基于服务站区域互联的共享电动汽车调度方法  

Scheduling Method for Shared Electric Vehicles Based on Regional Interconnection of Service Stations

作　　者：何鈜博 徐伟 HE Hongbo;XU Wei(State Grid Shanghai Electric Power Company Fengxian Power Supply Company)

机构地区：[1]国网上海市电力公司奉贤供电公司

出　　处：《上海节能》2023年第12期1882-1891,共10页Shanghai Energy Saving

摘　　要：用户出行的不规律性和不均衡性造成服务站点保有的共享电动汽车数量存在动态供需不平衡的问题,一定程度上限制了共享车辆服务行业的发展。为此,在准确预测共享电动汽车需求量的基础上,提出了基于服务站区域互联架构的共享电动汽车调度方法。在充分考虑用户实际需求影响因素的基础上,提出服务站区域互联调度模型,采用改进的Elman神经网络预测区域互联站点的车辆需求,以满足用户的出行需求。结合上海EVCARD共享电动汽车行业的实际数据,通过仿真实验将改进的Elman神经网络预测模型和未改进的Elman神经网络预测模型的预测结果与实际需求量进行对比,采用不同指标进行计算和分析,验证了该方法的合理性和优越性。The irregularity and imbalance of user travel have caused a dynamic supply-demand imbalance in the number of shared electric vehicles maintained by service stations,which to some extent limits the development of the shared vehicle service industry.Therefore,based on accurately predicting the demand for shared electric vehicles,a scheduling method for shared electric vehicles based on the regional interconnection architecture of service stations is proposed.On the basis of fully considering the factors affecting the actual demand of users,a regional interconnection scheduling model for service stations is proposed,and an improved Elman neural network is used to predict the vehicle demand of regional interconnection stations to meet the travel needs of users.Combined with the actual data of the EVCARD shared electric vehicle industry in Shanghai,the prediction results of the improved Elman neural network prediction model and the unimproved Elman neural network prediction model are compared with the actual demand through simulation experiments,and different indicators are used for calculation and analysis to verify the rationality and superiority of the method.

关 键 词：共享电动汽车 服务站区域互联 需求预测 神经网络 车辆调度规划 

分 类 号：U491[交通运输工程—交通运输规划与管理]