中文摘要：

提出一种基于小波分解（Wavelet Decomposition,WD）和极限学习机（Extreme Learning Machine,ELM）的新型短期风速组合预测模型。首先,采用小波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;其次,为避免极限学习机输入维数选取的随意性等问题,先对各分量进行重构相空间,再使用改进的极限学习机对各分量分别建模预测;最后,将各分量预测结果叠加得到最终预测结果。实验结果表明,文章所提的组合预测模型具有较高的预测精度。

英文摘要：

This paper studied the short-term prediction of wind speed by means of wavelet decomposition and Extreme Learning Machine. Wind speed signal was decomposed into several sequences by wavelet decomposition to reduce the non-stationary. Secondly, the phase space reconstructed was used to mine sequences characteristics, and then an improved extreme learning machine model of each component was established. Finally, the results of each component forecast superimposed to get the final result. The simulation result verified that the hybrid model effectively improved the wind speed prediction accuracy.