赵子鋆,彭清文,邓铭,李琳,邓亚芝,陈柏沅,吴东琳
ZHAO Zijun,PENG Qingwen,DENG Ming,LI Lin,DENG Yazhi,CHEN Boyuan,WU Donglin

• 1:国网湖南省电力有限公司长沙供电分公司

摘要(Abstract)：

电动汽车的快速发展导致充电负荷水平逐年升高，且具有强随机性、难预测的特点，因此关于充电站负荷预测的研究具有重要意义。首先，针对仅考虑负荷波动趋势的单因素模型预测精度不足问题，分析多重因素对充电站负荷预测精度的影响，建立考虑多重影响因素并基于CNN-LSTM（卷积神经网络-长短期记忆）混合网络结构的负荷预测模型；然后，考虑充电负荷的强随机性对模型的影响，提出基于RF（随机森林）算法的误差修正方法；最后，以真实充电站负荷数据为算例进行仿真验证。研究结果表明，经RF算法修正的CNN-LSTM模型的负荷预测结果能较为精准地覆盖真实值，相较于LSTM单模型和未经修正的CNN-LSTM模型，具有更高的预测精度和实用价值。
The rapid development of electric vehicles has led to a yearly increase in charging load levels, characterized by strong randomness and unpredictability. Therefore, research on load forecasting for charging stations holds significant importance. Firstly, to address the inaccuracy of single-factor forecasting models that only consider load fluctuation trends, this paper analyzes the impact of multiple factors on the accuracy of charging station load forecasting. A load forecasting model is established that takes into account multiple influencing factors and is based on CNN-LSTM(convolutional neural network, long short-term memory). Subsequently, given the impact of strong randomness of charging load on the model, an error correction method based on the random forest(RF) algorithm is proposed. Finally, the paper conducts simulation verification using real charging station load data as a case study.The research results indicate that the load prediction of the CNN-LSTM model, corrected by the RF algorithm, can accurately cover real values. Compared to the LSTM single model and the non-corrected CNN-LSTM model, it exhibits higher forecasting accuracy and practical value.

关键词(KeyWords)： 电动汽车;充电负荷;充电站;负荷预测;CNN-LSTM
electric vehicle;charging load;charging station;load forecasting;CNN-LSTM

Abstract:

Keywords:

基金项目(Foundation): 国网湖南省电力有限公司科技项目（5216A522001Z）

作者(Author): 赵子鋆,彭清文,邓铭,李琳,邓亚芝,陈柏沅,吴东琳
ZHAO Zijun,PENG Qingwen,DENG Ming,LI Lin,DENG Yazhi,CHEN Boyuan,WU Donglin

DOI: 10.19585/j.zjdl.202404003

参考文献(References)：

• [1] DAI Q,CAI T,DUAN S X,et al. Stochastic modeling and forecastingof load demand for electric bus batteryswap station[J].IEEE Transactions on Power Delivery,2014,29(4):1909-1917.
• [2]彭曙蓉，黄士峻，李彬，等.基于深度学习分位数回归模型的充电桩负荷预测[J].电力系统保护与控制，2020,48(2):44-50.PENG Shurong,HUANG Shijun,LI Bin,et al.Charging pile load prediction based on deep learning quantile regression model[J]. Power System Protection and Control,2020,48(2):44-50.
• [3]刘勇，李全优，戴朝华.电动汽车充电负荷时空分布建模研究综述[J].电测与仪表，2022,59(8):1-9.Liu Yong,Li Quanyou,Dai Chaohua.Review on the spatiotemporal distribution modeling of electric vehicle chargingload[J]. Electrical Measurement&Instrumentation,2022,59(8):1-9.
• [4]冷喜武，刘闯，何蕾，等.可调节负荷并网运行标准研究与应用[J].发电技术，2022,43(6):834-842.LENG Xiwu,LIU Chuang,HE Lei,et al.Research and application of grid-connected operation standard for adjustable load[J].Power Generation Technology,2022,43(6):834-842.
• [5]王婷，陈晨，谢海鹏.配电网对分布式电源和电动汽车的承载力评估及提升方法综述[J].电力建设，2022,43(9):12-24.WANG Ting,CHEN Chen,XIE Haipeng. Review on evaluation and promotion methods of carrying capacity for distributed generation and electric vehicles in distribution network[J]. Electric Power Construction,2022,43(9):12-24.
• [6]肖丽，谢尧平，胡华锋，等.基于V2G的电动汽车充放电双层优化调度策略[J].高压电器，2022,58(5):164-171.XIAO Li,XIE Yaoping,HU Huafeng,et al.Two-level optimization scheduling strategy for EV’s charging and discharging based on V2G[J]. High Voltage Apparatus,2022,58(5):164-171.
• [7]蒋林洳，龙羿，李兴源，等.基于实测数据的多类型电动汽车充电负荷分析[J].电测与仪表，2023,60(1):36-41.Jiang Linru,Long Yi,Li Xingyuan,et al. Charging load analysis of multi-type electric vehicle based on measured data[J].Electrical Measurement&Instrumentation,2023,60(1):36-41.
• [8]于海东，张焰，潘爱强.电动私家车充电负荷中长期推演模型[J].电力系统自动化，2019,43(21):80-87.YU Haidong,ZHANG Yan,PAN Aiqiang. Medium-and long-term evolution model of charging load for private electric vehicle[J]. Automation of Electric Power Systems,2019,43(21):80-87.
• [9] YANG W,XIANG Y,LIU J Y,et al.Agent-based modeling for scale evolution of plug-in electric vehicles and charging demand[J]. IEEE Transactions on Power Systems,2018,33(2):1915-1925.
• [10]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.
• [11]艾学勇，顾洁，解大，等.电动汽车日充电曲线预测方法[J].电力系统及其自动化学报，2013,25(6):25-30.AI Xueyong,GU Jie,XIE Da,et al. Forecasting method for electric vehicle daily charging curve[J].Proceedings of the CSU-EPSA,2013,25(6):25-30.
• [12]赵依.基于多因素挖掘的短期电力负荷预测[D].西安：长安大学，2022.ZHAO Yi. Short-term power load forecasting based on multi-factor mining[D].Xi’an:Changan University,2022.
• [13] CUI H R,PENG X.Short-term city electric load forecasting with considering temperature effects:an improved ARIMAX model[J].Mathematical Problems in Engineering,2015(12):589374.
• [14]张乔榆，蔡秋娜，刘思捷，等.基于样本扩展和特征标记的节假日短期负荷预测[J].广东电力，2019,32(7):67-74.ZHANG Qiaoyu,CAI Qiuna,LIU Sijie,et al. Holiday short-term load forecasting based on sample expansion and feature extraction[J].Guangdong Electric Power,2019,32(7):67-74.
• [15]李鹏，何帅，韩鹏飞，等.基于长短期记忆的实时电价条件下智能电网短期负荷预测[J].电网技术，2018,42(12):4045-4052.LI Peng,HE Shuai,HAN Pengfei,et al.Short-term load forecasting of smart grid based on long-short-term memory recurrent neural networks in condition of real-time electricity price[J]. Power System Technology,2018,42(12):4045-4052.
• [16] AGGA A,ABBOU A,LABBADI M,et al.CNN-LSTM:an efficient hybrid deep learning architecture for predicting short-term photovoltaic power production[J]. Electric Power Systems Research,2022,208:107908.
• [17]欧阳福莲，王俊，周杭霞.基于改进迁移学习和多尺度CNN-BiLSTM-Attention的短期电力负荷预测方法[J].电力系统保护与控制，2023,51(2):132-140.OUYANG Fulian,WANG Jun,ZHOU Hangxia. Shortterm power load forecasting method based on improved hierarchical transfer learning and multi-scale CNN-BiLSTMAttention[J].Power System Protection and Control,2023,51(2):132-140.
