基于AdaBoost-KELM方法的短期电力负荷预测研究

《无线互联科技》杂志社 ›› 2022, Vol. 19 ›› Issue (9): 134-136.

基于AdaBoost-KELM方法的短期电力负荷预测研究

任瑞琪

西安铁路职业技术学院,陕西西安 710026

出版日期:2022-05-10 发布日期:2022-07-25
作者简介:任瑞琪(1994— ),女,陕西西安人,助教,硕士;研究方向:电力负荷预测风电功率预测。
基金资助:
项目名称:改进核极限学习机方法在智能电网中的应用;项目编号:XTZY21G06。

Research on short-term power load forecasting based on Ada Boost-KELM method

Ren Ruiqi

School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China

Online:2022-05-10 Published:2022-07-25

摘要/Abstract

摘要： 针对短期电力负荷预测,在极限学习机的基础上,提出了一种AdaBoost-KELM的方法。文章将KELM作为AdaBoost方法的基学习器,将AdaBoost-KELM方法应用于某地区的单步或者多步的短期电力负荷预测的实例中,在同等条件下,与BP,RBF,ELM,KELM,AdaBoost-BP,AdaBoost-RBF,AdaBoost-ELM几种方法进行比较。实验结果表明,所提出的AdaBoost-KELM方法在预测精度上最有优势。

关键词: 电力负荷预测, 极限, 学习机

Abstract: A method of Adaboost-KELM is proposed based on the limit learning machine.This article will KELM AdaBoost method of learning, as the AdaBoost-KELM method was applied to single or more steps in an area of the short-term power load forecasting example, under the same condition, with BP, RBF, ELM, KELM, AdaBoost-BP, AdaBoost-RBF, AdaBoost-ELM comparing several methods. The experimental results show that the proposed AdaBoost-KELM method is the most advantageous in predicting accuracy.

Key words: prediction of short-term power load, kernel extreme, learning machine

任瑞琪. 基于AdaBoost-KELM方法的短期电力负荷预测研究[J]. 《无线互联科技》杂志社, 2022, 19(9): 134-136.

Ren Ruiqi. Research on short-term power load forecasting based on Ada Boost-KELM method[J]. Wireless Internet Technology Magazine Agency, 2022, 19(9): 134-136.

参考文献

[1]ELATTAR E E,GOULERMAS J,WU Q H.Electric load forecasting based on locally weighted support vector regression[J].IEEE Transactions on Systems Man & Cybernetics,Part C:Applications & Reviews,2010(4):438-447.
[2]HAO Q,DIPTI S.Short-Term load and wind power forecasting using neural network-based prediction intervals[J].IEEE Transactions on Neural Networks and Learning Systems,2014(2):303-315.
[3]RUI Z,ZHAO Y D.Short-term forecasting of Australian National Electricity Market by an ensemble model of extreme learing machine[J].IET Generation Transmission & Distribution,2013(4):391-397.
[4]SWASTI R K,IOSE L R.Forecasting the load of electrical power systems in mid- and long-term horizons:a review[J].IET Generation,Transmission & Distribution,2016(16):3971-3977.
[5]XIA C,ZHAO Y D.Electricity price forecasting with extreme learning machine and bootstrapping[J].IEEE Transactions on Power Systems,2012(4):2055-2062.
[6]李军,李青.基于回声状态网络的电力负荷预测研究[D].兰州:兰州交通大学,2015.
[7]FREUND Y,SCHAPIRE R E.A decision-theoretic generation of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,1997(1):119-139.
[8]高云龙,潘金艳,吉国力,等.基于Boosting梯度下降理论的时间序列建模方法[J].中国科学:技术科学,2011(7):929-943.
[9]寇鹏,高峰.几何转换boosting回归算法及其在高耗能企业负荷预测中的应用[J].系统工程理论与实践,2013(7):1880-1888.
[10]FENG G,PENG K, LIN G,et al.Boosting regression methods based on a geometric conversion approach:Using svms based learners[J].Neurocomput-Ing,2013(3):67-87.
[11]HUANG G B,ZHU Q Y,SIEW C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006(1-3):489-500.
[12]毛力,王运涛.基于改进极限学习机的短期电力负荷预测方法[J].电力系统保护与控制,2012(20):140-144.
[13]王保义,赵硕.基于云计算和极限学习机的分布式电力负荷预测算法[J].电网技术,2014(2):526-531.
[14]李东辉,闫振林.基于改进流行正则化极限学习机的短期电力负荷预测[J].高电压技术,2016(7):2092-2099.
[15]李军,李大超.基于优化核极限学习机的风电功率时间序列预测[J].物理学报,2016(13):1-10.

《无线互联科技》杂志社
Wireless Internet Technology Magazine Agency