基于MRMR的ORELM的短期风速预测

被引：3

作者：

王琦 ^{[1
]}

关添升 ^{[2
]}

秦本双 ^{[3
]}

机构：

[1] 中国电力工程顾问集团东北电力设计院有限公司

[2] 国网吉林省电力有限公司培训中心

[3] 东北电力大学电气工程学院

来源：

可再生能源 | 2018年 / 36卷 / 01期

关键词：

风速; 短期预测; MRMR; ORELM;

D O I：

10.13941/j.cnki.21-1469/tk.2018.01.013

中图分类号：

TM614 [风能发电];

学科分类号：

0807 ;

摘要：

由于风速具有间歇性、随机性及波动性等特点,导致大规模风电并网对电力系统的安全、稳定运行带来严重影响。文章提出一种基于最大相关最小冗余(Maximum Correlation Minimum Redundancy,MRMR)的离群鲁棒极限学习机(Outlier Robust Extreme Learning Machine,ORELM)的短期风速预测新方法。首先分析影响风速的属性特征,采用MRMR算法来衡量不同风速属性特征与风速的相关性,进而确定风速属性特征的输入维度;然后对极限学习机(Extreme Learning Machine,ELM)进行优化,构建ORELM风速预测模型。最后以美国某大型风电场实测数据为依据进行风速预测,仿真结果表明该方法具有较高的预测精度。

引用

页码：85 / 90

页数：6

共 18 条

[1]

Is extreme learning machine feasible?A theoretical assessment (part II).. Lin S,Liu X,Fang J,et al. IEEE Transactions on Neural Networks.&.Learning Systems . 2017

[2]

Collaborative representation based classification for face recognition. Zhang Lei,Yang Meng,Feng Xiangchu,et al. Computer Science . 2012

[3]

What are Extreme Learning Machines? Filling the gap between Frank Rosenblatt’’s dream and John von Neumann’’s puzzle. Guangbin Huang. Cognitive Computation . 2015

[4] 基于卡尔曼滤波的风速序列短期预测方法 [J].

修春波 ;

任晓 ;

李艳晴 ;

刘明凤 .

电工技术学报, 2014, 29 (02) :253-259

[5] 基于互信息的主成分分析特征选择算法 [J].

范雪莉 ;

冯海泓 ;

原猛 .

控制与决策 , 2013, (06) :915-919

[6]

An improved multi-step forecasting model based on WRF ensembles and creative fuzzy systems for wind speed[J] . Jing Zhao,Zhen-Hai Guo,Zhong-Yue Su,Zhi-Yuan Zhao,Xia Xiao,Feng Liu. &nbspApplied Energy . 2016

[7]

Local models-based regression trees for very short-term wind speed prediction[J] . A. Troncoso,S. Salcedo-Sanz,C. Casanova-Mateo,J.C. Riquelme,L. Prieto. &nbspRenewable Energy . 2015

[8] Regularized extreme learning machine for regression problems [J].

Martinez-Martinez, Jose M. ;

Escandell-Montero, Pablo ;

Soria-Olivas, Emilio ;

Martin-Guerrero, Jose D. ;

Magdalena-Benedito, Rafael ;

Gomez-Sanchis, Juan .

NEUROCOMPUTING, 2011, 74 (17) :3716-3721

[9]

Extreme Learning Machine for Regression and Multiclass Classification. Guang-Bin Huang,Hongming Zhou,Xiaojian Ding. IEEE Transactions on Systems Man and Cybernetics . 2012

[10]

Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. Peng H C,Long F H,Ding C. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2005

← 1 2 →