李振坤,胡焜,姚一聪
LI Zhenkun,HU Kun,YAO Yicong

• 1:上海电力大学教育部海上风电技术工程研究中心
• 2:上海电力大学电气工程学院

摘要(Abstract)：

针对EV（电动汽车）调度容量评估受用户参与意愿差异影响的问题，提出一种考虑用户意愿的EV集群可调度容量评估方法。首先，分析EV负荷数据概率密度函数间的联合熵，识别充电规律相似的日期，同时采用神经网络预测未来日EV的起始充电时刻及起始SOC（荷电状态）概率分布；然后，综合考虑电池健康状况、剩余SOC、预计的剩余停滞时长以及放电电价激励4个关键因素，构建EV用户主观参与调度意愿的模型，并运用模糊逻辑规则解析用户响应意愿；最后，在考虑用户出行需求和停滞时长约束的基础上，分析计算单体EV可调度容量，进而构建EV集群V2G（车网互动）可调度容量模型。算例分析结果表明，该方法能够精准预测EV的充电需求，有效量化用户响应意愿，实现对EV集群可调度容量的准确评估。
To address how variable user participation willingness affects electric vehicle(EV) dispatchable capacity assessment, this paper proposes a novel assessment method incorporating user willingness. First, joint entropy of probability density functions of EV load data is analyzed to identify dates with similar charging patterns, while a neural network predicts the probability distributions of initial charging times and initial state of charge(SOC) for future days. Second, a user participation willingness model is constructed by integrating four key factors—battery health status, remaining SOC, expected idle duration, and discharge electricity price incentives—using fuzzy logic rules to quantify response willingness. Finally, individual EV dispatch capacity is calculated subject to travel demand and idle duration constraints, followed by the development of an aggregate vehicle-to-grid(V2G) dispatchable capacity model for EV clusters. Case studies demonstrate that the proposed method accurately predicts EV charging demand, effectively quantifies user response willingness, and enables precise assessment of EV cluster dispatch capacity.

关键词(KeyWords)： 多层感知器神经网络预测;模糊逻辑规则;车网互动;响应容量
multilayer perceptron neural network prediction;fuzzy logic rules;V2G;response capacity

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金（52177098）;; 上海市科技计划项目（21010501200）

