[1]杨 骏,王冬姣,韩帅帅,等.基于改进NSGA-II的电动汽车多目标充电调度优化[J].机械与电子,2026,44(07):1-12.
　YANG Jun,WANG Dongjiao,HAN Shuaishuai,et al.Multi-objective Charging Scheduling Optimization for Electric Vehicles Based on an Improved NSGA-II Algorithm[J].Machinery & Electronics,2026,44(07):1-12.
点击复制

基于改进NSGA-II的电动汽车多目标充电调度优化()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年07期
页码:
1-12
栏目:
研究与设计
出版日期:
2026-07-25

文章信息/Info

Title:
Multi-objective Charging Scheduling Optimization for Electric Vehicles Based on an Improved NSGA-II Algorithm
文章编号:
1001-2257(2026)07-0001-12
作者:
杨 骏1; 王冬姣1; 韩帅帅2; 苏进展2
1.长安大学经济与管理学院,陕西 西安 710064;
2.长安大学工程机械学院,陕西 西安 710064
Author(s):
YANG Jun1; WANG Dongjiao1; HAN Shuaishuai2; SU Jinzhan2
(1.School of Economics and Management,Chang’an University,Xi’an 710064,China;
2.School of Construction Machinery,Chang’an University,Xi’an 710064,China)
关键词:
电动汽车; 充电调度; 改进NSGA-II算法; 多目标优化
Keywords:
electric vehicle; charging scheduling; improved NSGA-II algorithm; multi objective optimization
分类号:
U491.8;TM73
文献标志码:
A
摘要:
针对电动汽车充电调度中时间效率、经济成本与负荷平稳性难以协同优化的问题,构建了一种多目标充电调度优化模型。在满足车辆充电需求、充电桩容量约束及系统总功率约束的条件下,以车辆平均时间代价最小、平均充电成本最低及站内总负荷波动最小为目标,建立电动汽车多目标调度模型。针对标准非支配排序遗传算法(NSGA II)在离散调度问题中存在搜索能力不足、自适应调节能力较弱等问题,提出一种改进算法ALD NSGA II。该算法在NSGA II框架下引入连续隐空间搜索、自适应参数调节、精英引导差分进化及局部强化机制,以提高算法的收敛性能和Pareto前沿质量。仿真实验结果表明,与 NSGA-II、MODE-RMO 和MOPSO 相比,ALD-NSGA II在Pareto前沿分布、反向世代距离、超体积指标、平均IGD收敛曲线以及折中解负荷调度效果等均表现出更优性能。研究结果表明,所构建模型与改进算法能够有效实现电动汽车充电调度的多目标优化,并在提升调度综合性能和改善负荷平滑性方面具有较好的应用潜力。
Abstract:
To address the challenge of simultaneously optimizing temporal efficiency,economic cost,and load smoothness in electric vehicle charging scheduling,a multi objective charging scheduling optimization model is constructed.Under constraints that ensure vehicle charging demands,charger pile capacity,and total system power limits are satisfied,the model is formulated to minimize the average time cost of vehicles, the average charging cost,and the fluctuation of the total load within the station.To address the limitations of the standard Non dominated Sorting Genetic Algorithm II (NSGA-II) in discrete scheduling problems, such as insufficient search capability and weak adaptivity,an improved algorithm named ALD-NSGA-II is proposed.Within the NSGA-II framework,the proposed algorithm integrates continuous latentspace search,adaptive parameter adjustment,leader guided differential evolution,and a local intensification mechanism to enhance convergence performance and Pareto front quality.Simulation results show that,compared with NSGA-II,MOD- RMO,and MOPSO,ALD-NSGA-II achieves superior performance in terms of Pareto front distribution,inverted generational distance (IGD),hypervolume,the average IGD convergence curve,and the load scheduling performance of the compromise solution.The results demonstrate that the proposed model and the improved algorithm can effectively realize multi-objective optimization for electric vehicle charging scheduling,and exhibit promising potential for improving overall scheduling performance and enhancing load smoothing.

参考文献/References:

[1] Motlagh S G,Oladigbolu J,Li L.A review on electric vehicle charging station operation considering market dynamics and grid interaction[J].Applied Energy,2025,392:126058.

