计及相似日与气象因素的电动汽车充电负荷聚类预测

doi:10.12204/j.issn.1000-7229.2021.02.006

电力建设 ›› 2021, Vol. 42 ›› Issue (2): 43-49.doi: 10.12204/j.issn.1000-7229.2021.02.006

• 电动汽车 ·栏目主持孙英云教授、胡俊杰副教授 • 上一篇下一篇

计及相似日与气象因素的电动汽车充电负荷聚类预测

刘敦楠¹, 张悦¹, 彭晓峰², 刘明光¹, 王文², 加鹤萍¹, 秦光宇¹, 王峻², 杨烨²

1.新能源系统国家重点实验室(华北电力大学), 北京市 102206
2.国网电动汽车服务有限公司,北京市 100053

收稿日期:2020-08-21 出版日期:2021-02-01 发布日期:2021-02-09
通讯作者: 张悦
作者简介:刘敦楠(1979),男,博士,副教授,主要研究方向为电力市场与能源互联网;|彭晓峰(1975),男,高级工程师,主要研究方向为电动汽车与电网互动;|刘明光(1993),男,博士研究生,主要研究方向为需求侧资源聚合;|王文(1967),男,博士,主要研究方向为需求侧资源聚合交易;|加鹤萍(1992),女,博士,讲师,主要研究方向为智能电网风险评估;|秦光宇(1994),男,博士研究生,主要研究方向为综合能源系统运行优化;|王峻(1972),女,硕士研究生,主要研究方向为需求侧资源聚合交易;|杨烨(1985),男,博士,主要研究方向为车网互动技术与商业模式。
基金资助:
国家自然科学基金项目(72001078)

Clustering Prediction of Electric Vehicle Charging Load Considering Similar Days and Meteorological Factors

LIU Dunnan¹, ZHANG Yue¹, PENG Xiaofeng², LIU Mingguang¹, WANG Wen², JIA Heping¹, QIN Guangyu¹, WANG Jun², YANG Ye²

1. State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources(North China Electric Power University), Beijing 102206,China
2. State Grid Electric Vehicle Service Company, Beijing 100053, China

Received:2020-08-21 Online:2021-02-01 Published:2021-02-09
Contact: ZHANG Yue
Supported by:
This work is supported by National Natural Science Foundation of China(72001078)

摘要/Abstract

摘要：

电动汽车充电负荷精准预测对于电网调度、电力市场交易、充电站规划建设等具有实际意义。由于电动汽车充电负荷特性异于传统的电力负荷,两者负荷的规律性及影响因素的敏感性各有不同,有必要针对电动汽车充电负荷影响因素及预测模型开展针对性研究。考虑到不同类型电动汽车充电负荷时间序列特性及影响因素存在差异,构建考虑日类型、最高与最低温度的电动汽车充电负荷预测模型;采用模糊C均值(fuzzy C-means, FCM)聚类算法对充电负荷进行聚类分析,挖掘数据特征属性,提取相似日负荷;针对聚类后的相似日负荷采用最小二乘支持向量机(least square support vector machine, LS-SVM)进行预测。将所得的预测结果和测试集进行对比,结果显示,基于该模型的预测精度高于使用非聚类的LS-SVM方法,验证了预测模型的有效性。

关键词: 电动汽车, 充电负荷预测, 日期类型, 模糊C均值(FCM), 最小二乘支持向量机(LS-SVM)

Abstract:

Accurate prediction of electric vehicle charging load has practical significance for power grid dispatching, power market trading, charging station planning and construction. Because the characteristics of electric vehicle charging load are different from the traditional electric load, it is necessary to carry out targeted research on the influencing factors and prediction model of electric vehicle charging load. Considering the differences of time series characteristics and influencing factors of different types of electric vehicle charging load, a prediction model of electric vehicle charging load considering daily type, maximum and minimum temperature is established. Fuzzy C-means (FCM) is used to cluster the charging load, data feature attributes are mined, and similar daily load is extracted. The least square support vector machine (LS-SVM) is used to predict the similar daily load after clustering. The prediction results are compared with the test set, and the results show that the prediction accuracy of the proposed model is higher than that of the LS-SVM method, which verifies the effectiveness of the prediction model.

