An artificial neural network for short term load forecasting

This paper presents the implementation of an artificial neural network (ANN) based short-term load forecasting model for the Manitoba Hydro power system, Canada. The selection of input variables and their transformations, the choice of the neural network architecture, the collection of training samples and training process are discussed in this paper. The results of the proposed neural network are very encouraging. The architecture of the proposed network is very simple, takes less time to train, and it is easy to use for reforecasting. The weights in the network show the relationship between the load and the weather conditions