鲸鱼优化支持向量机的短期风电功率预测

为提高风电预测的精度,提出一种鲸鱼优化支持向量机SVM(support vector machine)的组合预测模型。该模型针对风电序列的非平稳波动特性,首先应用集合经验模态分解技术EEMD(ensemble empirical mode de?composition)将原始风电序列分解为一系列不同特征尺度的子序列;并引入鲸鱼优化算法WOA(whales optimiza?tion algorithm)解决SVM中学习参数选择难的问题,进而对各子序列建立WOA_SVM预测模型;最后,叠加各子序列的预测值以得到最终预测值。仿真表明,所提EEMD_WOA_SVM模型具有较高的风电预测精度,显著优于其他基本模型。

Short-term Wind Power Forecasting Based on Whales Optimization Algorithm and Support Vector Machine

To improve the accuracy of wind power forecasting,a combined prediction model based on whales optimiza?tion algorithm(WOA)and support vector machine(SVM)is proposed in this paper.First,according to the non-station?ary fluctuation characteristics of wind power sequences,the ensemble empirical mode decomposition(EEMD)tech?nique is used to decompose the original wind power sequences into a series of sub-sequence with different time charac?teristic scales.Then,WOA is introduced to solve the problem of difficulty in selecting the learning parameters in SVM,so that the WOA_SVM prediction model can be established for each sub-sequence.At last,the predicted values of each sub-sequence are superimposed to obtain the final predicted value.Simulation results show that the proposed EEMD_WOA_SVM model has higher prediction accuracy,which is significantly better than other basic models.