闫威,李南,沈月秀,施力欣,胡滨,周舟
YAN Wei,LI Nan,SHEN Yuexiu,SHI Lixin,HU Bin,ZHOU Zhou

• 1:国网浙江省电力有限公司嘉兴供电公司

摘要(Abstract)：

随着电动汽车用户在交通用户中所占比例不断增大，其充电行为对于电力系统运行产生重要的影响，因此对电动汽车充电负荷进行准确预测具有重要意义。对此，提出了一种基于CNN-GAN（卷积神经网络-生成对抗网络）与半监督回归的充电负荷预测方法。采用GMM（高斯混合模型）对用户样本进行聚类分析，并提取典型用户行为特征。考虑历史数据及降雨量、温度等天气信息的影响，搭建各组基于CNNGAN的电动汽车负荷预测模型，并通过半监督回归得到预测结果。以华东某区域内实际电动汽车数据为例，对比多种方法的预测结果及评价指标。结果显示，CNN-GAN预测模型预测精度优于其他方法，验证了所提方法的可行性。
With the increasing proportion of electric vehicle users in transportation users, their charging behavior dramatically influences the power system operation. Therefore, it is crucial to predict the charging load of electric vehicles accurately. In this regard, a charging load prediction method is proposed based on CNN-GAN(convolutional neural network-generative adversarial network) and semi-supervised regression. A GMM(Gaussian mixture model) is used for cluster analysis of the user samples and extraction of the typical user behavior features. Given the influence of historical data and weather information such as rainfall and temperature, the EV load prediction model groups based on CNN-GAN are built, and the prediction results are obtained by semi-supervised regression. The EV data from a region of East China are used to compare the prediction results and evaluation indexes of several methods. The results show that the prediction model based on CNN-GAN is superior to other methods in prediction accuracy, and the feasibility of the proposed method is verified.

关键词(KeyWords)： CNN-GAN;半监督回归;电动汽车;充电负荷预测
CNN-GAN;semi-supervised regression;electric vehicle;charging load prediction

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211JX2000K7）

作者(Author): 闫威,李南,沈月秀,施力欣,胡滨,周舟
YAN Wei,LI Nan,SHEN Yuexiu,SHI Lixin,HU Bin,ZHOU Zhou

DOI: 10.19585/j.zjdl.202302011

参考文献(References)：

• [1]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. Modeling the charging load of electric vehicle based on multi-factors and its impact on power grid[D].Chongqing:Chongqing University,2016.
• [2]MAJIDPOUR M,QIU C,CHU P,et al.Forecasting the EV charging load based on customer profile or station measurement[J].Applied Energy,2016,163:134-141.
• [3]毛为真，李永攀，陆轶祺，等.基于改进随机森林算法的电动汽车充电预测[J].上海节能，2019(11):920-925.MAO Weizhen,LI Yongpan,LU Yiqi,et al.Charging load forecasting of electric vehicle based on improved random forest algorithm[J].Shanghai Energy Conservation,2019(11):920-925.
• [4]张美霞，孙铨杰，杨秀.考虑多源信息实时交互和用户后悔心理的电动汽车充电负荷预测[J].电网技术，2022,46(2):632-645.ZHANG Meixia,SUN Quanjie,YANG Xiu. Electric vehicle charging load prediction considering multi-source information real-time interaction and user regret psychology[J].Power System Technology,2022,46(2):632-645.
• [5]张琳娟，许长清，王利利，等.基于OD矩阵的电动汽车充电负荷时空分布预测[J].电力系统保护与控制，2021,49(20):82-91.ZHANG Linjuan,XU Changqing,WANG Lili,et al.OD matrix based spatiotemporal distribution of EV charging load prediction[J].Power System Protection and Control,2021,49(20):82-91.
• [6]熊小萍，林光阳，郝邵磊，等.计及温度与交通影响的电动汽车充电负荷预测[J].电工技术，2021(14):73-76.XIONG Xiaoping,LIN Guangyang,HAO Shaolei,et al.Electric vehicle charging load forecasting considering temperature and traffic impact[J].Electric Engineering,2021(14):73-76.
• [7]刘杨，王维庆，王海云.考虑气象因素的改进ARIMA电动汽车充电负荷预测[J].电器与能效管理技术，2018(8):53-58.LIU Yang,WANG Weiqing,WANG Haiyun.Forecasting model of EV charging load based on improved ARIMA and meteorological factors[J]. Electrical&Energy Management Technology,2018(8):53-58.
• [8]华远鹏，王圆圆，韩丁，等.考虑有序充电的居民区电动汽车中长期充电负荷预测[J].电力系统及其自动化学报，2022,34(6):142-150.HUA Yuanpeng,WANG Yuanyuan,HAN Ding,et al.Mid-and long-term charging load forecasting for electric vehicles in residential areas considering orderly charging[J]. Proceedings of the CSU-EPSA,2022,34(6):142-150.
• [9]牛牧童，廖凯，杨健维，等.考虑季节特性的多时间尺度电动汽车负荷预测模型[J].电力系统保护与控制，2022,50(5):74-85.NIU Mutong,LIAO Kai,YANG Jianwei,et al. Multitime-scale electric vehicle load forecasting model considering seasonal characteristics[J]. Power System Protection and Control,2022,50(5):74-85.
• [10]胡博，张鹏飞，黄恩泽，等.基于图WaveNet的电动汽车充电负荷预测[J].电力系统自动化，2022,46(16):207-213.HU Bo,ZHANG Pengfei,HUANG Enze,et al. Graph WaveNet based charging load forecasting of electric vehicle[J].Automation of Electric Power Systems,2022,46(16):207-213.
• [11]刘敦楠，张悦，彭晓峰，等.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,et al.Clustering prediction of electric vehicle charging load considering similar days and meteorological factors[J]. Electric Power Construction,2021,42(2):43-49.
• [12]王哲，万宝，凌天晗，等.基于谱聚类和LSTM神经网络的电动公交车充电负荷预测方法[J].电力建设，2021,42(6):58-66.WANG Zhe,WAN Bao,LING Tianhan,et al. Electric bus charging load forecasting method based on spectral clustering and LSTM neural network[J]. Electric Power Construction,2021,42(6):58-66.
• [13]QU G,MENG X F,YIN Y K,et al. A demosaicing method for compressive color single-pixel imaging based on a generative adversarial network[J].Optics and Lasers in Engineering,2022,155:107053.
• [14]XU H F,CAO D L,LI S Z.A self-regulated generative adversarial network for stock price movement prediction based on the historical price and tweets[J]. KnowledgeBased Systems,2022,247:108712.
• [15]HAN K L,YANG K,YIN L F.Lightweight actor-critic generative adversarial networks for real-time smart generation control of microgrids[J].Applied Energy,2022,317:119163.
• [16]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Proceedings of the27th International Conference on Neural Information Processing Systems,8-13 Dec.2014,Montreal,Canada. MIT Press,2014:2672-2680.
• [17]张美霞，李丽，杨秀，等.基于高斯混合模型聚类和多维尺度分析的负荷分类方法[J].电网技术，2020,44(11):4283-4296.ZHANG Meixia,LI Li,YANG Xiu,et al.A load classification method based on Gaussian mixture model clustering and multi-dimensional scaling analysis[J]. Power System Technology,2020,44(11):4283-4296.
• [18]NAIR V,HINTON G E.Rectified linear units improve restricted boltzmann machines[C]//Proceedings of the 27th International Conference on International Conference on Machine Learning,21-24 Jun.2010,Haifa,Israel.DBLP,2010:807-814.