The invention discloses a cluster electric vehicle charging behavior optimization method based on deep reinforcement learning, and belongs to the technical field of new energy vehicle optimization management. The invention relates to a deterministic strategy gradient algorithm based on double delay depths. Modeling is carried out on the power continuous adjustable charging process of the electricvehicle, an intelligent agent is trained to control the charging power, the charging behavior of the electric vehicle is optimized, the load when the time-of-use electricity price is high is transferred to the load when the electricity price is low, and the purposes of reducing the user charging expenditure and stabilizing the peak-time load of a power grid are achieved. Compared with a traditional optimization control method, the TD3 has obvious advantages in speed and flexibility, and the problems that an existing reinforcement learning method is discrete in action space, difficult in training convergence and poor in stability can be effectively solved. In order to enhance the generalization ability of the intelligent agent, noise is added on the basis of original state observation, a group of electric vehicles with different initial SOCs and different arrival and departure time are simulated, and the method is expanded to cluster electric vehicle charging behavior control.

    本发明公开了属于新能源汽车优化管理技术领域的一种基于深度强化学习的集群电动汽车充电行为优化方法。本发明为基于双延迟深度确定性策略梯度算法,实现对电动汽车的功率连续可调充电过程进行建模,训练智能体控制充电功率,优化电动汽车充电行为,将分时电价高时的负荷向电价低时进行转移,达到减少用户充电开销,平抑电网峰时负荷的目的;相较于传统的优化控制方法,TD3在速度和灵活性上优势明显,且可以有效克服以往的强化学习方法动作空间离散、训练收敛困难、稳定性差的问题。为增强智能体的泛化能力,本发明在原有状态观测上添加噪声,模拟一组初始SOC不同,到达与驶离时间各异的电动汽车,并扩展到集群电动汽车充电行为控制。


    Access

    Download


    Export, share and cite



    Title :

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


    Additional title:

    一种基于深度强化学习的集群电动汽车充电行为优化方法


    Contributors:
    HU JUNJIE (author) / ZHAO XINGYU (author)

    Publication date :

    2020-11-13


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    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 / 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



    REINFORCEMENT LEARNING-BASED ELECTRIC VEHICLE CHARGING METHOD AND SYSTEM

    CHOI JUNGHWA / KIM MINKOOK / KIM YEONJUNG et al. | European Patent Office | 2021

    Free access

    One-pile multi-connection electric vehicle ordered charging method based on deep reinforcement learning

    CUI HAOQIAN / YU HAO / LIU MINGYUAN et al. | European Patent Office | 2023

    Free access


    Reinforcement Learning Based Fast Charging of Electric Vehicle Battery Packs

    Xu, Bin / Zhang, Jiangfeng / Abbasi, Mohammad Hossein et al. | SAE Technical Papers | 2023


    Photovoltaic-electric vehicle charging station combined control method based on reinforcement learning

    SUN FANGYUAN / DIAO RUISHENG / ZHENG WAISHENG et al. | European Patent Office | 2023

    Free access