The invention relates to an electric vehicle short-term load prediction method considering charging behavior information privacy protection, and the method comprises the following steps: 1, constructing a user behavior data set through an electric vehicle short-term charging load prediction system considering user charging behavior information safety privacy protection based on a transverse federation; 2, performing local prediction model training on the charging operator EVCO according to the sample set constructed in the step 1; step 3, extracting and uploading parameters in the local prediction model of the charging operator EVCO trained in the step 2; and step 4, the grid company GC aggregates and issues the local prediction model parameters uploaded in the step 3. The method can effectively improve the prediction precision of the short-term charging load of the electric vehicle on the premise of guaranteeing the safety of the privacy data of the user, and has a good model generalization capability.

    本发明涉及一种计及充电行为信息隐私保护的电动汽车短期负荷预测方法,包括以下步骤:步骤1、基于横向联邦的考虑用户充电行为信息安全隐私保护的电动汽车短期充电负荷预测系统,对用户行为数据集进行构建;步骤2、根据步骤1中构建的样本集,对充电运营商EVCO进行本地预测模型训练;步骤3、对步骤2训练好的充电运营商EVCO的本地预测模型中的参数进行提取上传;步骤4、电网公司GC对步骤3上传的本地预测模型参数进行聚合并下发。本发明能够在保证用户隐私数据安全的前提下,有效地提升电动汽车短期充电负荷预测的精度,同时具备较好的模型泛化能力。


    Access

    Download


    Export, share and cite



    Title :

    Electric vehicle short-term load prediction method considering charging behavior information privacy protection


    Additional title:

    计及充电行为信息隐私保护的电动汽车短期负荷预测方法


    Contributors:
    YANG TING (author) / QIN XIAOBING (author)

    Publication date :

    2023-11-24


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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



    Spatial Load Prediction Considering Spatiotemporal Distribution of Electric Vehicle Charging Load

    Gao Xiang / Wei Lingyan / Wang Bing et al. | DOAJ | 2021

    Free access

    Short-term electric vehicle charging load prediction method and system, terminal and medium

    LONG CHUAN / YE SHENGYONG / LIU XUNA et al. | European Patent Office | 2023

    Free access

    Electric vehicle load prediction method and system considering user charging selection

    LIU JINSEN / LUO NING / LONG JIAHUAN et al. | European Patent Office | 2024

    Free access


    Urban-range electric vehicle charging demand prediction method considering geographic information

    FANG CHEN / LIU ZEYU / WANG HAOJING et al. | European Patent Office | 2020

    Free access