The invention discloses an electric vehicle charging facility recommendation method and system based on federated learning. The method comprises the steps: acquiring a pile feature data set and a vehicle feature data set, the pile feature data set being a set formed by pile features related to charging pile operation and extracted from pile operation data platform data, and the vehicle feature data set being a set formed by vehicle features related to vehicle charging and extracted from vehicle enterprise data platform data; performing federation training on the pile feature data set and the vehicle feature data set by adopting a federation recommendation algorithm to obtain a federation recommendation model; obtaining a current pile feature data set and a current vehicle feature data setcorresponding to all charging piles in the to-be-recommended charging pile list; and inputting the current pile feature data set and the current vehicle feature data set into a federation recommendation model to obtain a recommendation result. By implementing the method and the system, the fusion use of the pile operation data platform data and the vehicle enterprise data platform data is realized, the model characteristics are expanded, and the personalized recommendation of the charging facilities is realized.

    本发明公开了一种基于联邦学习的电动汽车充电设施推荐方法及系统,该方法包括:获取桩特征数据集以及车特征数据集,桩特征数据集为从桩运营数据平台数据中提取的与充电桩运营相关的桩特征构成的集合,车特征数据集为从车企数据平台数据中提取的与车充电相关的车特征构成的集合;采用联邦推荐算法对桩特征数据集和车特征数据集进行联邦训练,得到联邦推荐模型;获取待推荐充电桩列表中所有充电桩对应的当前桩特征数据集和当前车特征数据集;将当前桩特征数据集及当前车特征数据集输入联邦推荐模型,得到推荐结果。通过实施本发明,实现了桩运营数据平台数据和车企数据平台数据的融合使用,扩充了模型特征,实现了对充电设施的个性化推荐。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Electric vehicle charging facility recommendation method and system based on federated learning


    Weitere Titelangaben:

    一种基于联邦学习的电动汽车充电设施推荐方法及系统


    Beteiligte:
    WANG XIAOHUI (Autor:in) / AN NINGYU (Autor:in) / ZHENG XIAOKUN (Autor:in) / LIANG XIAO (Autor:in)

    Erscheinungsdatum :

    2020-11-06


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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 / G07F Selbstkassierende und ähnliche Geräte , COIN-FREED OR LIKE APPARATUS






    CHARGING SYSTEM, ELECTRIC VEHICLE, AND CHARGING FACILITY

    IIYOSHI RYOTA | Europäisches Patentamt | 2021

    Freier Zugriff

    Predicting Electric Vehicle Charging Stations Occupancy: A Federated Deep Learning Framework

    Douaidi, Lydia / Senouci, Sidi-Mohammed / El Korbi, Ines et al. | IEEE | 2023