Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Beijing Information Science & Technology University》 2013-06
Add to Favorite Get Latest Update

Short-term wind power forecast based on empirical mode decomposition

WANG Li-jie;LI Hui;School of Automation,Beijing Information Science and Technology University;  
The short-term prediction of wind power generating capacity is made by means of empirical mode decomposition and neural network for the nonlinearity and nonstationarity of the system. Signal was decomposed into finite number of intrinsic mode functions( IMF) by empirical mode decomposition. Different neural networks are built and rolling learning for improving weight and threshold values is used. Every IMF is predicted separately,and the predicted resultsare added to get the final prediction. Some simulations are performed on the real data from Saihanba wind farm. The results show that the neural network model based on empirical mode decomposition is effective and the mean absolute error drops from 12. 55% to 10. 20%,compared with the persistence model.
【Fund】: 北京市属高校青年拔尖人才培养计划(CIT&TCD201304113);; 北京信息科技大学校基金项目(5026010919)
【CateGory Index】: TM614;TM715
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved