Application of SVM Methods for Mid-term Load Forecasting

Abstract

This paper presents an approach for the medium-term load forecasting using Support Vector Machines (SVMs). The proposed SVM model was employed to predict the maximum daily load demand for the period of a month. Analyses of available data were performed and the most important features for the construction of SVM model are selected. It was shown that the size and the structure of the training set may significantly affect the accuracy of predictions. The presented model was tested by applying it on real-life load data obtained from distribution company “ED Jugoistok” for the territory of city Niš and its surroundings. Experimental results show that the proposed approach gives acceptable results for the entire period of prediction, which are in range with other solutions in this area.