虞殷树,陈东海,朱耿,贺旭,白文博
YU Yinshu,CHEN Donghai,ZHU Geng,HE Xu,BAI Wenbo

• 1:国网浙江省电力有限公司宁波供电公司
• 2:宁波市电力设计院有限公司

摘要(Abstract)：

行业短期电力负荷的准确预测对于地区电网的安全经济运行具有重要意义。为此，提出一种基于关联分析和卷积神经网络的行业短期电力负荷预测模型。首先，对k-means聚类算法进行优化，并对行业负荷和外部影响因素的原始数据进行聚类处理，以改善后续关联分析的准确性；然后，提出一种基于标准互信息的改进关联分析方法，对各种外部影响因素和行业负荷的关联性进行定量分析；最后，基于卷积神经网络设计一种计及外部影响因素关联性的负荷预测网络，网络在经过训练后可用于行业短期电力负荷的预测。对照实验结果表明，所提模型在各行业的短期电力负荷预测中都具有更好的准确性和稳定性。
Accurate forecasting of short-term power load for industrial sectors plays a pivotal role in ensuring the safe and economic operation of regional power grids. To address this critical need, a short-term power load forecasting model in industries based on correlation analysis and convolutional neural network(CNN) is proposed. First, the k-means clustering algorithm is optimized, and the raw data of industry load and external influencing factors are clustered to improve the accuracy of the subsequent correlation analysis. Then, an improved correlation analysis method based on normalized mutual information(NMI) is proposed to quantitatively assess the correlation between various external influencing factors and industrial loads. Last, a load forecasting network considering the correlation of external influencing factors based on the CNN is designed, which can be used for the short-term power load forecasting of industrial sectors after training. The results of a controlled experiment demonstrate the superiority of the proposed model in terms of both accuracy and stability when it comes to short-term power load forecasting for industrial sectors.

关键词(KeyWords)： 负荷预测;关联分析;标准互信息;k-means聚类;卷积神经网络
load forecasting;correlation analysis;NMI;k-means clustering;CNN

Abstract:

Keywords:

基金项目(Foundation): 宁波永耀电力投资集团有限公司科技项目（CY820400QT20210652）

作者(Author): 虞殷树,陈东海,朱耿,贺旭,白文博
YU Yinshu,CHEN Donghai,ZHU Geng,HE Xu,BAI Wenbo

DOI: 10.19585/j.zjdl.202311004

参考文献(References)：

• [1] SUN M Y,WANG Y,STRBAC G,et al. Probabilistic peak load estimation in smart cities using smart meter data[J].IEEE Transactions on Industrial Electronics,2018,66(2):1608-1618.
• [2] GE L,XIAN Y,WANG Z,et al.Short-term load forecasting of regional distribution network based on generalized regression neural network optimized by grey wolf optimization algorithm[J]. CSEE Journal of Power and Energy Systems,2021,7(5):1093-1101.
• [3]马梦冬，彭道刚，王丹豪.基于EEMD-LSTM的区域能源短期负荷预测[J].浙江电力，2020,39(4):29-35.MA Mengdong,PENG Daogang,WANG Danhao.Shortterm load forecasting based on EEMD-LSTM for regional energy[J].Zhejiang Electric Power,2020,39(4):29-35.
• [4] ZHANG C R,CHEN Z H,ZHOU J.Research on shortterm load forecasting using K-means clustering and CatBoost integrating time series features[C]//2020 39th Chinese Control Conference(CCC). July 27-29,2020,Shenyang,China.IEEE,2020:6099-6104.
• [5]应张驰，陈淑萍，卢旭航.基于多源信息的短期负荷混合预测模型应用研究[J].浙江电力，2019,38(9):100-104.YING Zhangchi,CHEN Shuping,LU Xuhang. Study on application of short-term hybrid load forecasting model based on multi-source information[J]. Zhejiang Electric Power,2019,38(9):100-104.
• [6]刘伟，张锐锋，彭道刚.基于K-Adaboost数据挖掘的配电网负荷预测[J].浙江电力，2019,38(1):104-110.LIU Wei,ZHANG Ruifeng,PENG Daogang.Load forecasting of distribution network based on K-adaboost data mining[J].Zhejiang Electric Power,2019,38(1):104-110.
• [7]邓带雨，李坚，张真源，等.基于EEMD-GRU-MLR的短期电力负荷预测[J].电网技术，2020,44(2):593-602.DENG Daiyu,LI Jian,ZHANG Zhenyuan,et al. Shortterm electric load forecasting based on EEMD-GRU-MLR[J].Power System Technology,2020,44(2):593-602.
• [8]陈振宇，刘金波，李晨，等.基于LSTM与XGBoost组合模型的超短期电力负荷预测[J].电网技术，2020,44(2):614-620.CHEN Zhenyu,LIU Jinbo,LI Chen,et al. Ultra shortterm power load forecasting based on combined LSTMXGBoost model[J].Power System Technology,2020,44(2):614-620.
• [9]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.
• [10]赵兵，王增平，纪维佳，等.基于注意力机制的CNN-GRU短期电力负荷预测方法[J].电网技术，2019,43(12):4370-4376.ZHAO Bing,WANG Zengping,JI Weijia,et al.A shortterm power load forecasting method based on attention mechanism of CNN-GRU[J].Power System Technology,2019,43(12):4370-4376.
• [11]黄冬梅，庄兴科，胡安铎，等.基于灰色关联分析和K均值聚类的短期负荷预测[J].电力建设，2021,42(7):110-117.HUANG Dongmei,ZHUANG Xingke,HU Anduo,et al.Short-term load forecasting based on similar-day selection with GRA-K-means[J]. Electric Power Construction,2021,42(7):110-117.
• [12]沈兆轩，袁三男.利用卷积神经网络支持向量回归机的地区负荷聚类集成预测[J].电网技术，2020,44(6):2237-2244.SHEN Zhaoxuan,YUAN Sannan. Regional load clustering integration forecasting based on convolutional neural network support vector regression machine[J].Power System Technology,2020,44(6):2237-2244.
• [13]李玉志，刘晓亮，邢方方，等.基于Bi-LSTM和特征关联性分析的日尖峰负荷预测[J].电网技术，2021,45(7):2719-2730.LI Yuzhi,LIU Xiaoliang,XING Fangfang,et al. Daily peak load forecasting based on Bi-LSTM and characteristic correlation analysis[J]. Power System Technology,2021,45(7):2719-2730.
• [14]杨秀，陈斌超，朱兰，等.基于相关性分析和长短期记忆网络分位数回归的短期公共楼宇负荷概率密度预测[J].电网技术，2019,43(9):3061-3071.YANG Xiu,CHEN Binchao,ZHU Lan,et al.Short-term public building load probability density prediction based on correlation analysis and long-and short-term memory network quantile regression[J].Power System Technology,2019,43(9):3061-3071.
• [15]陈纬楠，胡志坚，岳菁鹏，等.基于长短期记忆网络和LightGBM组合模型的短期负荷预测[J].电力系统自动化，2021,45(4):91-97.CHEN Weinan,HU Zhijian,YUE Jingpeng,et al.Shortterm load prediction based on combined model of long short-term memory network and light gradient boosting machine[J].Automation of Electric Power Systems,2021,45(4):91-97.
• [16]庄家懿，杨国华，郑豪丰，等.并行多模型融合的混合神经网络超短期负荷预测[J].电力建设，2020,41(10):1-8.ZHUANG Jiayi,YANG Guohua,ZHENG Haofeng,et al.Ultra-short-term load forecasting using hybrid neural network based on parallel multi-model combination[J].Electric Power Construction,2020,41(10):1-8.
• [17]陈吕鹏，殷林飞，余涛，等.基于深度森林算法的电力系统短期负荷预测[J].电力建设，2018,39(11):42-50.CHEN Lüpeng,YIN Linfei,YU Tao,et al. Short-term power load forecasting based on deep forest algorithm[J].Electric Power Construction,2018,39(11):42-50.
• [18]郑瑞骁，张姝，肖先勇，等.考虑温度模糊化的多层长短时记忆神经网络短期负荷预测[J].电力自动化设备，2020,40(10):181-186.ZHENG Ruixiao,ZHANG Shu,XIAO Xianyong,et al.Short-term load forecasting of multi-layer long short-term memory neural network considering temperature fuzziness[J]. Electric Power Automation Equipment,2020,40(10):181-186.
• [19] MACQUEEN J. Some methods for classification and analysis of multivariate observations[C]//Proceedings of Fifth Berkeley Symposium on Mathematical Statistics and Probability.Los Angeles,CA,1967:281-297.
• [20]崔树银，汪昕杰.基于最大信息系数和多目标Stacking集成学习的综合能源系统多元负荷预测[J].电力自动化设备，2022,42(5):32-39.CUI Shuyin,WANG Xinjie.Multivariate load forecasting in integrated energy system based on maximal information coefficient and multi-objective Stacking ensemble learning[J].Electric Power Automation Equipment,2022,42(5):32-39.
• [21]王继东，杜冲.基于Attention-BiLSTM神经网络和气象数据修正的短期负荷预测模型[J].电力自动化设备，2022,42(4):172-177.WANG Jidong,DU Chong. Short-term load prediction model based on Attention-BiLSTM neural network and meteorological data correction[J].Electric Power Automation Equipment,2022,42(4):172-177.
• [22]林珊，王红，齐林海，等.基于条件生成对抗网络的短期负荷预测[J].电力系统自动化，2021,45(11):52-60.LIN Shan,WANG Hong,QI Linhai,et al.Short-term load forecasting based on conditional generative adversarial network[J].Automation of Electric Power Systems,2021,45(11):52-60.
• [23]李滨，高枫.基于虚拟相似日与DA-LSTPNet的地区电网短期负荷预测[J].电力系统自动化，2021,45(22):55-64.LI Bin,GAO Feng. Short-term load forecasting for regional power grid based on virtual similar days and dualstage attention-based long and short time pattern network[J]. Automation of Electric Power Systems,2021,45(22):55-64.