[2] Chandra I,Singh N K,Samuel P.A comprehensive review on coordinated charging of electric vehicles in distribution networks[J].Journal of Energy Storage,2024,89:111659.
[3] Zhao Zhonghao,Lee C K M,Ren Jingzheng.A two-level charging scheduling method for public electric vehicle charging stations considering heterogeneous demand and nonlinear charging profile[J].Applied Energy,2024,355:122278.
[4] Mishra S,Mondal A,Mondal S.A multi-objective optimization framework for electric vehicle charge scheduling with adaptable charging ports[J].IEEE Transactions on Vehicular Technology,2022,72(5):5702-5714.
[5] Ren Yuling,Tan Mao,Su Yongxin,et al.Two-stage adaptive robust charging scheduling of electric vehicle station based on hybrid demand response[J].IEEE Transactions on Transportation Electrification,2025,11:1442-1454.
[6] Khiar A,Brahmia M E A,Oulamara A,et al.Multi-objective electric vehicle charging scheduling under stochastic duration uncertainty[J].Omega,2025:103506.
[7] Zhang Lei,Ji Yingjun,Li Xiaohui,et al.Multi-objective charging scheduling for electric vehicles at charging stations with renewable energy generation[J]. Green Energy and Intelligent Transportation,2025:100283.
[8] Deb K,Pratap A,Agarwal S,Meyarivan T.A fast and elitistmultiobjective genetic algorithm:NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002,6(2):182-197.
[9] Ma Haiping,Zhang Yajing,Sun Shengyi,et al.A comprehensive survey on NSGA-II for multi-objective optimization and applications[J].Artificial IntelligenceReview,2023,56(12):15217-15270.
[10] Chen Jingwen,Mao Lei,Liu Yaoxian,et al.Multi-objective optimization scheduling of active distribution network considering large-scale electric vehicles based on NSGAII-NDAX algorithm[J].IEEE Access, 2023,11:97259-97273.
[11] Chen Yikang,Bao Zhicheng,Tan Yihang,et al.Hierarchical charging scheduling strategy for electric vehicles based on NSGA-II[J].Energies,2025,18(13):3269.
[12] Li Jingxuan,Tang Hezhong,Li Pengcheng,et al.An improved NSGA-II based multi-objective optimization model for electric vehicle charging station selection[J].Mathematics,2025,13(23):3855.
[13] Zhang Bo,Zhao Meng,Hu Xiangpei.Location planning of electric vehicle charging station with users’ preferences and waiting time:multi-objective bilevel programming model and HNSGA II algorithm[J].International Journal of Production Research,2023,61(5):1394-1423.
[14] 崔明勇,吕静,薛思嘉,等.考虑电动汽车优先级需求的两阶段优化调度策略[J].电工电能新技术,2024,43(4):20-28.
[15] 李恒杰,胡哲辉,周云,等.基于混合整数线性规划的电动汽车充电引导优化策略[J].电网技术,2025,49(10):4386-4395.
[16] 骆徐,程静.考虑用户随机出行行为的大规模电动汽车集群调度策略[J].太阳能学报,2025,46(11):419-430.
[17] 张芮华,马永翔,闫群民,等.多目标优化的高渗透率电动汽车有序充电策略[J].电工技术,2024(6):26-31.
[18] 陈奎,马子龙,周思宇,等.电动汽车两阶段多目标有序充电策略研究[J].电力系统保护与控制,2020,48(1):65-72.
[19] Coello C A C,Cortés N C.Solvingmultiobjective optimization problems using an artificial immune system[J].Genetic Programming and Evolvable Machines, 2005,6(2):163-190.
[20] Zitzler E,Thiele L.Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach[J].IEEE Transactions on Evolutionary Computation,2002,3(4):257-271.
[21] 黄小庆,陈颉,谢啟波,等.用户充电选择对电网充电调度的影响[J].电工技术学报,2018,33(13):3002-3011.
[22] 刘向军,潘娟,许刚.基于用户电网双向优化的电动私家车日间调度[J].计算机应用与软件,2020,37(10):99-106.
[23] Coello C A C,Pulido G T,Lechuga M S.Handling multiple objectives with particle swarm optimization [J].IEEE Transactions on Evolutionary Computation,2004,8(3):256-279.
[24] Chen Xu,Du Wenli,Qian Feng.Multi-objective differential evolution with ranking-based mutation operator and its application in chemical process optimization[ J].Chemometrics and Intelligent Laboratory Systems,2014,136:85-96.
[25] Mena R,Godoy M,Catalán C,et al.Multi-objective two-stage stochastic unit commitment model for wind-integrated power systems:A compromise programming approach[J].International Journal of Electrical Power and Energy Systems,2023,152:109214.

相似文献/References:

[1]雷永锋,孙莉莉,徐慧博.Z源逆变在电动汽车电机驱动系统中的应用研究[J].机械与电子,2018,(09):52.
　LEI Yongfeng,SUN Lili,XU Huibo.Research of Z-source Inverter in Electric Vehicle Motor Drive System[J].Machinery & Electronics,2018,(07):52.
[2]史国宝１,宋天麟２,金达锋３.电机驱动的 ＡＢＳ／ＴＣＳ的建模仿真[J].机械与电子,2019,(12):33.
　,Modeling and Simulation Based on Motor Driven ABS/TCS[J].Machinery & Electronics,2019,(07):33.
[3]赵 熙,候亚虹,汪贵平,等.基于云平台的电池管理系统设计与实现[J].机械与电子,2019,(12):51.
　ZHAO Xi,HOU Yahong,WANG Guiping,et al.Design and Implementation of Battery Management System Based on Cloud Platform[J].Machinery & Electronics,2019,(07):51.

备注/Memo

备注/Memo:
收稿日期:2026-05-05
基金项目:国家自然科学基金资助项目(52475050)
作者简介:杨 骏 (1978-),女,江苏镇江人,博士,副教授,研究方向为企业数字化管理、市场营销等。
更新日期/Last Update: 2026-08-27