Key words: electric vehicle, charging load forecasting, date type, fuzzy C-means(FCM), least square support vector machine (LS-SVM)

中图分类号:

TM714

刘敦楠, 张悦, 彭晓峰, 刘明光, 王文, 加鹤萍, 秦光宇, 王峻, 杨烨. 计及相似日与气象因素的电动汽车充电负荷聚类预测[J]. 电力建设, 2021, 42(2): 43-49.

LIU Dunnan, ZHANG Yue, PENG Xiaofeng, LIU Mingguang, WANG Wen, JIA Heping, QIN Guangyu, WANG Jun, YANG Ye. Clustering Prediction of Electric Vehicle Charging Load Considering Similar Days and Meteorological Factors[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(2): 43-49.

图/表 8

图1 电动汽车充电负荷前期分析流程示意

Fig.1 Flow of preliminary analysis of electric vehicle charging load

图2 2019年11月至2020年4月北京地区工作日与非工作日充电负荷

Fig.2 Charging load of working days and non-working days in Beijing

图3 2020年1—7月某地区电动汽车不同温度下的典型充电负荷曲线

Fig.3 Typical charging load curve of electric vehicles at different temperatures in a certain area from January to July in 2020

图4 负荷预测流程图

Fig.4 Flow chart of load forecast

表1 BP神经网络和LS-SVM预测λMAPE对比

Table 1 Comparison of prediction accuracy between BP neural network and LS-SVM

图5 BP神经网络和LS-SVM预测结果

Fig.5 BP neural network and LS-SVM prediction chart

图6 不同场景预测结果

Fig.6 Prediction curve of different methods

图7 不同场景预测误差对比

Fig.7 Comparison of prediction errors of different methods

参考文献 24

[1]	苏小林, 张艳娟, 武中, 等. 规模化电动汽车充电负荷的预测及其对电网的影响[J]. 现代电力, 2018,35(1):45-54.
	SU Xiaolin, ZHANG Yanjuan, WU Zhong, et al. Forecasting the charging load of large-scale electric vehicle and its impact on the power grid[J]. Modern Electric Power, 2018,35(1):45-54.
[2]	TUSHAR M H K, ZEINEDDINE A W, ASSI C. Demand-side management by regulating charging and discharging of the EV, ESS, and utilizing renewable energy[J]. IEEE Transactions on Industrial Informatics, 2018,14(1):117-126.
[3]	袁泉, 汤奕. 基于路-电耦合网络的电动汽车需求响应技术[J/OL]. 中国电机工程学报, [2020-07-19]. https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/11.2107.tm.20200515.1131.009.html.
	YUAN Quan, TANG Yi. Electric vehicle demand response technology based on road electric coupling network[J]. Proceedings of CSEE, [2020-07-19]. https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/11.2107.tm.20200515.1131.009.html.
[4]	孙玲玲, 高赐威, 谈健, 等. 负荷聚合技术及其应用[J]. 电力系统自动化, 2017,41(6):159-167.
	SUN Lingling, GAO Ciwei, TAN Jian, et al. Load aggregation technology and its applications[J]. Automation of Electric Power Systems, 2017,41(6):159-167.
[5]	李雨哲. 电动汽车负荷的多因素预测模型及其对电网的影响分析[D]. 重庆:重庆大学, 2016.
	LI Yuzhe. Multi factor forecasting model of electric vehicle load and its influence on power grid[D]. Chongqing: Chongqing University, 2016.
[6]	ARIAS M B, BAE S. Electric vehicle charging demand forecasting model based on big data technologies[J]. Applied Energy, 2016,183:327-339.
[7]	ZHANG J, YAN J, LIU Y Q, et al. Daily electric vehicle charging load profiles considering demographics of vehicle users[J]. Applied Energy, 2020,274:1-13.
[8]	MOON H, PARK S Y, JEONG C, et al. Forecasting electricity demand of electric vehicles by analyzing consumers’ charging patterns[J]. Transportation Research Part D: Transport and Environment, 2018,62:64-79.
[9]	梅杰, 高赐威. 交通特性在电动汽车并网研究中的考虑[J]. 电网技术, 2015,39(12):3549-3555.
	MEI Jie, GAO Ciwei. Considerations of traffic characteristics in research of grid integration of electric vehicles[J]. Power System Technology, 2015,39(12):3549-3555.
