陈振宇;刘金波;李晨;季晓慧;李大鹏;黄运豪;狄方春;高兴宇;徐立中;

• 1:电力调度自动化技术研究与系统评价北京市重点实验室(中国电力科学研究院有限公司)
• 2:国家电网有限公司大数据中心
• 3:国家电网有限公司国家电力调度控制中心
• 4:中国地质大学(北京)信息工程学院

摘要(Abstract)：

为进一步提高电力负荷预测精度,提出了基于LSTM(longshorttermmemorynetwork, LSTM)和XGBoost(eXtremegradientboosting)的组合预测模型。针对电力负荷数据,首先建立了LSTM预测模型和XGBoost预测模型,然后使用误差倒数法将LSTM与XGBoost组合起来进行预测。采用2016年电工数学建模竞赛的电力负荷数据进行算例分析,结果表明所构建的LSTM和XGBoost组合预测模型的MAPE (mean absolute percentage error)为0.57%,明显低于单一预测模型。将上述方法与GRU (gated recurrent unit)和XGBoost两者组合的预测模型相比较,结果表明所提出的方法具有更高的超短期电力负荷预测精度。

关键词(KeyWords)： 电力负荷;超短期;负荷预测;LSTM网络;XGBoost;组合模型

Abstract:

Keywords:

基金项目(Foundation): 国家电网有限公司总部科技项目“大电网理想调度及知识发现关键技术研究与应用”(52110418002A)~~

作者(Author): 陈振宇;刘金波;李晨;季晓慧;李大鹏;黄运豪;狄方春;高兴宇;徐立中;

Email:

DOI: 10.13335/j.1000-3673.pst.2019.1566

参考文献(References)：

• [1]康重庆，夏清，刘梅．电力系统负荷预测[M]．北京：中国电力出版社2007.
• [2]刘敏，邓勇，何光宇，等．电力系统超短期负荷预测研究综述[C]//福建省电机工程学会第十五届学术年会．福州：福建省电机工程学会，2015:1-12.
• [3] Tao H,Shu F.Probabilistic electric load forecasting:a tutorial review[J].International Journal of Forecasting,2016,32(3):914-938.
• [4] Shi D.Application of outlier mining in power load forecasting[C]//International Conference on Computer Application&System Modeling(ICCASM 2010),Taiyuan,2010:V5-174-V5-176.
• [5] Li H.Short term load forecasting by adaptive neural network[J].IOP Conference Series:Materials Science and Engineering, DOI:10.1088/1757-899X/449/1/012028.
• [6] Wang N,Fu P,Chen D,et al.Application of big data method in optimal load dispatching of power plant[J].Proceedings of the CSEE,2015,35(1):263.
• [7]张振高，杨正瓴．短期负荷预测中的负荷求导法及天气因素的使用[J]．电力系统及其自动化学报，2006,18(5):79-83.Zhang Zhengao, Yang Zhengyi. Load derivation in short term forecasting using weather factor[J].Proceedings of the CSU-EPSA,2006,18(5):79-83(in Chinese).
• [8]张宇航，邱才明，贺兴等．一种基于LSTM神经网络的短期用电负荷预测方法[J]．电力信息与通信技术，2017,15(9):19-25.Zhang Yuhang,Qiu Caiming,He Xing,et al.A short-term load forecasting based on LSTM neural network[J]. Electric Power Information and Communication Technology,2017,15(9):19-25(in Chinese).
• [9] Baharudin Z,Kamel N.Autoregressive method in short term load forecast[C]//2008 IEEE 2nd International Power and Energy Conference.Johor Bahru:IEEE,2008:1603-1608.
• [10] Ji P,Xiong D,Wang P,et al.A study on exponential smoothing model for load forecasting[C]//2012 Asia-Pacific Power and Energy Engineering Conference.Shanghai:Energy Procedia,2012:2884-2887.
• [11] Zhu X,Shen M.Based on the ARIMA model with grey theory for short term load forecasting model[C]//2012International Conference on Systems and Informatics(ICSAI2012).Yantai:IEEE,2012:564-567.
• [12] Ma W M W.Power system short-term load forecasting based on improved support vector machines[C]//2008 International Symposium on Knowledge Acquisition and Modeling.Wuhan:IEEE,2008:658-662.
• [13] Huo J,Shi T,Jing C.Comparison of random forest and SVM for electrical short-term load forecast with different data sources[C]//2016 7th IEEE International Conference on Software Engineering and Service Science(ICSESS).Beijing:IEEE,2016:1077-1080.
• [14]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 sequential extreme support vector regression[J].Power System Technology,2018,42(7):2240-2247(in Chinese).
• [15] Lahouar A,Ben H S J.Day-ahead load forecast using random forest and expert input selection[J].Energy Conversion and Management,2015,103:1040-1051.
• [16] Papadopoulos S, Karakatsanis I. Short-term electricity load forecasting using time series and ensemble learning methods[C]//2015 IEEE Power and Energy Conference at Illinois(PECI),Champaign,IL:IEEE,2015:1-6.
• [17] Qiu X,Suganthan P N,Amaratunga G A J.Ensemble incremental learning random vector functional link network for short-term electric load forecasting[J].Knowledge-Based Systems,2018,145(4):182-196.
• [18] Hayashi Y,Iwamoto S.Long-term load forecasting using improved recurrent neural network[J].Electrical Engineering in Japan,2010,114(8):41-54.
• [19]肖白，刘庆永，牛强等．基于元胞负荷特性分析的RBF神经网络空间负荷预测方法[J]．电网技术，2018,42(1):301-307.Xiao Bai,Liu Qingyong,Niu Qiang,et al.A spatial load forecasting method based on RBF neural network and cellular load characteristics analysis[J].Power System Technology,2018,42(1):301-307(in Chinese).
• [20] Li L,Ota K,Dong M.Everything is image:CNN-based short-term electrical load forecasting for smart grid[C]//2017 14th International Symposium on Pervasive Systems,Algorithms and Networks&201711th International Conference on Frontier of Computer Science and Technology&2017 Third International Symposium of Creative Computing(ISPAN-FCST-ISCC).Exeter,2017:344-351.
• [21]毛李帆，姚建刚，金永顺，等．中长期电力组合预测模型的理论研究[J]．中国电机工程学报，2010,30(16):53-59.Mao Lifan,Yao Jiangang,Jin Yongshun,et al.Theoretical study of combination model for medium and long term load forecasting[J].Proceedings of the CSEE,2010,30(16):53-59(in Chinese).
• [22]刘龙龙．基于SARIMA与SVR的短期电力负荷预测[D]．南昌：东华理工大学，2018.
• [23]梁智，孙国强，李虎成，等．基于VMD与PSO优化深度信念网络的短期负荷预测[J]．电网技术，2018,42(2):598-606.Liang Zhi,Sun Guoqiang,Li Hucheng,et al.Short-term load forecasting based on VMD and PSO optimized deep belief network[J].Power System Technology,2018,42(2):598-606(in Chinese).
