Short term load forecasting using non-linear template matching

Author

Jordaan, J.A. ; Ukil, A.

Author_Institution

Dept. of Electr. Eng., Tshwane Univ. of Technol., Emalahleni, South Africa

fYear

2011

fDate

13-15 Sept. 2011

Firstpage

1

Lastpage

5

Abstract

Accurate short term load forecasting plays a very important role in power system management. As electrical load data is highly non-linear in nature, in the proposed approach, we first use a Reproducing Kernel Hilbert Space (RKHS) method to fit the data. Afterwards a template is constructed based on the input-output data and the results from the RKHS method. To predict the load, only the template is used with no additional RKHS calculations. The proposed method is compared to a Support Vector Machine (SVM) prediction. Results show that the proposed method predicts much more accurate than the SVM.

Keywords

Hilbert spaces; load forecasting; pattern matching; power system management; support vector machines; Kernel Hilbert space method; RKHS method; electrical load data; input-output data; nonlinear template matching; power system management; short term load forecasting; support vector machine; Estimation; Hilbert space; Kernel; Load forecasting; Polynomials; Support vector machines; Training; Kernel methods; Reproducing Kernel Hilbert Space; Short Term Load Forecasting; Template Matching;

fLanguage

English

Publisher

ieee

Conference_Titel

AFRICON, 2011

Conference_Location

Livingstone

ISSN

2153-0025

Print_ISBN

978-1-61284-992-8

Type

conf

DOI

10.1109/AFRCON.2011.6072066

Filename

6072066