[10]	ISLAM M S, MITHULANANTHAN N, HUNG D Q. A day-ahead forecasting model for probabilistic EV charging loads at business premises[J]. IEEE Transactions on Sustainable Energy, 2018,9(2):741-753.
[11]	龙勇, 苏振宇, 汪於. 基于季节调整和BP神经网络的月度负荷预测[J]. 系统工程理论与实践, 2018,38(4):1052-1060.
	LONG Yong, SU Zhenyu, WANG Yu. Monthly load forecasting model based on seasonal adjustment and BP neural network[J]. Systems Engineering-Theory & Practice, 2018,38(4):1052-1060.
[12]	刘晓悦, 孙玉容. 基于Hadoop的电动汽车充电站负荷预测[J]. 现代电子技术, 2018,41(13):74-77, 82.
	LIU Xiaoyue, SUN Yurong. Hadoop-based load forecasting of electric vehicle charging station[J]. Modern Electronics Technique, 2018,41(13):74-77, 82.
[13]	刘文霞, 徐晓波, 周樨. 基于支持向量机的纯电动公交车充/换电站日负荷预测[J]. 电力自动化设备, 2014,34(11):41-47.
	LIU Wenxia, XU Xiaobo, ZHOU Xi. Daily load forecasting based on SVM for electric bus charging station[J]. Electric Power Automation Equipment, 2014,34(11):41-47.
[14]	蒋燕, 吴洋, 栾毅, 等. 基于模糊C均值聚类算法和最小二乘支持向量机的母线负荷预测研究[J]. 电气自动化, 2019,41(3):45-47, 51.
	JIANG Yan, WU Yang, LUAN Yi, et al. Research on bus load forecasting based on fussy C-means clustering algorithm and least squares support vector machine[J]. Electrical Automation, 2019,41(3):45-47, 51.
[15]	蒯圣宇, 田佳, 台德群, 等. 计及分布式能源与电动汽车接入的空间负荷预测[J]. 电力需求侧管理, 2019,21(1):47-51.
	KUAI Shengyu, TIAN Jia, TAI Dequn, et al. Space load forecasting considering distributed energy and electric vehicles[J]. Power Demand Side Management, 2019,21(1):47-51.
[16]	杨俊闯, 赵超. K-Means聚类算法研究综述[J]. 计算机工程与应用, 2019,55(23):7-14, 63.
	YANG Junchuang, ZHAO Chao. Survey on K-means clustering algorithm[J]. Computer Engineering and Applications, 2019,55(23):7-14, 63.
[17]	石亮缘, 周任军, 张武军, 等. 采用深度学习和多维模糊C均值聚类的负荷分类方法[J]. 电力系统及其自动化学报, 2019,31(7):43-50.
	SHI Liangyuan, ZHOU Renjun, ZHANG Wujun, et al. Load classification method using deep learning and multi-dimensional fuzzy C-means clustering[J]. Proceedings of the CSU-EPSA, 2019,31(7):43-50.
[18]	徐辰, 李伟绩. 新能源汽车分类[J]. 国外电子测量技术, 2017,36(5):1-3.
[19]	闫志强. 我国车辆分类方法和标准研究与分析[D]. 大连:大连理工大学, 2014.
	YAN Zhiqiang. Research and analysis of vehicle classification methods and standards in China[D]. Dalian: Dalian University of Technology, 2014.
[20]	邢强, 陈中, 黄学良, 等. 基于数据驱动方式的电动汽车充电需求预测模型[J]. 中国电机工程学报, 2020,40(12):3796-3813.
	XING Qiang, CHEN Zhong, HUANG Xueliang, et al. Electric vehicle charging demand forecasting model based on data-driven approach[J]. Proceedings of the CSEE, 2020,40(12):3796-3813.
[21]	KOROLKO N, SAHINOGLU Z, NIKOVSKI D. Modeling and forecasting self-similar power load due to EV fast chargers[J]. IEEE Transactions on Smart Grid, 2016,7(3):1620-1629.
[22]	李滨, 黄佳, 吴茵, 等. 基于分形特性修正气象相似日的节假日短期负荷预测方法[J]. 电网技术, 2017,41(6):1949-1955.
	LI Bin, HUANG Jia, WU Yin, et al. Holiday short-term load forecasting based on fractal characteristic modified meteorological similar day[J]. Power System Technology, 2017,41(6):1949-1955.
[23]	康晓凡. 基于优化支持向量回归机的充电站负荷预测研究[D]. 西安:西安科技大学, 2019.
	KANG Xiaofan. Research on load forecasting of charging station based on optimized support vector regression[D]. Xi’an: Xi’an University of Science and Technology, 2019.
[24]	罗浩成, 胡泽春, 张洪财. 环境温度对电动汽车充电负荷的影响分析[J]. 电力建设, 2015,36(7):69-74.
	LUO Haocheng, HU Zechun, ZHANG Hongcai. Effect analysis of ambient temperature on electric vehicle charging load[J]. Electric Power Construction, 2015,36(7):69-74.

