Short-term power load forecasting with least squares support vector machines and wavelet transform

Author

Chen, Qi-song ; Zhang, Xin ; Xiong, Shi-huan ; Chen, Xiao-wei

Author_Institution

Sch. of Comput. Sci. & Technol., Guizhou Univ., Guiyang

Volume

3

fYear

2008

fDate

12-15 July 2008

Firstpage

1425

Lastpage

1429

Abstract

Based on least squares support vector machines (LS-SVM) and Wavelet Transform theory, a novel approach for short-term power load forecasting is presented. The historical time series is decomposed by wavelet, so the approximate part and several detail parts are obtained. Then the results of Wavelet Transform are predicted by a separate LS-SVM predictor. The new forecast model combines the advantage of WT with LS-SVM. Compared with other predictors, this forecast model has greater generalizing ability and higher accuracy.

Keywords

least squares approximations; load forecasting; power engineering computing; support vector machines; time series; wavelet transforms; LS-SVM predictor; historical time series; least squares support vector machines; short-term power load forecasting; wavelet transform theory; Autoregressive processes; Cybernetics; Economic forecasting; Least squares methods; Load forecasting; Machine learning; Predictive models; Risk management; Support vector machines; Wavelet transforms; Wavelet Transform; least squares support vector machines; power load forecasting; short-term;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2008 International Conference on

Conference_Location

Kunming

Print_ISBN

978-1-4244-2095-7

Electronic_ISBN

978-1-4244-2096-4

Type

conf

DOI

10.1109/ICMLC.2008.4620629

Filename

4620629