Daily peak load forecasting using ANN

Abstract

Accurate load forecasting plays a key role in economical use of energy. Artificial Neural Network (ANN) models have been extensively implemented to produce accurate results for short-term load forecasting with time lead ranging from an hour to a week. In this paper daily peak load forecasting has been performed for the part of a town supplied by 19 distribution feeders on weekdays by taking into consideration the historical maximum load (Lmax) and maximum temperature (Tmax) data. Back-Propagation algorithm is verified for Momentum learning rule (MLR) and Delta-Bar-Delta learning rule (D-B-DLR). Optimization of the network parameters is performed for both learning rules. The optimized network performances are compared in terms of the mean absolute percentage error (MAPE) and the network complexity.