基于Voronoi图和改进免疫克隆选择算法的充电站布局优化

doi:10.3969/j.issn.1008-0198.2026.04.016

湖南电力 ›› 2026, Vol. 46 ›› Issue (4): 121-128.doi: 10.3969/j.issn.1008-0198.2026.04.016

• 电力人工智能与数字化 • 上一篇下一篇

基于Voronoi图和改进免疫克隆选择算法的充电站布局优化

彭世博¹, 肖辉², 雷嘉乐³, 曾林俊⁴

1.华能湖南清洁能源分公司,湖南长沙 410000;
2.长沙理工大学电网防灾减灾全国重点实验室,湖南长沙 410114;
3.加州大学戴维斯分校,美国加州 95616;
4.长沙理工大学能源与动力工程学院,湖南长沙 410114

收稿日期:2026-03-08 出版日期:2026-08-25 发布日期:2026-09-11
通信作者: 彭世博（1999）,男,湖南长沙人,本科,助理工程师,研究方向为车网互动。
作者简介:肖辉（1975）,女,湖南长沙人,博士,教授,博士生导师,研究方向为电动汽车充电控制技术及车网互动、新型电力系统。
基金资助:
湖南省自然科学基金项目(2026JJ80510)

Charging Station Layout Optimization Based on Voronoi Diagram and Improved Immune Clonal Selection Algorithm

PENG Shibo¹, XIAO Hui², LEI Jiale³, ZENG Linjun⁴

1. Hua Neng Hunan Clean Energy Branch, Changsha 410000, China;
2. State Key Laboratory of Disaster Prevention & Reduction for Power Grid, Changsha University of Science & Technology, Changsha 410114, China;
3. University of California, Davis, California 95616, America;
4. College of Energy and Power Engineering, Changsha University of Science & Technology, Changsha 410114, China

Received:2026-03-08 Online:2026-08-25 Published:2026-09-11

摘要/Abstract

摘要： 针对电动汽车充电站布局优化中服务范围划分不精确与算法寻优能力不足的问题,提出一种基于Voronoi图和改进免疫克隆选择算法的充电站选址定容方法。首先,综合考虑充电站建设与运维经济性、区域电网功率约束及用户充电便利性,构建以年总成本最小化为目标的充电站规划模型。其次,引入Voronoi图对规划区域进行服务范围划分,依据充电站位置动态生成服务区域,确保各站点覆盖合理且重合度可控。然后,通过引入抗体间亲和力计算与多项式变异策略对免疫克隆选择算法进行改进,提升其全局搜索能力与收敛速度,以高效求解充电站选址与定容联合优化问题。最后,通过MATLAB仿真算例验证所提模型与算法的有效性,结果表明该方法能够在满足覆盖率与电网约束的前提下,降低充电站综合成本。

关键词: 电动汽车, 充电站布局, Voronoi图, 免疫克隆选择算法, 服务范围

Abstract: Aiming at the problems of imprecise service scope division and insufficient algorithmic optimization ability in the layout optimization of electric vehicle charging stations, a charging station site selection and capacity determination method based on Voronoi diagram and improved immune clone selection algorithm is proposed. Firstly, a charging station planning model is constructed with the goal of minimizing annual total costs by considering the economics of charging station construction and operation and maintenance, the power constraints of the regional power grid, and the convenience of charging for users. Secondly, a Voronoi diagram is introduced to classify the service scope of the planning area, and the service area is dynamically generated based on the location of charging stations to ensure that the coverage of each station is reasonable and the degree of overlap is controllable. On this basis, the immune clonal selection algorithm is improved by introducing affinity calculation between antibodies and polynomial variation strategy to improve its global search capability and convergence speed, so as to solve the joint optimization problem of charging station siting and capacity determination efficiently. Finally, the effectiveness of the proposed model and algorithm is verified by MATLAB simulation examples, and the results show that the method can reduce the comprehensive cost of charging stations under the premise of satisfying the coverage and grid constraints.

Key words: electric vehicles, charging station layout, voronoi diagram, immune clonal selection algorithm, service scope

中图分类号:

TM715

彭世博, 肖辉, 雷嘉乐, 曾林俊. 基于Voronoi图和改进免疫克隆选择算法的充电站布局优化[J]. 湖南电力, 2026, 46(4): 121-128.

PENG Shibo, XIAO Hui, LEI Jiale, ZENG Linjun. Charging Station Layout Optimization Based on Voronoi Diagram and Improved Immune Clonal Selection Algorithm[J]. Hunan Electric Power, 2026, 46(4): 121-128.

