基于经验模态分解和支持向量机的短期风电功率组合预测模型.pdfVIP

第31 卷 第31 期 中 国 电 机 工 程 学 报 Vol.31 No.31 Nov.5, 2011 102 2011 年11 月5 日 Proceedings of the CSEE ©2011 Chin.Soc.for Elec.Eng. 0258-8013 (2011) 31-0102-07 TM 71 A 470 40 文章编号： 中图分类号： 文献标志码： 学科分类号： ⋅ 基于经验模态分解和支持向量机的 短期风电功率组合预测模型 叶林，刘鹏 ( 中国农业大学信息与电气工程学院，北京市 海淀区 100083) Combined Model Based on EMD-SVM for Short-term Wind Power Prediction YE Lin, LIU Peng (College of Information and Electrical Engineering, China Agricultural University, Haidian District, Beijing 100083, China) ABSTRACT: A wind power prediction method based on EMD 将风速序列分解为一系列相对平稳的分量，以减少不 empirical mode decomposition (EMD) and support vector 同特征信息间的相互影响；然后利用SVM 法对各分量建立 machine (SVM) is proposed to treat with the nonlinearity and 预测模型，针对各序列自身特点选择不同的核函数和相关参 nonstationarity of wind speed data. Firstly, the wind speed data 数来处理各组不同数据，以提高单个模型预测精度。最后将 is decomposed into a series of components with stationarity by 风速预测结果叠加并输入功率转化曲线以得到风电功率预 using EMD to reduce the influence between different feature 测结果。研究结果表明，EMD-SVM 组合预测模型能更好地 information. Then, different models were built and different 跟踪风电功率的变化，其预测误差比单一统计模型降低了 kernel functions and parameters were chosen to deal with each 5%~10%，有效地提高了短期风电功率预测的精度。 group of data by using SVM in order to improve the 关键词：经验模态分解；支持向量机；风速；短期风电功 forecasting accuracy. Finally, short term wind power 率预测；组合预测模型 forecasting was made based on wind speed data through a 0 引言 practical wind power curve. Case study was carried out to investi