENGZHUO (Autor:in) / CHEN XIAOWEI (Autor:in) / GONG LEI (Autor:in) / LUO QIN (Autor:in) / CHEN JINGJING (Autor:in)

    Erscheinungsdatum :

    14.01.2025


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / H02J CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER , Schaltungsanordnungen oder Systeme für die Abgabe oder Verteilung elektrischer Leistung / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen



    Electric vehicle charging method and device based on multi-agent deep reinforcement learning

    LI CHAO / MENG ZIJIE / NI BINYE et al. | Europäisches Patentamt | 2025

    Freier Zugriff


    Electric vehicle battery charging regulation and control method based on multi-agent reinforcement learning

    DU LIUFENG / TIAN XIYAN / WANG ZHANKUI et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Charging pile scheduling method and system based on deep reinforcement learning

    WU ZHAOJU / ZHU YONGDONG / XU TU et al. | Europäisches Patentamt | 2024

    Freier Zugriff