引用本文:张翌晖,王贺,胡志坚,等.基于集合经验模态分解和改进极限学习机的短期风速组合预测研究[J].电力系统保护与控制,2014,42(10):29-34.
ZHANG Yi-hui,WANG He,HU Zhi-jian,et al.A hybrid short-term wind speed forecasting model based on ensemble empirical mode decomposition and improved extreme learning machine[J].Power System Protection and Control,2014,42(10):29-34
【打印本页】   【下载PDF全文】   【查看/发表评论】  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被：浏览 6004次   下载 3682次 本文二维码信息
码上扫一扫！
分享到： 微信 更多
字体:加大+|默认|缩小-
基于集合经验模态分解和改进极限学习机的短期风速组合预测研究
张翌晖1, 王贺2, 胡志坚2, 王凯1, 黄东山1, 宁文辉1, 张承学2
1.广西电力科学研究院，广西 南宁 530023;2.武汉大学电气工程学院，湖北 武汉 430072
摘要:
提出一种基于集合经验模态分解（Ensemble empirical mode decomposition）和改进极限学习机（Improved Extreme Learning Machine，IELM）的新型短期风速组合预测模型。采用集合经验模态分解将风速序列分解成不同频段的分量，以降低序列的非平稳性。使用改进极限学习机对各分量分别建模预测，为避免极限学习机输入维数选取的随意性和分量信息丢失等问题，先对各分量重构相空间，最后将各分量预测结果叠加得到最终预测结果。实例研究表明，所提的组合预测模型具有较高的预
关键词:  风速  预测  改进极限学习机  集合经验模态分解  相空间重构
DOI：10.7667/j.issn.1674-3415.2014.10.005
分类号:
基金项目:博士点基金项目（20110141110032）；教育部中央高校基本科研业务费专项资金资助（20112072020008）
A hybrid short-term wind speed forecasting model based on ensemble empirical mode decomposition and improved extreme learning machine
ZHANG Yi-hui1, WANG He2, HU Zhi-jian2, WANG Kai1, HUANG Dong-shan1, NING Wen-hui1, ZHANG Cheng-xue2
1.Guangxi Electric Power Research Institute, Nanning 530023, China;2.School of Electrical Engineering, Wuhan University, Wuhan 430072, China
Abstract:
This paper proposes a new short-term combination prediction model of wind speed by means of ensemble empirical mode decomposition (EEMD) and improved extreme learning machine (IELM). Firstly, wind speed series is decomposed into several components with different frequency bands by EEMD to reduce the series non-stationary. Secondly, the phase space of each component is reconstructed in order to solve the randomness and component information lost of input dimensionality selection of extreme learning machine, and then an IELM model of each component is established. Finally, the forecast result of each component is superimposed to get the final result. The simulation result verifies that the hybrid model has higher prediction accuracy of wind speed.
Key words:  wind speed  forecasting  improved extreme learning machine  ensemble empirical mode decomposition  phase space reconstruction
  • 1
X关闭
  • 1
X关闭