The Research of Power Load Forecasting Method on Combination Forecasting Model

Author

Liu, Shuliang ; Hu, Zhiqiang ; Chi, Xiukai

Author_Institution

Sch. of Manage., North China Electr. Power Univ., Baoding, China

fYear

2009

fDate

26-28 Dec. 2009

Firstpage

5257

Lastpage

5260

Abstract

The problem of power load market forecasting is studied and analyzed, and a new method of power load market forecasting is advanced in this paper. Counter to the characteristic of high nonlinear and high noise of stock time series, the noise is efficiently filtered and the reduction in the data performed by means of. LS-SVM model and BP neural network model are studied and analyzed, and the fuzz change weight combination prediction model based on the forecasting model of LS-SVM and BP neural network is introduced. The model is used to forecast power load time series and satisfactory effect is acquired.

Keywords

least squares approximations; load forecasting; power engineering computing; power markets; support vector machines; time series; BP neural network; LS-SVM model; combination forecasting model; power load market forecasting; stock time series; Demand forecasting; Economic forecasting; Energy management; Load forecasting; Multi-layer neural network; Neural networks; Noise reduction; Power system modeling; Power system security; Predictive models;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Science and Engineering (ICISE), 2009 1st International Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4244-4909-5

Type

conf

DOI

10.1109/ICISE.2009.1273

Filename

5455617