发电技术 ›› 2026, Vol. 47 ›› Issue (2): 383-394.DOI: 10.12096/j.2096-4528.pgt.260215

• 虚拟电厂 • 上一篇    

考虑用户决策偏好的电动汽车充电引导策略

李恒杰1, 张尊康1, 周云2, 冯冬涵2, 马喜平3   

  1. 1.兰州理工大学电气工程与信息工程学院,甘肃省 兰州市 730050
    2.上海交通大学电力传输与功率变换控制教育部重点实验室,上海市 闵行区 200240
    3.国网甘肃省电力公司电力科学研究院,甘肃省 兰州市 730070
  • 收稿日期:2025-04-12 修回日期:2026-06-20 出版日期:2026-04-30 发布日期:2026-04-21
  • 作者简介:李恒杰(1981),男,博士,教授,研究方向为电力/综合能源系统应急及用电能效管理,lihj915@lut.edu.cn
    张尊康(1999),男,硕士研究生,研究方向为充电基础设施规划及运行优化,ZZK_631@163.com
    周云(1990),男,博士,讲师,研究方向为电力/综合能源系统应急及用电能效管理,yun.zhou@sjtu.edu.cn
    冯冬涵(1981),男,博士,教授,研究方向为智能电网中电动策略与风险、电力市场理论与设计等,seed@sjtu.edu.cn
    马喜平(1987),男,硕士,高级工程师,研究方向为新能源并网与电网降损节能技术,maxpgs@163.com
  • 基金资助:
    国家自然科学基金项目(52167014)

Electric Vehicle Charging Guidance Strategy Considering User Decision Preferences

Hengjie LI1, Zunkang ZHANG1, Yun ZHOU2, Donghan FENG2, Xiping MA3   

  1. 1.School of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, Gansu Province, China
    2.Key Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Shanghai Jiao Tong University, Minhang District, Shanghai 200240, China
    3.Electric Power Research Institute, State Grid Gansu Electric Power Company, Lanzhou 730070, Gansu Province, China
  • Received:2025-04-12 Revised:2026-06-20 Published:2026-04-30 Online:2026-04-21
  • Supported by:
    National Natural Science Foundation of China(52167014)

摘要:

目的 在电动汽车充电引导过程中,用户在选择充电站中存在不同偏好,导致用户的充电站选择标准不同,影响用户参与优化调度。因此,针对用户选择充电站习惯以及用户与充电聚合商利益冲突,提出了一种考虑目标充电站选择习惯的电动汽车充电引导策略。 方法 采用自组织特征映射(self-organizing feature mapping,SOFM)来进行用户画像,再使用SHAP(Shapley additive explanations)确定最佳画像结果。使用熵权法来确定每类用户在选择充电站过程中时间成本和经济成本所占的权重;根据权重结果将用户的费用成本和时间成本归化为用户满意度;然后,根据用户满意度对用户进行充电引导。 结果 算例表明,该策略相比于最短路径算法显著提升了用户选择充电站的满意度和充电桩的单位时间盈利,同时在不同的交通情况下该策略受影响较小。 结论 该策略有效地解决了用户充电决策偏好对充电引导的影响,对提高用户的充电利益和减少用户的充电拥堵有重要意义。

关键词: 电动汽车(EV), 决策偏好, 用户画像, 充电引导, 费用成本, 时间成本, 满意度

Abstract:

Objectives During the electric vehicle (EV) charging guidance process, users have different preferences in selecting charging stations, resulting in different selection criteria, which affects their participation in optimal scheduling. Therefore, considering user habits in selecting charging stations and the conflicts of interest between users and charging aggregators, an EV charging guidance strategy that incorporates target charging station selection habits is proposed. Methods Self-organizing feature mapping (SOFM) is used for user profiling, and Shapley additive explanations (SHAP) are utilized to determine the optimal profiling results. Secondly, the entropy weight method is applied to determine the weights of time cost and economic cost for each type of user during the charging station selection process. Based on the weight results, user economic cost and time cost are normalized into user satisfaction. Then, users are guided to charge based on their user satisfaction. Results The example shows that compared with the shortest path The numerical example shows that compared with the shortest path algorithm, this strategy significantly improves user satisfaction in selecting charging stations and the profit per unit time of charging piles. Additionally, this strategy is less affected under different traffic conditions. Conclusions This strategy effectively addresses the impact of user charging decision preferences on charging guidance, which is of great significance for improving user charging benefits and reducing charging congestion.

Key words: electric vehicle (EV), decision preferences, user profiling, charging guidance, economic cost, time cost, satisfaction

中图分类号: