A study of advanced learning algorithms for short-term load forecasting

Abstract

Neural networks are currently finding practical applications, ranging from ‘soft’ regulatory control in consumer products, to the accurate modelling of nonlinear systems. This paper presents the development of improved neural-network-based short-term electric load forecasting models for the power system of the Greek island of Crete. Several approaches, including radial basis function networks, dynamic neural networks and fuzzy-neural-type networks, have been proposed, and are discussed in this paper. Their performances are evaluated through a simulation study, using metered data provided by the Greek Public Power Corporation. The results indicate that the load-forecasting models developed in this way provide more accurate forecasts, compared with conventional backpropagation network forecasting models. Finally, the embedding of the new model capability in a modular forecasting system is presented.