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

李逸凡; 张晓东; 张鸿伟; 陈颉

doi:10.3969/j.issn.1008-0198.2025.06.002

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

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

专家专栏：考虑复杂安全边界的大规模新型电力系统规划建模与优化问题研究 | 更新时间：2026-02-06

- 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
- Method of DNQ Dual-Strategy Collaborative Optimization Scheduling for Electric Vechicle Mobile Charging Stations Integrating IGDT Robustness Opportunistic Decision-Making
- 湖南电力 2025年45卷第6期页码：9-18
- 作者机构：
  
  1. 湘潭大学自动化与电子信息学院,湖南,湘潭,411105
  2. 中国铁路广州局集团有限公司长沙机务段,湖南,长沙,410007
  3. 广西电网有限责任公司百色供电局,广西,百色,533099
- 作者简介：
- 基金信息：
  
  湖南省教育厅教学改革项目(202401000571);湘潭大学校级科研项目(22QDZ05)
- DOI：10.3969/j.issn.1008-0198.2025.06.002
  中图分类号： TM732
- 网络首发：2026-01-13，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
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.

李逸凡, 张晓东, 张鸿伟, et al. Method of DNQ Dual-Strategy Collaborative Optimization Scheduling for Electric Vechicle Mobile Charging Stations Integrating IGDT Robustness Opportunistic Decision-Making[J]. 2025, 45(6): 9-18.
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. DOI： 10.3969/j.issn.1008-0198.2025.06.002.

李逸凡, 张晓东, 张鸿伟, et al. Method of DNQ Dual-Strategy Collaborative Optimization Scheduling for Electric Vechicle Mobile Charging Stations Integrating IGDT Robustness Opportunistic Decision-Making[J]. 2025, 45(6): 9-18. DOI： 10.3969/j.issn.1008-0198.2025.06.002.

摘要

电动汽车(electric vehicle

EV)移动充电站(mobile charging station

MCS)面临需求预测误差影响、多目标协同不足及多主体交互机制缺失等难点

亟须解决多维度协同优化问题。为此

提出一种基于信息间隙决策理论(information gap decision theory

IGDT)的深度Q网络(deep Q-network

DQN)双策略MCS调度优化方法。首先

搭建多目标优化框架

以最小化系统总成本、最小化用户平均等待时间、提升充电需求满足率为目标实现协同平衡。其次

结合IGDT量化充电需求不确定性参数

设计动态调度策略

当高不确定性(如节假日需求突增时)

启用鲁棒性模型优先保障高需求区域基础服务不中断。当低不确定性(如工作日通勤时段时)

切换机会性模型通过路径优化、电价低谷充电优化成本

以适配不同场景决策偏好。最后

采用改进双策略深度强化学习算法DQN求解模型

并通过仿真实验验证其有效性。算例分析表明

相比传统演员-评论家算法

所提DQN算法模型通过动态选择鲁棒型决策和机会型决策

能够有效降低MCS运行成本

合理满足EV用户的充电需求。

Abstract

Electric vehicle(EV) mobile charging stations(MCS) face challenges including demand prediction errors

insufficient multi-objective coordination

and lack of multi-agent interaction mechanisms

necessitating multidimensional collaborative optimization. An IGDT-based dual-strategy DQN optimization method for MCS scheduling is proposed. First

a multi-objective optimization framework is constructed to achieve coordinated balance with the goals of minimizing total system costs

minimizing the average user waiting time

and improving the satisfaction rate of charging demand. Second

by combining IGDT to quantify uncertainty parameters in charging demand

a dynamic scheduling strategy is designed. Under high-uncertainty scenarios(such as holiday demand spikes)

a robustness model is activated to prioritize to ensure uninterrupted basic services in high-demand areas. Under low-uncertainty periods(such as weekday commutes periods)

an opportunistic model is applied to optimize costs through route planning and off-peak charging

accommodating different scenario-based decision preferences. Finally

an improved dual-strategy deep reinforcement learning DQN algorithm is used to solve the model

and its effectiveness is verified through simulation experiments. Case analysis shows that

compared to the traditional actor-critic(AC) algorithm

the proposed DQN model can effectively reduce MCS operating costs and reasonably meet EV users' charging demands by dynamically selecting robust or opportunistic decision-making.

关键词

Keywords

references

王娟. 国际能源署(IEA)和中国建立广泛、深入的合作关系[J]. 天然气勘探与开发,2017,40(1):113.

钱兴坤,陆如泉,罗良才,等. “稳中有变”下探寻能源均衡之道:国内外油气行业2024年回顾与2025年展望[J]. 国际石油经济,2025,33(2):1-6,24.

SHIRIZADEH B,AILLERET A,GUILLON A,et al.Clean hydrogen economy outlook:green is the future[C] //2024 20th International Conference on the European Energy Market (EEM). Istanbul,Turkiye. 2024:1-7.

AFSHAR S,MACEDO P,MOHAMED F,et al.A literature review on mobile charging station technology for electric vehicles[C] //2020 IEEE Transportation Electrification Conference & Expo(ITEC). Chicago,IL,USA. 2020:1184-1190.

RĂBOACĂ M S,BĂNCESCU I,PREDA V,et al. An optimization model for the temporary locations of mobile charging stations[J]. Mathematics,2020,8(3):453.

VANSOLA B,CHANDRA M,SHUKLA R N.GIS-based model for optimum location of electric vehicle charging stations[M] //Recent Advances in Transportation Systems Engineering and Management. Springer,2020:163-172.

SUDDDALA S.Dynamic demand forecasting in supply chainsusing hybrid arima-LSTM architectures[J]. International Journal of Advanced Research,2024,12(10):1167-1171.

李建华,王泽鼎. 考虑路径耗时的城市汽车分布式充电桩选点规划[J]. 吉林大学学报(工学版),2023,53(8):1184-1191.

钱科军,秦萌,宋远军,等. 基于模糊隶属度的充电站多目标优化调度[J]. 电力建设,2020,41(2):118-124.

TUCKER N,TURAN B,ALIZADEH M.Online charge scheduling for electric vehicles in autonomous mobility on demand fleets[C] //2019 IEEE Intelligent Transportation Systems Conference(ITSC). Auckland,New Zealand. IEEE,2019:226-231.

何克成,贾宏杰,穆云飞,等. 基于信息间隙决策理论的卡车式移动充电站协同调度策略[J]. 电力系统自动化,2024,48(15):44-53.

李德强,任新一,徐佳. 无线可充电传感器网络中异构感知的限时移动充电调度[J]. 计算机科学,2025,52(6):355-364.

沙浩冬. 高时效低成本的传感器移动协作充电调度优化研究[D]. 南京:南京邮电大学,2023.

申辰雷. 无线传感器网络中面向事件监测的移动充电调度研究[D]. 南京:南京邮电大学,2023.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于融合模型驱动和数据驱动的电动汽车充电负荷预测

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

基于阶段分时电价响应的电动汽车充电负荷优化策略