Short-Term Electricity Price Forecasting Based on Rough Sets and Improved SVM

Author

Tian, Jinyu ; Lin, Yan

Author_Institution

Sch. of Bus. & Adm., North China Electr. Power Univ., Baoding

fYear

2009

fDate

23-25 Jan. 2009

Firstpage

68

Lastpage

71

Abstract

A novel model was proposed for short-term electricity price forecasting based on rough set approach and improved support vector machines (SVM). Firstly, we can get reduced information table with no information loss by rough set approach. And then, this reduced information is used to develop classification rules and train SVM, at the same time, we make use of the particle swarm optimization to optimize the parameters. The effectiveness of our methodology was verified by experiments comparing BP neural networks with our approach.

Keywords

learning (artificial intelligence); particle swarm optimisation; pattern classification; power engineering computing; power markets; pricing; rough set theory; support vector machines; classification rule; electricity price forecasting; particle swarm optimization; reduced information table; rough set approach; support vector machine; Data mining; Information systems; Neural networks; Particle swarm optimization; Power industry; Power markets; Rough sets; Support vector machine classification; Support vector machines; Training data; Electric price; Particle Swarm Optimization; Rough sets; SVM; forecasting;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge Discovery and Data Mining, 2009. WKDD 2009. Second International Workshop on

Conference_Location

Moscow

Print_ISBN

978-0-7695-3543-2

Type

conf

DOI

10.1109/WKDD.2009.93

Filename

4771880