The invention discloses an electric vehicle charging station pricing optimization method based on deep reinforcement learning, relates to the technical field of power system planning and operation, and adopts a model-free thought to formulate the charging price of an urban public charging station in a road-electricity coupling network. Firstly, a road-electricity coupling network operation intelligent agent is constructed, and the intelligent agent and a road-electricity coupling network operation environment carry out interactive learning and optimal pricing. And then constructing an efficient interaction environment based on the deep belief network, wherein the efficient interaction environment comprises a driving path and a charging decision of an electric vehicle cluster. And then a training acceleration mechanism considering the carbon emission intensity is provided, the carbon emission of each charging station is tracked and traced to guide the optimization direction of the intelligent agent, the low-carbon economic operation of the road-electric coupling network is promoted, and the effectiveness and superiority of the pricing optimization method are ensured.

    本发明公开了一种基于深度强化学习的电动汽车充电站定价优化方法,涉及电力系统规划与运行技术领域,采用无模型思想,制定路电耦合网络中的城市公共充电站的充电价格。首先构造路电耦合网络运营智能体,该智能体与路电耦合网络运行环境交互学习最优定价。然后基于深度置信网络构建高效交互环境,包括电动汽车集群的行驶路径和充电决策。进而提出考虑碳排放强度的训练加速机制,对各充电站的碳排放量进行追踪溯源以指导智能体的寻优方向,促进路电耦合网络的低碳经济运行,从而保证本定价优化方法的有效性和优越性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Electric vehicle charging station pricing optimization method based on deep reinforcement learning


    Weitere Titelangaben:

    一种基于深度强化学习的电动汽车充电站定价优化方法


    Beteiligte:
    YUAN QUAN (Autor:in) / LI PENG (Autor:in) / MAO MINGXUAN (Autor:in) / WANG LEI (Autor:in) / GE XUEJIAN (Autor:in)

    Erscheinungsdatum :

    06.09.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    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 / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Cluster electric vehicle charging behavior optimization method based on deep reinforcement learning

    HU JUNJIE / ZHAO XINGYU | Europäisches Patentamt | 2020

    Freier Zugriff

    ELECTRIC VEHICLE CHARGING STATION HOST DEFINABLE PRICING

    LOWENTHAL RICHARD / MANDAL PRAVEEN / TORMEY MILTON et al. | Europäisches Patentamt | 2018

    Freier Zugriff

    ELECTRIC VEHICLE CHARGING STATION HOST DEFINABLE PRICING

    LOWENTHAL RICHARD / MANDAL PRAVEEN / TORMEY MILTON et al. | Europäisches Patentamt | 2019

    Freier Zugriff

    ELECTRIC VEHICLE CHARGING STATION HOST DEFINABLE PRICING

    LOWENTHAL RICHARD / MANDAL PRAVEEN / TORMEY MILTON et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Electric vehicle charging station host definable pricing

    LOWENTHAL RICHARD / MANDAL PRAVEEN / TORMEY MILTON et al. | Europäisches Patentamt | 2021

    Freier Zugriff