Short Time Forecast of Wind Speed Based on EMD and SVM
As an important renewable energy,wind power is paid great attention by all countries.It is of great significance to predict wind speed accurately for the power system which includes large amounts of wind power.The wind speed time series appears typical non-stationary,as a result,the outcome obtained from applying single prediction method directly will be unsatisfied.In order to improve the accuracy of wind speed prediction,a model based on empirical mode decomposition (EMD) and support vector machines (SVM) is proposed in the paper.The wind speed time series is made by EMD at first,then appropriate support vector machine model is established with different frequency bands,finally the output value of each model is summed equal right to get the final prediction result.The radial kernel is selected by the SVM,the parameters that necessary are obtained through cross-validation.The actual cases are employed to demonstrate the validity of the proposed approach.The results are compared with those obtained by the single SVM model,which shows that the given model can effectively improve the accuracy of wind speed forecasting.
Wind speed forecast SVM EMD
Yancai XIAO Chunya LI Peng WANG
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China
国际会议
The 21st ISPE International Conference on Concurrent Engineering (2014国际并行工程学术会议)
北京
英文
806-812
2014-09-08（万方平台首次上网日期，不代表论文的发表时间）