Application of SVM based on rough sets to short-term load forecasting

Authors:
Zhang Jinhui;Deng Jiajia
Affiliations:
North China Electric Power University, Baoding, China;Department of Economics and Management, North China Electric Power University, Baoding, China
Venue:
IITA'09 Proceedings of the 3rd international conference on Intelligent information technology application
Year:
2009

Citing 3
Cited 0

Support-Vector Networks

Machine Learning
Rough sets and intelligent data analysis

Information Sciences—Informatics and Computer Science: An International Journal
Practical selection of SVM parameters and noise estimation for SVM regression

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Support vector machines (SVM) has been used in load forecasting field. The noise and redundancy of sample data are important factors to the generalized performance of SVM. They can cause some disadvantages of slow convergence speed and low forecasting accuracy. A SVM forecasting method for short-term load forecasting based on rough sets (RS-SVM) is developed in this paper, using rough sets algorithm to preprocess historical load data, and both processing speed and forecasting accuracy will be improved. At last, this model is applied to short-term load forecasting, and compared with the method of SVM and BP neural networks it manifests better performance and better forecasting accuracy.