基于CEEMD-IDA-SVM的风电功率短期预测

Short-term wind power prediction based on CEEMD-IDA-SVM

为提高风电功率预测精度,提出一种结合完全集合经验模态分解(CEEMD)、改进蜻蜓算法(IDA)和支持向量机(SVM)的风电功率短期预测模型。首先,使用CEEMD方法对风电功率原始数据进行预处理,将非平稳信号分解为多个子序列,从而提高数据的稳定性,改善数据质量。其次,在蜻蜓算法中引入反向学习策略,以改善算法的收敛性能,形成的IDA用于SVM参数的寻优。最后,利用IDA优化后的SVM构建预测模型。实例仿真结果及对比实验表明:本文使用的方法能有效地提高风电功率的预测准确率,有一定的优越性。

A short-term wind power prediction model combining complementary ensemble empirical mode decomposition(CEEMD),improved dragonfly algorithm(IDA)and support vector machine(SVM)is proposed.First,the CEEMD method is used to preprocess the original data of wind power,and the non-stationary signal is decomposed into multiple subsequences.Therefore,the stability and quality of data are improved.Second,a reverse learning strategy is introduced into the dragonfly algorithm to improve the convergence performance of the algorithm.The IDA is used for parameter optimization.Finally,the prediction model is established with the SVM optimized by the IDA.The simulation results and comparative experiments show that the CEEMD-IDA-SVM method can effectively improve the prediction accuracy of wind power and has certain advantages.