参考文献

[1] 张文会,乔梓凡,陈德启. 出租车轨迹数据驱动的充电站选址定容方法[J]. 交通运输系统工程与信息,2025,25(5):291-301.
[2] 栗然,臧向迪,张文昕,等. 共享电动汽车混合充换电站选址优化[J]. 电力自动化设备,2021,41(10):67-74.
[3] 苏粟,李玉璟,贾泽瑞,等. 基于GPS轨迹挖掘的电动出租车充电站规划[J]. 电力自动化设备,2022,42(10):255-263.
[4] 陈骏鹏,苗世洪,何武,等. 考虑农村配电网承载力的电动汽车充电站自适应分阶段选址定容方法[J/OL]. 电力自动化设备,1-18. (2025-11-18)[2026-03-02]. https://doi.org/10.16081/j.epae.202511007.
[5] 吴雨,王育飞,张宇,等. 基于改进免疫克隆选择算法的电动汽车充电站选址定容方法[J]. 电力系统自动化,2021,45(7):95-103.
[6] 何晨可,韦钢,朱兰,等. 电动汽车充换放储一体化电站选址定容[J]. 中国电机工程学报,2019,39(2):479-489.
[7] Fang B,Zhang Q,Luo Z,et al.Charging decision modelling and load collaborative simulation of electric vehicles based on multi-source fusion:Adaptive Huff-LSTM method[J]. Energy,2025,340:139235.
[8] 赵炳耀,陈璟华,郭经韬,等. 基于Voronoi图和改进引力搜索算法的电动汽车充电站选址定容[J]. 广东工业大学学报,2021,38(3):72-78.
[9] 林福根,温祥西,吴明功,等. 基于Voronoi图和改进K-means的扇区优化研究[J]. 西北工业大学学报,2023,41(1):170-179.
[10] Jurado C C,Martínez C M J,Merino G C J,et al. Optimal location of electric vehicle charging stations using proximity diagrams[J]. Sustainable Cities and Society,2024,113:105719.
[11] Jin Y,Acquah M,Seo M,et al.Optimal siting and sizing of EV charging station using stochastic power flow analysis for voltage stability[J]. IEEE Transactions on Transportation Electrification,2024,10(1):777-794.
[12] 曹慕昆,王逸诚,刘新龙,等. 轨迹数据驱动的新能源汽车充电站选址模型研究[J]. 控制与决策,2025,40(9):2739-2747.
[13] 侯慧,唐俊一,王逸凡,等. 城区电动汽车充电站布局规划研究[J]. 电力系统保护与控制,2022,50(14):181-187.
[14] 李晶晶,田桂林,张永敏,等. 基于充电需求的电动汽车充电站选址定容优化方法[J]. 西华大学学报(自然科学版),2025,44(3):47-60.
[15] Zhou B,Wu Q.An improved immune clonal selection algorithm for bi-objective robotic assemble line balancing problems considering time and space constraints[J]. Engineering Computations,2019,36(6):1868-1892.
[16] Lou G,Cai Z.Improved hybrid immune clonal selection genetic algorithm and its application in hybrid shop scheduling[J]. Cluster Computing,2019,22(2):3419-3429.
[17] 焦靖淞,周凯红. 基于改进免疫克隆选择算法的侧铣刀位包络误差优化模型[J]. 机电工程,2025,42(8):1543-1551.
[18] 王雷,邹新. 基于改进免疫克隆选择算法的柔性作业车间调度[J]. 南京理工大学学报(自然科学版),2018,42(3):345-351.
[19] 朱耿,蒋元元,王波,等. 基于Voronoi图与改进TT-GAN的光伏时序数据增强方法[J]. 浙江电力,2026,45(1):102-115.
[20] Mei H,Wu Q,Ren H,et al.Optimization of electric vehicle charging station layout considering the improvement of distribution network resilience under extreme disasters[J]. Energy,2025,323:135831.

基于Voronoi图和改进免疫克隆选择算法的充电站布局优化

Charging Station Layout Optimization Based on Voronoi Diagram and Improved Immune Clonal Selection Algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	张梓钦, 罗志坤, 谢培元, 庄洪波, 熊尚峰, 胡涵. 面向湖南地域特性的车网互动放电价格模型与多模式市场机制研究[J]. 湖南电力, 2026, 46(3): 61-68.
[2]	李永军, 潘明明, 郑博文, 王小明, 赵文广, 汪宇航. 基于改进双向门控循环单元的电动汽车可调节能力辨识方法[J]. 湖南电力, 2026, 46(1): 19-28.
[3]	唐轩逸, 刘平, 兰征, 唐明斌, 胡思阳. 基于河马优化算法的电动汽车有序充电策略[J]. 湖南电力, 2026, 46(1): 76-83.
[4]	李逸凡, 张晓东, 张鸿伟, 陈颉. 融合IGDT鲁棒-机会型决策的DQN双策略电动汽车移动充电站协同优化调度[J]. 湖南电力, 2025, 45(6): 9-18.
[5]	孙充勃, 原凯, 宋毅, 高枝, 丁羽頔, 杜孟珂. 基于高斯混合模型的电动汽车用电行为随机模拟与充电同时系数测算方法[J]. 湖南电力, 2025, 45(6): 19-25.
[6]	曾伟杰, 崔泽政, 尹华平, 申丽曼, 刘谋海, 郑闻麟. 考虑台风影响的电动汽车充电桩故障改进决策树预测方法[J]. 湖南电力, 2025, 45(4): 10-14.
[7]	许文哲, 方八零, 张淇菲, 李伟, 刘浩. 基于阶段分时电价响应的电动汽车充电负荷优化策略[J]. 湖南电力, 2024, 44(1): 94-100.
[8]	康童, 朱吉然, 唐海国, 周恒逸, 周可慧. 采用改进共生生物搜索算法的大规模电动汽车接入微电网协调优化研究[J]. 湖南电力, 2023, 43(5): 144-150.
[9]	李奕杰, 宋恒, 叶晨晖, 申庆祥. 基于融合模型驱动和数据驱动的电动汽车充电负荷预测[J]. 湖南电力, 2023, 43(3): 9-15.
[10]	谢鹰, 郑众, 刘剑峰, 高希, 李大祥. 基于遗传算法计及充电行驶距离的电动汽车充电网络规划[J]. 湖南电力, 2023, 43(3): 29-36.
[11]	邓元望, 尹会春, 鄂加强, 刘帅, 朱浩. 电动汽车电池组绝缘监测方法研究[J]. 湖南电力, 2023, 43(1): 46-49.