Neural network with fuzzy set-based classification for short-term load forecasting

Electric power utilities require forecast of system demand or electrical load for one to seven days ahead. This paper studies a short-term electric load forecasting technique using a multi-layered feedforward artificial neural network (ANN) and a fuzzy set-based classification algorithm. The hourly data is subdivided into various class of weather conditions using the fuzzy set representation of weather variables and then the ANN's are trained and used to perform the load forecasting up to 120 hours ahead with a remarkable accuracy.