计及相似日与气象因素的电动汽车充电负荷聚类预测

Clustering Prediction of Electric Vehicle Charging Load Considering Similar Days and Meteorological Factors

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 24

相关文章 15

编辑推荐

Metrics

本文评价

[1]	魏震波, 田轲, 罗筱均, 方涛. 电动汽车聚合商参与下的主辅联合市场均衡分析[J]. 电力建设, 2021, 42(2): 50-57.
[2]	吴宛潞, 韩帅, 孙乐平, 郭小璇. 负荷聚合商多类型需求侧资源激励价格制定一般模型及应用[J]. 电力建设, 2021, 42(1): 1-9.
[3]	罗筱均, 魏震波, 田轲, 方涛. 基于源荷匹配度的多综合能源社区日前共享模型[J]. 电力建设, 2021, 42(1): 20-27.
[4]	张卫国, 陈良亮, 成海生, 付蓉, 季娟. 基于电动汽车供电资源态势感知的台区负荷弹性调度策略[J]. 电力建设, 2020, 41(8): 48-56.
[5]	吴钉捷, 李晓露. 基于实时出行需求和交通路况的电动汽车充电负荷预测[J]. 电力建设, 2020, 41(8): 57-67.
[6]	谭忠富，谭彩霞，蒲雷，杨佳澄. 基于协同免疫量子粒子群优化算法的虚拟电厂双层博弈模型[J]. 电力建设, 2020, 41(6): 9-17.
[7]	胡珏，韦钢，袁洪涛，罗志刚. 电动汽车充换储一体站的建模[J]. 电力建设, 2020, 41(6): 44-51.
[8]	刘辉，谢良峰，谢海敏，阳育德，覃智君. 考虑电动汽车响应AGC的系统网损评估[J]. 电力建设, 2020, 41(6): 52-59.
[9]	周斌，张卫国，崔文佳，毛东宇，陈中. 考虑预警负荷的电动汽车充放电优化策略[J]. 电力建设, 2020, 41(4): 10-21.
[10]	赵文会，张九阳，高姣倩，宋亚君. 考虑动态电量和无限次博弈的电动汽车上网电价模型#br#[J]. 电力建设, 2020, 41(4): 30-37.
[11]	蒋浩，林舜江，卢艺，何森. 考虑时间相关性的电动汽车充电站负荷概率建模及场景生成[J]. 电力建设, 2020, 41(2): 47-57.
[12]	王晞, 徐浩, 王海燕, 陈博, 王长浩, 刘洋. 考虑风电和电动汽车不确定性的综合能源系统日前经济调度[J]. 电力建设, 2020, 41(12): 82-91.
[13]	付晓琳, 王鸿, 王致杰. 基于区块链含电动汽车的微电网组合出力优化策略[J]. 电力建设, 2020, 41(11): 16-26.
[14]	原增泉, 许海平, 陈曦, 袁志宝. 共交流母线电动汽车充放电系统小信号建模及稳定性分析[J]. 电力建设, 2020, 41(11): 27-37.
[15]	卢少平, 应黎明, 王霞, 李文杰. 基于用户出行模拟的电动汽车快充站负荷预测及其优化调度[J]. 电力建设, 2020, 41(11): 38-48.