沈兆轩;袁三男;

• 1:上海电力大学电子与信息工程学院

摘要(Abstract)：

为提高地区负荷预测的运算效率和预测精度,提出了一种基于卷积神经网络支持向量回归机的地区负荷聚类集成预测方法。首先,通过聚类模型对地区内大量用户的真实负荷数据进行分组并分析了不同聚类模型的效果。其次,使用得到的聚类分组标签将用户数据分组集成并构建训练数据。然后,基于改进的卷积神经网络构建了卷积神经网络支持向量回归机模型。最后,分组进行负荷预测并将预测结果求和得到地区最终预测月负荷,并与卷积神经网络模型、长短期记忆神经网络模型、决策树模型、支持向量回归机模型进行对比。文中使用扬中市高新区的负荷数据作为算例进行分析,结果表明文中所提方法相较于现有算法具有更高的负荷预测精度和运算效率。

关键词(KeyWords)： 负荷预测;卷积神经网络;支持向量回归机;聚类

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 沈兆轩;袁三男;

Email:

DOI: 10.13335/j.1000-3673.pst.2019.0759

参考文献(References)：

• [1]《2018-2019年度全国电力供需形势分析预测报告》速览[J]．中国电力企业管理，2019(3):7.A quick overview of the national electric power supply and demand situation analysis and forecast report for 2018-2019[J].China Power Enterprise Management,2019(3):7(in Chinese)．
• [2]Haben S,Singleton C,Grindrod P.Analysis and clustering of residential customers energy behavioral demand using smart meter data[J].IEEE Transactions on Smart Grid,2017,7(1):136-144．
• [3]Stephen B,Mutanen J A,Galloway J S,et al.Enhanced load profiling for residential network customers[J].IEEE Transactions on Power Delivery,2014,29(1):88-96．
• [4]熊音笛，刘开培，秦亮，等．基于时序数据动态天气划分的短期风电功率预测方法[J/OL]．电网技术：1-8[2019-06-10].https://doi.org/10.13335/j.1000-3673.pst.2018.1568.Xiong Yindi,Liu Kaipei,Qin Liang,et al.Short-term wind power prediction method based on time series data dynamic weather division[J/OL].Power System Technology:1-8[2019-06-10].https://doi.org/10.13335/j.1000-3673.pst.2018.1568(in Chinese)．
• [5]Mohamed C.Clustering-based improvement of nonparame-tric functional time series forecasting:application to intra-day household-level load curves[J].IEEE Transactions on Smart Grid,2014,5(1):411-419．
• [6]Al-Otaibi R,Jin N,Wilcox T,et al.Feature construction and calibration for clustering daily load curves from smart-meter data[J].IEEE Transactions on Industrial Informatics,2017,12(2):645-654．
• [7]杨德昌，赵肖余，何绍文，等．面向海量用户用电数据的集成负荷预测[J]．电网技术，2018,42(9):2923-2929.Yang Dechang,Zhao Xiaoyu,He Shaowen,et al.Aggregated load forecasting based on massive household smart meter data[J].Power System Technology,2018,42(9):2923-2929(in Chinese)．
• [8]Mcloughlin F,Duffy A,Conlon M.A clustering approach to domestic electricity load profile characterisation using smart,metering data[J].Applied Energy,2015(141):190-199．
• [9]蒋敏，顾东健，孔军，等．基于在线序列极限支持向量回归的短期负荷预测模型[J]．电网技术，2018,42(7):2240-2247.Jiang Min,Gu Dongjian,Kong Jun,et al.Short-term load forecasting model based on online sequence limit support vector regression[J].Power System Technology,2018,42(7):2240-2247(in Chinese)．
• [10]谢敏，邓佳梁，吉祥，等．基于信息熵和变精度粗糙集优化的支持向量机降温负荷预测方法[J]．电网技术，2017,41(1):210-214.Xie Min,Deng Jialiang,Ji Xiang,et al.Cooling load forecasting method based on support vector machine optimized with entropy and variable accuracy roughness set[J].Power System Technology,2017,41(1):210-214(in Chinese)．
• [11]崔杨，李莉，陈德荣．基于最小二乘支持向量机的超短期风电负荷预测[J]．电气自动化，2014,36(5):35-37.Cui Yang,Li Li,Chen Derong.Ultra-short-term wind power load forecasting based on least squares support vector machine[J].Electrical Automation,2014,36(5):35-37(in Chinese)．
• [12]何耀耀，刘瑞，撖奥洋．基于实时电价与支持向量分位数回归的短期电力负荷概率密度预测方法[J]．中国电机工程学报，2017,37(3):768-776.He Yaoyao,Liu Rui,Han Aoyang.Short-term power load probability density forecasting method based on real time price and support vector quantile regression[J].Proceedings of the CSEE,2017,37(3):768-776(in Chinese)．
• [13]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(in Chinese)．
• [14]Yu-Hang Z,Cai-Ming Q,Xing H,et al.A short-term load forecasting based on LSTM neural network[J].Electric Power Information and Communication Technology,2017,15(9):19-25．
