Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load

Abstract

This paper introduces an approach based on artificial neural networks in order to forecast the Hellenic daily electricity demand load. Several structures, learning algorithms and transfer functions were tested in order to produce a model with the best generalising ability. Actual input and output data collected from the Hellenic power network were used in the training, validation and testing process. Different factors such as economical, seasonality and weather conditions which indisputably affect the daily electricity demand load were taken into account in this approach. The produced results were compared with real electricity demand load records showing a great accuracy. The proposed approach can be useful in the studies of electricity providers, retailers and regulatory authorities aiming mainly in the uninterrupted supply of energy, maintaining at the same time a low cost.