作者(Author): 李振坤,胡焜,姚一聪
LI Zhenkun,HU Kun,YAO Yicong

DOI: 10.19585/j.zjdl.202601004

参考文献(References)：

• [1]杨镜司，秦文萍，史文龙，等.基于电动汽车参与调峰定价策略的区域电网两阶段优化调度[J].电工技术学报，2022,37(1):58-71.YANG Jingsi,QIN Wenping,SHI Wenlong,et al.Twostage optimal dispatching of regional power grid based on electric vehicles'participation in peak-shaving pricing strategy[J]. Transactions of China Electrotechnical Society,2022,37(1):58-71.
• [2]YUE H Z,ZHANG Q,ZENG X S,et al.Optimal scheduling strategy of electric vehicle cluster based on index evaluation system[J].IEEE Transactions on Industry Applications,2023,59(1):1212-1221.
• [3]赵宇，贺兴，艾芊.基于碳流追踪的电动汽车充电站定价方法[J].电力工程技术，2025,44(6):2-12.ZHAO Yu,HE Xing,AI Qian.Pricing method for electric vehicle charging stations based on carbon flow tracing[J].Electric Power Engineering Technology,2025,44(6):2-12.
• [4]肖怡康，牟玉亭，潘博，等.面向电动汽车聚合商参与电能量-备用市场的分色电价设计[J].电力工程技术，2025,44(6):13-24.XIAO Yikang,MOU Yuting,PAN Bo,et al. Design of color-coded pricing for electric vehicle aggregators participating in energy-reserve markets[J].Electric Power Engineering Technology,2025,44(6):13-24.
• [5]董晓红，孔华志，丁飞，等.考虑电池老化的电动汽车中长期充电负荷预测方法[J].电力系统自动化，2024,48(13):109-119.DONG Xiaohong,KONG Huazhi,DING Fei,et al.Medium-and long-term charging load forecasting method for electric vehicles considering battery aging[J].Automation of Electric Power Systems,2024,48(13):109-119.
• [6]ZHANG X,CHAN K W,LI H R,et al. Deep-learningbased probabilistic forecasting of electric vehicle charging load with a novel queuing model[J]. IEEE Transactions on Cybernetics,2021,51(6):3157-3170.
• [7]李练兵，郭兴辰，曾四鸣，等.基于GLDSC-ConvAutoformer模型的区域电动汽车短期充电负荷预测[J].太阳能学报，2025,46(2):90-98.LI Lianbing,GUO Xingchen,ZENG Siming,et al.Shortterm charging load prediction of regional electric vehicles based on gldsc-convautoformer model[J]. Acta Energiae Solaris Sinica,2025,46(2):90-98.
• [8]姚芳，汤俊豪，陈盛华，等.基于ISSA-CNN-GRU模型的电动汽车充电负荷预测方法[J].电力系统保护与控制，2023,51(16):158-167.YAO Fang,TANG Junhao,CHEN Shenghua,et al.Charging load prediction method for electric vehicles based on an ISSA-CNN-GRU model[J]. Power System Protection and Control,2023,51(16):158-167.
• [9]葛晓琳，胡文哲，符杨，等.基于用户响应意愿度三维Sigmoid云模型的电动汽车优化调度策略[J].中国电机工程学报，2024,44(22):8874-8884.GE Xiaolin,HU Wenzhe,FU Yang,et al.Optimal scheduling strategy for electric vehicles based on user response willingness three dimensional sigmoid cloud model[J].Proceedings of the CSEE,2024,44(22):8874-8884.
• [10]胡俊杰，马文帅，薛禹胜，等.基于CPSSE框架的电动汽车聚合商备用容量量化[J].电力系统自动化，2022,46(18):46-54.HU Junjie,MA Wenshuai,XUE Yusheng,et al.Quantification of reserve capacity provided by electric vehicle aggregator based on framework of cyber-physical-social system in energy[J].Automation of Electric Power Systems,2022,46(18):46-54.
• [11]李含玉，杜兆斌，陈丽丹，等.基于出行模拟的电动汽车充电负荷预测模型及V2G评估[J].电力系统自动化，2019,43(21):88-96.LI Hanyu,DU Zhaobin,CHEN Lidan,et al.Trip simulation based charging load forecasting model and vehicle-togrid evaluation of electric vehicles[J].Automation of Electric Power Systems,2019,43(21):88-96.
• [12]周玮，徐从明，杨丹霞，等.P2P能源共享下考虑意愿动态调整的电动汽车群需求响应策略研究[J].中国电机工程学报，2023,43(21):8217-8230.ZHOU Wei,XU Congming,YANG Danxia,et al. Research on demand response strategy of electric vehicles considering dynamic adjustment of willingness under P2P energy sharing[J]. Proceedings of the CSEE,2023,43(21):8217-8230.
• [13]DENG R Q,XIANG Y,HUO D,et al.Exploring flexibility of electric vehicle aggregators as energy reserve[J].Electric Power Systems Research,2020,184:106305.
• [14]张亚朋，穆云飞，贾宏杰，等.电动汽车虚拟电厂的多时间尺度响应能力评估模型[J].电力系统自动化，2019,43(12):94-103.ZHANG Yapeng,MU Yunfei,JIA Hongjie,et al. Response capability evaluation model with multiple time scales for electric vehicle virtual power plant[J].Automation of Electric Power Systems,2019,43(12):94-103.
• [15]WANG M S,MU Y F,LI F X,et al.State space model of aggregated electric vehicles for frequency regulation[J].IEEE Transactions on Smart Grid,2020,11(2):981-994.
• [16]LEI X,YU H,ZHONG J H,et al.Exploring electric vehicle’s potential as capacity reservation through V2G operation to compensate load deviation in distribution systems[J].Journal of Cleaner Production,2024,451:141997.
• [17]LAM A Y S,LEUNG K C,LI V O K.Capacity estimation for vehicle-to-grid frequency regulation services with smart charging mechanism[J]. IEEE Transactions on Smart Grid,2016,7(1):156-166.
• [18]WANG Q F,WANG J H,GUAN Y P. Stochastic unit commitment with uncertain demand response[J]. IEEE Transactions on Power Systems,2013,28(1):562-563.
• [19]庞松岭，赵雨楠，张瑞恩，等.市场环境下计及用户响应的电动汽车充电站优化运行策略[J].电力建设，2024,45(10):59-68.PANG Songling,ZHAO Yunan,ZHANG Ruien,et al.The optimal operation strategy of electric vehicle charging stations considering user response in market environment[J].Electric Power Construction,2024,45(10):59-68.
• [20]彭文昊，陆俊，冯勇军，等.计及用户参与不确定性的需求响应策略优化方法[J].电网技术，2018,42(5):1588-1594.PENG Wenhao,LU Jun,FENG Yongjun,et al.A demand response strategy optimization considering user participation uncertainty[J].Power System Technology,2018,42(5):1588-1594.
• [21]王吉兴，余洋，米增强，等.考虑响应不确定性的电动汽车集群可调度容量评估方法[J].浙江电力，2022,41(5):1-7.WANG Jixing,YU Yang,MI Zengqiang,et al.An estimation method for schedulable capability of aggregated electric vehicles considering response uncertainty[J].Zhejiang Electric Power,2022,41(5):1-7.
• [22]张谦，邓小松，岳焕展，等.计及电池寿命损耗的电动汽车参与能量-调频市场协同优化策略[J].电工技术学报，2022,37(1):72-81.ZHANG Qian,DENG Xiaosong,YUE Huanzhan,et al.Coordinated optimization strategy of electric vehicle cluster participating in energy and frequency regulation markets considering battery lifetime degradation[J].Transactions of China Electrotechnical Society,2022,37(1):72-81.
• [23]史乐峰.需求侧管理视角下的电动汽车充放电定价策略研究[D].重庆：重庆大学，2012.SHI Lefeng. Design for the electric vehicle charging and discharging price strategy from demand side management perspective[D].Chongqing:Chongqing University,2012.
• [24]AN Y S,GAO Y X,WU N Q,et al.Optimal scheduling of electric vehicle charging operations considering realtime traffic condition and travel distance[J]. Expert Systems with Applications,2023,213:118941.
• [25]MURATORI M,MORAN M J,SERRA E,et al.Highlyresolved modeling of personal transportation energy consumption in the United States[J]. Energy,2013,58:168-177.