Short-term load forecasting in an autonomous power system using artificial neural networks

This paper presents the development of an artificial neural network based short-term load forecasting model for an autonomous power system. Problems encountered in data preparation, network structure definition and the model's sensitivity to temperature, together with suggested solutions, are discussed. The proposed model can provide next week's load forecasts. Experiences obtained during the application of the model to predict daily load curves in the autonomous power system of the Greek island of Crete are presented.