An efficient kernel machine technique for short-term load forecasting under smart grid environment

In this paper, a kernel machine based method is proposed for short-term load forecasting. This paper makes use of Informative Vector Machine (IVM) of kernel machine to provide better prediction results with short-term load forecasting. The Kernel Machine technique is an extension of Support Vector Machine (SVM) that is very useful for pattern recognition to deal with the regression model with quantitative variables. IVM has advantage that better model is constructed with the use of a limited number of learning data through new information theory. The proposed method is successfully applied to real data of short-term load forecasting in Japan.