模糊信息粒化和GWO-SVM算法结合的短期风速范围预测

为了实现对风速范围区间的准确预测,提出一种基于模糊信息粒化和灰狼优化-支持向量机(GWO-SVM)算法的风速预测模型.该模型首先利用模糊信息粒子,从一段连续时间的风速值提取出最大值、最小值及大致的平均水平值;然后,采用时间序列风速输入模型,构建输入支持向量机模型的标签向量与特征矩阵;最后,通过灰狼算法进行支持向量机预测模型的参数寻优,实现对风速范围区间的准确预测.在实例验证阶段,将风速历史数据进行模糊粒化,采取4种不同的参数寻优方式对支持向量机预测模型进行参数寻优.结果表明:GWO-SVM算法可以有效地提高风速范围预测的精确度.

Short-Term Wind Speed Range Prediction Based on Fuzzy Information Granulation and GWO-SVM Algorithm

In order to achieve accurate prediction of wind speed range interval, this paper proposes a wind speed prediction model based on fuzzy information granulation and grey wolf optimizer-support vector machine(GWO-SVM)algorithm. Firstly, the fuzzy information granules are used to extract the maximum, minimum and general average values of wind speed for a continuous period of time. Then the label vector and feature matrix are constructed as input of the SVM model by the time series wind speed prediction model, and finally the parameters of the SVM prediction model are optimized by the gray wolf algorithm to realize the accurate prediction of the wind speed range interval. On the example verified stage, the fuzzy information granulation of historical wind speed data is carried out, and the parameters of the SVM prediction model are optimized by four different parameter optimization methods. The results show that the GWO-SVM algorithm can improve the accuracy of wind speed range interval prediction more effectively.