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

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.