基于负荷跟踪和客户低感知的电动汽车群调个控充电管理方法  

Group-tuning and Individual-control Charging Management Method for Electric Vehicles Based on Load Tracking and Low Customer Perception

作　　者：文爱军 姜雨滋 孟洪民 刘泽三 WEN Aijun;JIANG Yuzi;MENG Hongmin;LIU Zesan(State Grid Information&Telecommunication Group Co.,Ltd.,Changping District,Beijing 100052,China)

机构地区：[1]国网信息通信产业集团有限公司,北京市昌平区100052

出　　处：《电力信息与通信技术》2024年第3期43-51,共9页Electric Power Information and Communication Technology

基　　金：国家重点研发计划项目(2022YFB2403900)。

摘　　要：针对电动汽车充电站对电网负荷调控指令跟踪精度低、充电客户对站内负荷分配不满意的问题,文章提出了基于负荷跟踪和客户低感知的电动汽车群调个控充电管理方法。首先,基于改进的条件生成对抗网络建立电动汽车单体可调度潜力的预测模型,可根据客户车辆电池管理系统历史上报的充电数据,生成车辆调度潜力时序曲线。然后,根据电动汽车充电集群的调度潜力总曲线和来自电网的负荷调控信号,提出计及能量损失和客户低感知的负荷分解优化模型,使用改进的多目标麻雀搜索算法进行求解,并在四川成都的电动汽车充电站验证了所提模型的合理性,证实其能有效地降低对客户车辆的控制功率损失,提高对调度负荷控制信号的跟踪精度,同时提高单个充电客户的感知满意度。In response to the problems of low tracking accuracy of electric vehicle(EV)charging stations to grid load regulation commands and charging customers'dissatisfaction with station load allocation,a group-tuning individual-control charging management method for EVs based on load tracking and low customer perception is proposed.Firstly,an improved conditional generative adversarial network is used to establish a prediction model of the adjustable potential of EV individually.This model can generate a time-series curve of vehicle dispatch potential based on the charging data historically reported by the battery management system of the customer's vehicle.Then,based on the total dispatch potential curve of EV charging cluster and the load control signal from the grid,a load decomposition optimization model is proposed to consider the energy loss and the low perception of customers.The improved multi-objective sparrow search algorithm is used for solving the problem.The reasonableness of the proposed model is verified at electric vehicle charging stations in Chengdu,Sichuan.It was confirmed that the model could effectively reduce the control power loss of customer vehicles,improve the load tracking accuracy of the load control signal,and at the same time,increase the perceived satisfaction of individual charging customers.

关 键 词：电动汽车 可调度能力 负荷跟踪 条件生成对抗网络 多目标麻雀搜索算法 低感知函数 

分 类 号：TM73[电气工程—电力系统及自动化]