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

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测精度。

A hybrid short-term wind speed forecasting model based on ensemble empirical mode decomposition and improved extreme learning machine

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.