• [18]陈峰，余轶，徐敬友，等.基于Bayes-LSTM网络的风电出力预测方法[J].电力系统保护与控制，2023,51(6):170-178.CHEN Feng,YU Yi,XU Jingyou,et al. Prediction method of wind power output based on a Bayes-LSTM network[J].Power System Protection and Control,2023,51(6):170-178.
• [19]陈卓，孙龙祥.基于深度学习LSTM网络的短期电力负荷预测方法[J].电子技术，2018,47(1):39-41.CHEN Zhuo,SUN Longxiang. Short-term electrical load forecasting based on deep learning LSTM networks[J].Electronic Technology,2018,47(1):39-41.
• [20]李静茹，姚方.引入注意力机制的CNN和LSTM复合风电预测模型[J].电气自动化，2022,44(6):4-6.LI Jingru,YAO Fang.Integrated CNN and LSTM wind power prediction modelwith the introduction of attention mechanism[J].Electrical Automation,2022,44(6):4-6.
• [21]李大中，李颖宇.基于深度学习与误差修正的超短期风电功率预测[J].太阳能学报，2021,42(12):200-205.LI Dazhong,LI Yingyu.Ultra-short term wind power prediction based on deep learning and error correction[J].Acta Energiae Solaris Sinica,2021,42(12):200-205.
• [22]韩富佳，王晓辉，乔骥，等.基于人工智能技术的新型电力系统负荷预测研究综述[J].中国电机工程学报，2023,43(22):8569-8592.HAN Fujia,WANG Xiaohui,QIAO Ji,et al.Review on artificial intelligence based load forecasting research for the new-type power system[J]. Proceedings of the CSEE,2023,43(22):8569-8592.
• [23] WANG P J,RAO L,LIU X,et al.D-pro:dynamic data center operations with demand-responsive electricity prices in smart grid[J].IEEE Transactions on Smart Grid,2012,3(4):1743-1754.
• [24] ARIAS M B,BAE S. Electric vehicle charging demand forecasting model based on big data technologies[J].Applied Energy,2016,183:327-339.
• [25]陈丽丹，张尧，FIGUEIREDO A.电动汽车充放电负荷预测研究综述[J].电力系统自动化，2019,43(10):177-191.CHEN Lidan,ZHANG Yao,FIGUEIREDO A.Overview of charging and discharging load forcasting for electric vehicles[J].Automation of Electric Power Systems,2019,43(10):177-191.
• [26]席乐，张琳娟，秦楠，等.峰平谷电价下动态修正充电目标的EV充电负荷预测[J].电力系统及其自动化学报，2020,32(8):62-69.XI Le,ZHANG Linjuan,QIN Nan,et al. EV charging load prediction with dynamically modified charging target under peak-flat-valley electricity price[J]. Proceedings of the CSU-EPSA,2020,32(8):62-69.
• [27] KUO P H,HUANG C J.A high precision artificial neural networks model for short-term energy load forecasting[J].Energies,2018,11(1):213-226.
• [28] HAO Z H,LIU G X,ZHANG H Y. Correlation filterbased visual tracking via adaptive weighted CNN features fusion[J].IET Image Processing,2018,12(8):1423-1431.
• [29] GRAVES A,MOHAMED A R,HINTON G.Speech recognition with deep recurrent neural networks[C]//2013IEEE International Conference on Acoustics,Speech and Signal Processing. May 26-31,2013. Vancouver,BC,Canada:IEEE,2013.
• [30] KONG W C,DONG Z Y,JIA Y W,et al.Short-term residential load forecasting based on LSTM recurrent neural network[J].IEEE Transactions on Smart Grid,2019,10(1):841-851.
• [31]陆继翔，张琪培，杨志宏，等.基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J].电力系统自动化，2019,43(8):131-137.LU Jixiang,ZHANG Qipei,YANG Zhihong,et al.Shortterm load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of Electric Power Systems,2019,43(8):131-137.
• [32] LAHOUAR A,BEN HADJ SLAMA J.Hour-ahead wind power forecast based on random forests[J].Renewable Energy,2017,109:529-541.
• [33]刘季昂，刘友波，邱高，等.基于高斯过程回归的电网运行方式快速置信评价[J].电力系统自动化，2022,46(11):181-190.LIU Ji’ang,LIU Youbo,QIU Gao,et al.Fast confidence evaluation of operation mode of power grid based on Gaussian process regression[J]. Automation of Electric Power Systems,2022,46(11):181-190.
• [34]陈亚红，穆钢，段方丽.短期电力负荷预报中几种异常数据的处理[J].东北电力学院学报，2002,22(2):1-5.CHEN Yahong,MU Gang,DUAN Fangli. Identification and management to anomalous data in short-term load forecasting[J]. Journal of Northeast China Institute of Electric Power Engineering,2002,22(2):1-5.