基于随机森林算法的中短期用电量预测
CSTR:
作者:
中图分类号:

TM863


Medium and shortterm electricity demand prediction based on random forests algorithm
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [20]
  • | | | |
  • 文章评论
    摘要:

    传统电力预测模型不能很好地将多种影响因素纳入考虑,也无法对关联因素进行筛选。针对该类问题,该文将信息论中的互信息及人工智能随机森林算法引入中短期用电量预测中。互信息可以根据多种变量与用电量间的平均互信息值大小辨识出关联性高的因素,不同产业可能高关联于不同变量。考虑不同关联因素,采用随机森林算法对不同产业进行针对性预测建模。以江苏省的用电量数据作为实际算例,并将上述方法与未采用互信息的方法以及未针对性分产业建模进行对比。仿真结果表明,上述方法具有科学性和有效性,且有较高的预测精度。

    Abstract:

    Traditional power forecasting models can not efficiently take various factors into account, neither to identify the relation factors. In this paper, mutual information in information theory and the artificial intelligence random forests algorithm are introduced into the medium and shortterm electricity demand prediction. Mutual information can identify the high relation factors based on the value of average mutual information between a variety of variables and electricity demand. Different industries may be highly associated with different variables. The random forests algorithm is used to build the different industries forecasting models according to the different correlation factors. The data of electricity consumption in Jiangsu Province is taken as a practical example. In the example, the above methods are compared with the methods without mutual information and the industries. The simulation results show that the above method is scientific, effective, and can provide higher prediction accuracy.

    参考文献
    [1] 国家发展和改革委员会,国家能源局.电力发展“十三五”规划(2016—2020年)[EB/OL].http://bgt.ndrc.gov.cn/zcfb/201612/P020161222582163986577.pdf,20161107.
    [2] 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.
    [3] 徐晨,曹莉,梁小晓,等.基于ABCBP神经网络的用电量预测研究[J].计算机测量与控制,2014,22(3):912914,922.XU Chen,CAO Li,LIANG Xiaoxiao,et al.Research on electricity demand forecasting based on ABCBP neural network[J].Computer Measurement & Control,2014,22(3):912914,922.
    [4] 温盛科,杨悦辉,蔡妙妆,等.基于纵横交叉优化灰色模型的电能计量装置状态评估方法[J].电力科学与技术学报,2018,33(3):4449.WEN Shengke,YANG Yuehui,CAI Miaozhuang,et al.Research on state assessment method of electric energy metering device based on crisscross optimization grey model[J].Journal of Electric Power Science and Technology,2018,33(3):4449.
    [5] 牟宏,王春义,顾洁,等.基于支持向量-分位数回归的短期负荷预测及风险分析[J].电力科学与技术学报,2016,31(3):5156.MOU Hong,WANG Chunyi,GU Jie,et al..Shortterm load forecasting and risk analysis based on support vectorquantile regressing[J].Journal of electric power science and technology,2016,31(3):5156.
    [6] Chu Yinghao,Urquhart Bryan,Gohari Seyyed M I,et al.Shortterm reforecasting of power output from a 48 MWe solar PV plant[J].Solar Energy,2015,112:6877.
    [7] 李元诚,方廷健,于尔铿,等.短期负荷预测的支持向量机方法研究[J].中国电机工程学报,2003,23(6):5559.LI Yuancheng,FANG Tingjian,YU Erkeng,et al.Study of support vector machines for shortterm load forecasting[J].Proceeding of the CSEE,2003,23(6):5559.
    [8] 王宁,谢敏,邓佳梁,等. 基于支持向量机回归组合模型的中长期降温负荷预测[J].电力系统保护与控制,2016,44(3):9297.WANG Ning,XIE Min,DENG Jialiang,et al.Midlong term temperaturelowering load forecasting based on combination of support vector machine and multiple regression[J].Power System Protection and Control,2016,44(3):9297.
    [9] Breiman L.Random forest[J].Machine Learning,2001,45:532.
    [10] Ho T K.The random subspace method for constructing decision forests[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1998,20(8):832844.
    [11] 吴潇雨,和敬涵,张沛,等.基于灰色投影改进随机森林算法的电力系统短期负荷预测[J].电力系统自动化,2015,39(12):5055.WU Xiaoyu,HE Jinghan,ZHANG Pei,et al.Power system shortterm load forecasting based on improved random forest with grey relation projection[J].Automation of Electric Power Systems,2015,39(12):5055.
    [12] 赵腾,王林童,张焰,等.采用互信息与随机森林算法的用户用电关联因素辨识及用电量预测方法[J].中国电机工程学报,2016,36(3):604614.ZHAO Teng,WANG Lintong,ZHANG Yan,et al.Relation factor identification of electricity consumption behavior of users and electricity demand forecasting based on mutual information and random forecasts[J].Proceedings of the CSEE,2016,36(3):604614.
    [13] 许保勋.面向高维数据的随机森林算法优化研究[D].哈尔滨:哈尔滨工业大学,2013.
    [14] 刘强,胡志强,周宇,等.基于CEEMD和随机森林算法的短期风电功率预测[J].智慧电力,2019,47(06):7176+94.LIU Qiang,HU Zhiqiang,ZHOU Yu,et al.Shortterm Wind Power Forecasting Based on CEEMD and Random Forest Algorithm[J].Smart Power,2019,47(06):7176+94.
    [15] 赵晋泉,杨婷,吴凡,等.基于数据挖掘的输配网一体化事故响应决策[J].电力系统保护与控制,2018,46(5):18.ZHAO Jinquan,YANG Ting,WU Fan,et al.Data mining based accident response and decision-making for integrated transmission and distribution grid[J].Power System Protection and Control,2018,46(5):1-8.
    [16] 原媛,顾洁,黄薇,等.互信息在电力系统中长期负荷预测中的应用[J].华东电力,2009,37(2):236239.YUAN Yuan,GU Jie,HUANG Wei,et al.Application of mutual information to power system medium and longterm load forecasting[J].East China Electric Power,2009,37(2):236239.
    [17] 傅祖芸.信息论:基础理论与应用(第4版)[M].北京:电子工业出版社,2015.
    [18] 曹雪虹.信息论基础[M].北京:清华大学出版社,2009.
    [19] 蔡林霖.随机森林的模型选择及其并行化方法[D].哈尔滨:哈尔滨工业大学,2013.
    [20] Cutler A,Cutler D R,Stevens J R.Random forests[J].Machine Learning,2011,45(1):157176.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

乔黎伟,王静怡,郭 炜,等.基于随机森林算法的中短期用电量预测[J].电力科学与技术学报,2020,35(2):150-156.
QIAO Liwei, WANG Jingyi, GUO Wei, et al. Medium and shortterm electricity demand prediction based on random forests algorithm[J]. Journal of Electric Power Science and Technology,2020,35(2):150-156.

复制
分享
文章指标
  • 点击次数:401
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2020-09-03
文章二维码