新型大规模电动汽车充电负荷预测方法及其在区域配电网中的应用  

A New Charging Load Forecasting Method for Large-Scale Electric Vehicles and Its Application in Regional Distribution Network

作　　者：熊昊哲 刘曼佳 向慕超 赵子龙 唐金锐[2] XIONG Haozhe;LIU Manjia;XIANG Muchao;ZHAO Zilong;TANG Jinrui(Electric Power Research Institute,State Grid Hubei Electric Power Co.,Ltd.,Wuhan Hubei 430077,China;School of Automation,Wuhan University of Technology,Wuhan Hubei 430070,China)

机构地区：[1]国网湖北省电力有限公司电力科学研究院,湖北武汉430077 [2]武汉理工大学自动化学院,湖北武汉430070

出　　处：《湖北电力》2022年第5期31-36,共6页Hubei Electric Power

基　　金：国家自然科学基金(项目编号:52276160);国网湖北省电力有限公司科技项目(项目编号:52153222000F)。

摘　　要：越来越多的电动汽车(EV)保有量将对现有的居民微电网及配电网络(PDN)构成潜在威胁,大规模的电动汽车充电负荷将影响配电网的运行。采用K-means和长短期记忆神经网络(LSTM)算法,提出了一种大规模电动汽车充电负荷的日负荷曲线预测方法。为突出未来电动汽车数量的不确定性,将根据不同的电动汽车增长模型预测电动汽车的数量。考虑到大规模的电动汽车充电负载,系统的方法包括电动汽车充电配置文件和未来的电动汽车保有量可以预估未来电动汽车充电负载。该方法在湖北省的实证分析中得到了验证。仿真结果表明,预计在2025年电动汽车充电负荷的最大值将出现在18:00,达到938.66 MW,比现有负荷峰值提升2.01%。The growing number of electric vehicles(EVs)will pose a potential threat to the existing residential microgrids and power distribution networks(PDNs).The large-scale EV charging load will affect the operation of PDNs.In this paper,a daily load curve forecasting method for large-scale EV charging load is proposed by using Kmeans and long short-term memory neural network(LSTM)algorithms.In order to highlight the uncertainty of the number of electric vehicles in the future,the number of electric vehicles will be projected based on different electric vehicle growth models.With the large-scale EV charging load considered,the system's approach including EV charging profile and future EV ownership can be employed to predict the future EV charging load.The proposed method is verified by the empirical analyses in Hubei province.The simulation results indicate that the maximum value of the predicted EV charging load in 2025 would occur at 18:00 and equal 938.66 MW,which could elevate the existing load peak by 2.01%in 2025.

关 键 词：电动车 日负荷曲线 充电负载 配电网 

分 类 号：U469.72[机械工程—车辆工程]