• [15]Shi H,Xu M,Li R.Deep learning for household load forecasting-a novel pooling deep RNN[J].IEEE Transactions on Smart Grid,2018,9(5):5271-5280．
• [16]Dong M,Grumbach L S.A hybrid long-term load forecasting model for distribution feeder peak demand using LSTM neural network[EB/OL].Ithaca,New York:ar Xiv,(2018-12-9)[2019-04-08].https://arxiv.org/abs/1812.04480v1．
• [17]朱乔木，李弘毅，王子琪，等．基于长短期记忆网络的风电场发电功率超短期预测[J]．电网技术，2017,41(12):3797-3802.Zhu Qiaomu,Li Hongyi,Wang Ziqi,et al.Ultra-short-term prediction of wind farm power generation based on long-term and short-term memory networks[J].Power System Technology,2017,41(12):3797-3802(in Chinese)．
• [18]杨甲甲，刘国龙，赵俊华，等．采用长短期记忆深度学习模型的工业负荷短期预测方法[J]．电力建设，2018,39(10):29-36.Yang Jiajia,Liu Guolong,Zhao Junhua,et al.A long short term memory based deep learning method for industrial load forecasting[J].Power Construction,2018,39(10):29-36(in Chinese)．
• [19]Tang Y.Deep learning using linear support vector machines[EB/OL].Ithaca,New York:ar Xiv,(2015-2-21)[2019-04-08].https：//arxiv.org/abs/1306.0239v1．
• [20]时永刚，程坤，刘志文．结合深度学习和支持向量机的海马子区图像分割[J]．中国图象图形学报，2018,23(4):542-551.Shi Yonggang,Cheng Kun,Liu Zhiwen.Hippocampus sub-area image segmentation combined with deep learning and support vector machine[J].Journal of Image and Graphics,2018,23(4):542-551(in Chinese)．
• [21]时培明，梁凯，赵娜，等．基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J]．中国机械工程，2017,28(9):1056-1061.Shi Peiming,Liang Kai,Zhao Na,et al.Gear intelligent fault diagnosis based on deep learning feature extraction and particle swarm support vector machine state recognition[J].China Mechanical Engineering,2017,28(9):1056-1061(in Chinese)．
• [22]邹京希，曹敏，董立军，等．基于总体测辨和人工神经网络的负荷建模及预测方法[J]．电力系统及其自动化学报，2018,30(8):108-112.Zou Jingxi,Cao Min,Dong Lijun,et al.Load modeling and forecasting method considering measurement-based method and artificial neural network[J].Proceedings of the CSU-EPSA,2018,30(8):108-112(in Chinese)．
• [23]Babnik T,Aggarwal R K,Moore P J.Principal component and hierarchical cluster analyses as applied to transformer partial discharge data with particular reference to transformer condition monitoring[J].IEEE Transactions on Power Delivery,2008,23(4):2008-2016．
• [24]常亮，邓小明，周明全，等．图像理解中的卷积神经网络[J]．自动化学报，2016,42(9):1300-1312.Chang Liang,Deng Xiaoming,Zhou Mingquan,et al.Convolutional neural networks in image understanding[J].Acta Automatica Sinica,2016,42(9):1300-1312(in Chinese)．
• [25]周飞燕，金林鹏，董军．卷积神经网络研究综述[J]．计算机学报，2017,40(6):1229-1251.Zhou Feiyan,Jin Linpeng,Dong Jun.Review of convolutional neural networks[J].Journal of Computers,2017,40(6):1229-1251(in Chinese)．
• [26]张文达，许悦雷，倪嘉成，等．基于多尺度分块卷积神经网络的图像目标识别算法[J]．计算机应用，2016,36(4):1033-1038.Zhang Wenda,Xu Yuelei,Ni Jiacheng,et al.Image target recognition algorithm based on multi-scale block convolutional neural network[J].Computer Applications,2016,36(4):1033-1038(in Chinese)．
• [27]Vapnik V.The nature of statistical learning theory[M].Springer,1995．
• [28]黄磊，舒杰，姜桂秀，等．基于多维时间序列局部支持向量回归的微网光伏发电预测[J]．电力系统自动化，2014,38(5):19-24.Huang Lei,Shu Jie,Jiang Guixiu,et al.Microgrid photovoltaic generation prediction based on multi-dimensional time series local support vector regression[J].Automation of Electric Power Systems,2014,38(5):19-24(in Chinese)．
• [29]潘超，谭启德，蔡国伟，等．基于递归量化分析的COA-SVR短期风速混合预测模型[J]．电网技术，2018,42(8):2373-2381.Pan Chao,Tan Qide,Cai Guowei,et al.COA-SVR short-term wind speed hybrid prediction model based on recursive quantitative analysis[J].Power System Technology,2018,42(8):2373-2381(in Chinese)．
• [30]Kingma D,Ba J A.A method for stochastic optimization[EB/OL].Ithaca,New York:ar Xiv,(2017-01-30)[2019-04-08].https://arxiv.org/abs/1412.6980.