基于有限信息的电动汽车用户充电行为特征识别  

Identification of Charging Behavior Characteristics of Electric Vehicle Users Based on Limited Information

作　　者：石天琛 杨烨 刘明光 王文 王佳妮 刘敦楠[1,2] SHI Tianchen;YANG Ye;LIU Mingguang;WANG Wen;WANG Jiani;LIU Dunnan(School of Economics and Management,North China Electric Power University,Beijing 102206,China;Beijing Key Laboratory of New Energy and Low-Carbon Development,Beijing 102206,China;State Grid Smart Internet of Vehicles Co.,Ltd.,Beijing 100052,China)

机构地区：[1]华北电力大学经济与管理学院,北京市102206 [2]新能源电力与低碳发展北京市重点实验室,北京市102206 [3]国网智慧车联网技术有限公司,北京市100052

出　　处：《电力建设》2024年第10期69-77,共9页Electric Power Construction

基　　金：国家自然科学基金面上项目(72171082)。

摘　　要：随着电动汽车的广泛应用,电动汽车用户充电行为成为了电动汽车领域的一个关键焦点。然而,电动汽车用户参与车网互动的积极性较低,难以被有效激励参与调峰调频。同时,用户行为数据具有复杂性与有限性,难以准确分析用户行为。文章提出一种在有限信息下识别电动汽车用户充电行为特征的模型,以制定差异化的激励策略。首先,梳理了用户充电行为的基础特征,提出不同特征用户的激励策略;其次,构建用户充电行为分类模型;再次,构建用户充电行为识别的步骤流程,并设计基于云模型和模糊Petri网的用户充电行为特征识别模型;最后,通过某充电厂区的有限用户数据进行算例分析。算例结果表明,提出的模型成功将电动汽车用户分为不同类型,从而实现有针对性的激励策略的目标。这一模型提供了一种有效的工具,用于更好地理解用户行为、优化能源管理,以及提供个性化的激励策略,从而鼓励用户更积极地参与车网互动和能源调度,进一步推动电动汽车的可持续发展。With the widespread adoption of electric vehicles(EVs),the charging behavior of EV users has become a critical focus area.However,EV users often exhibit low enthusiasm for participating in vehicle-to-grid(V2G)interactions,making it difficult to effectively motivate their involvement in load balancing and frequency regulation.Moreover,user behavior data are complex and limited,posing challenges for the accurate analysis of user behavior.This study proposes a model for identifying the charging behavior characteristics of EV users based on limited information to formulate differentiated incentive strategies.First,it outlines the fundamental characteristics of user charging behavior and proposes incentive strategies tailored to different user types.Subsequently,a classification model for user charging behavior is developed.It then details the steps for identifying user charging behavior and designs a model for recognizing these characteristics based on a cloud model and fuzzy Petri nets.Finally,the model is validated through a case study using limited user data from a specific charging facility.The results of the case study demonstrate that the proposed model successfully categorizes EV users into different types,thereby achieving the goals of targeted incentive strategies.This model offers an effective tool to better understand user behavior,optimize energy management,and provide personalized incentive strategies,thereby encouraging more active participation in V2G interactions and energy scheduling.It further promotes the sustainable development of electric vehicles.

关 键 词：电动汽车 用户充电行为 特征识别 云模型 模糊PETRI网 

分 类 号：TM73[电气工程—电力系统及自动化]