Application of Core Vector Machine for Prediction of Day-Ahead Electricity Prices

Abstract

This paper presents Core Vector Machine (CVM) applied for short term electricity price forecasting in an Indian energy market. The accuracy in electricity price forecasting is very crucial for the power producers and consumers. With the accurate price forecasting, power producers can maximize their profit and manage short term operation. Meanwhile, consumers can maximize their utilities efficiently. The objective of this research is to develop models for day-ahead price forecasting using CVM during various seasons. A feature selection technique is used along with the CVM to reduce the variables for accurate price forecasting. Simulation results reveal that the CVM along with feature selection gives better results when compared with other machine learning techniques.