• [24]彭文，王金睿，尹山青．电力市场中基于Attention-LSTM的短期负荷预测模型[J]．电网技术，2019,43(5):1745-1751.Peng Wen,Wang Jinrui,Yin Shanqing.Short-term load forecasting model based on attention-LSTM in electricity market[J]. Power System Technology,2019,43(5):1745-1751(in Chinese).
• [25]张宇帆，艾芊，林琳，等．基于深度长短时记忆网络的区域级超短期负荷预测方法[J]．电网技术，2019,43(6):1884-1892.Zhang Yufan,Ai Wei,Lin Lin,et al.A very short-term load forecasting method based on deep LSTM RNN at zone level[J].Power System Technology,2019,43(6):1884-1892(in Chinese).
• [26]段晶晶．基于神经网络的短期电力负荷组合预测方法研究[D]．兰州：兰州大学，2017.
• [27]陈鸿琳，李欣然，冷华，等．运用PSO和GRNN的短期负荷二维组合预测[J]．电力系统及其自动化学报，2018,30(2):85-89.Chen Honglin,Li Xinran,Leng Hua,et al.Bidirectional combined short-term load forecasting by using PSO and GRNN[J].Proceedings of the CSU-EPSA,2018,30(2):85-89(in Chinese).
• [28]程津，黎燕，夏向阳，等．基于双组合预测的经济-电力负荷预测模型[J]．电力科学与技术学报，2018,33(3):20-24.Cheng Jin,Li Yan,Xia Xiangyang,et al.Economic-electricity conduction prediction model based on dual combination prediction[J].Journal of Electric Power Science and Technology,2018,33(3):20-24(in Chinese).
• [29]蒋晋文，刘伟光．XGBoost算法在制造业质量预测中的应用[J]．智能计算机与应用，2017(6):61-63.Jiang Jinwen,Liu Weiguang.Application of XGBoost algorithm in manufacturing quality prediction[J]. Intelligent Computer and Applications,2017(6):61-63(in Chinese).
• [30] Li L,Situ R,Gao J,et al.A hybrid model combining convolutional neural network with XGBoost for predicting social media popularity[C]//In Proceedings of the 25th ACM international conference on Multimedia(MM’17).New York,USA:ACM,2017:1912-1917.
• [31] Pan B. Application of XGBoost algorithm in hourly PM2.5concentration prediction[J]. IOP Conference Series:Earth and Environmental Science,2018,113:1-7.
• [32] Wang J,Lou C,Yu R,et al.Research on hot micro-blog forecast based on XGBOOST and random forest[M]. Knowledge Science,Engineering and Management, KSEM 2018, Lecture Notes in Computer Science,Springer.
• [33] Graves A. Long short-term memory[M]. Supervised Sequence Labeling with Recurrent Neural Networks.Textbook,Studies in Computational Intelligence,Springer,2012.
• [34] Li C,Chen Z.Y,Liu J.B,et al.Power load forecasting based on the combined model of LSTM and XGBoost[C]//PRAI’19:Proceedings of the 2019 the International Conference on Pattern Recognition and Artificial Intelligence.Wenzhou,China:ACM,2019:46-51.
• [35] Tang D,Li C,Ji X,et al.Power load forecasting using a refined LSTM[C]//In Proceeding of 2019 International Conference on Machine Learning and Computing(ICMLC 2019).Zhuhai,China:ACM,2019:104-108.
• [36]王增平，赵兵，纪维佳，等．基于GRU-NN模型的短期负荷预测方法[J]．电力系统自动化，2019,43(5):86-95.Wang Zengping,Zhao Bing,Ji Weijia,et al.Short-term load forecasting method based on GRU-NN model[J].Automation of Electric Power Systems,2019,43(5):86-95(in Chinese).
• [37]牛哲文，余泽远，李波，等．基于深度门控循环单元神经网络的短期风功率预测模型[J]．电力自动化设备，2018,38(5):36-42.Niu Zhewen,Yu Zeyuan,Li Bo,et al.Short-term wind power forecasting model based on deep gated recurrent unit neural network[J].Electric Power Automation Equipment,2018,38(5):36-42(in Chinese).
• [38]张建寰，吉莹，陈立东．深度学习在电力负荷预测中的应用[J]．自动化仪表，2019(8):8-12.Zhang Jianwei,Ji Ying,Chen Lidong.Application of deep learning in power load forecasting[J].Process Automation Instrumentation2019(8):8-12(in Chinese).
• [39]周永生．基于LSTM神经网络的PM2.5预测[D]．长沙：湖南大学，2018.
• [40] Wang S,Sun J,Xu Z.Hyper Adam:a learnable task-adaptive Adam for network training[C]//Thirty-Third AAAI Conference on Artificial Intelligence(AAAI).Honolulu,Hawaii,USA,2019:5297-5304.
• [41] Chen T,Guestrin C.Xgboost:A scalable tree boosting System[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco,USA:ACM,2016:785-794.
• [42] Gómez-Ríos A,Luengo J,Herrera F.A study on the noise label influence in boosting algorithms:Adaboost,GBM and XGBoost[C]//International Conference on Hybrid Artificial Intelligence Systems(HAIS),2017:268-280.
• [43] Aarshay J.Complete guide to parameter tuning in XGBoost[DB/OL].[2019-05-16].https://www.analyticsvidhya.com/blog/2016/03/complete-guide-parameter-tuning-XGBoost-with-codes-python.
• [44]王效．基于综合模型的电力系统中长期负荷预测方法研究[J]．华电技术，2013(6):40-41.Wang Xiao.Research on medium and long term load forecasting method of power system based on comprehensive model[J].Water Conservancy&Electric Power Machinery, 2013(6):40-41(in Chinese).
• [45]中国电机工程学会电工数学专委会．2016年电工数学建模竞赛[DB/OL].[2018-12-01].http://shumo.neepu.edu.cn/upload/2016-05/27/dijiujiediangongshuxuejianmojingsaishiti_2016Ati-dc56c.rar.