摘要
为了提高风电场风速短期预测的精度,提出了将经验模式分解与数据挖掘方法相结合对风速时间序列进行建模预测。对风速时间序列进行经验模式分解,使之分解为若干不同频带的本征模式分量。对不同频带的平稳分量建立相应的最小二乘支持向量机预测模型,将各模型的预测值等权求和得到最终预测值。仿真实验结果表明,风电场短期风速预测的MAPE为1.507%,提高了此类预测的精度,表明了该方法的有效性。
In order to improve the forecast precision,a forecasting method based on empirical mode decomposition(EMD) and data mining method is proposed.The wind speed time series is decomposed into several intrinsic mode functions(IMF) and the trend term.The different least square support vector machine(LS-SVM) models to forecast each IMF are built up.These forecasting results of each IMF are combined to obtain the final forecasting result.The simulation experiment shows the value of the MAPE is 1.507% about wind speed forecasting and the prediction accuracy is improved considerably.
出处
《计算机工程与设计》
CSCD
北大核心
2010年第10期2303-2307,共5页
Computer Engineering and Design
基金
国家自然科学基金项目(50967001)
关键词
风速时间序列
数据挖掘
经验模式分解
本征模式分量
最小二乘支持向量机
wind speed time series
data mining
empirical mode decomposition(EMD)
intrinsic mode function(IMF)
least square support vector machine(LS-SVM)