The invention relates to an electric vehicle charging technology, and aims to provide a transformer area electric vehicle orderly charging method based on load prediction and deep reinforcement learning. Comprising the following steps: predicting future residual charging capacity by using a full-connection feedforward neural network according to historical charging residual capacity information of a transformer substation; and according to an elastic electricity price mechanism and the predicted future residual charging capacity, a DQN-based deep reinforcement learning algorithm is used for adjusting an electric vehicle charging strategy, and the number of the electric vehicles connected to the charging piles is controlled. According to the invention, the load prediction method is introduced into the ordered charging operation of the electric vehicle, the predicted future residual charging capacity is used as the basis of the charging scheduling of the electric vehicle, and the method is more real-time and advanced than a traditional method. According to the method, deep reinforcement learning is introduced into the electric vehicle ordered charging operation, the electric vehicle ordered charging is scheduled in advance by using the predicted future information, the method has real-time self-learning updating capability, the method is more flexible and effective than a traditional algorithm, and the economical efficiency and the high efficiency are further improved.

    本发明涉及电动汽车充电技术,旨在提供一种基于负荷预测和深度强化学习的台区电动汽车有序充电方法。包括:根据变电站历史充电剩余容量信息,使用全连接前馈神经网络预测未来剩余充电容量;根据弹性电价机制和预测的未来剩余充电容量,使用基于DQN的深度强化学习算法调整电动汽车充电策略,控制电动汽车接入充电桩的数量。本发明将负荷预测方法引入到电动汽车有序充电运算中,将预测的未来剩余充电容量作为电动汽车充电调度的依据,比传统方法更具实时性、超前性。通过引入深度强化学习到电动汽车有序充电运算中,利用预测到的未来信息超前调度电动汽车有序充电,且具有实时自学习更新能力,比传统算法更灵活有效,进一步提高了经济性和高效性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Load prediction and deep reinforcement learning-based orderly charging method for electric vehicles in court


    Weitere Titelangaben:

    基于负荷预测和深度强化学习的台区电动汽车有序充电方法


    Beteiligte:
    HU XIAOMAN (Autor:in) / PAN BIN (Autor:in) / CHEN QIZHAN (Autor:in) / CUI YIGUO (Autor:in) / CHEN HAOHE (Autor:in) / DONG ZHICHUN (Autor:in) / WANG GANJUN (Autor:in) / HUANG YUXING (Autor:in) / LU JINGYU (Autor:in) / MAI HAN (Autor:in)

    Erscheinungsdatum :

    2022-03-11


    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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Dynamic optimization control method and system for orderly charging of electric vehicles in court

    FANG KAIJIE / HUANG QIFENG / LONG YU et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Orderly charging control method and system for electric vehicles

    SUN KAN / DING YANG / ZHANG XUAN et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    System and method for orderly charging electric vehicles in intelligent park

    WANG FENGXIA / FAN LIN | Europäisches Patentamt | 2022

    Freier Zugriff


    Orderly charging collector

    CAI FUHAN / ZHANG CHAOKAI / WANG YU et al. | Europäisches Patentamt | 2023

    Freier Zugriff