A New Spike Based Neural Network for Short-Term Electrical Load Forecasting

Accurate short-term power demand forecast is of great importance to utility companies for power system planning and operation. Based on the literature survey, artificial neural networks (ANN) are found to be an alternative to classical statistical methods in terms of the accuracy of the forecasted results. This paper presents the implementation of a Spiking Neural Network (SNN) for short-term load forecasting model to forecast one day ahead and one week ahead hourly demand pattern. The selection of input variables, SNN architecture and training algorithm are discussed in this paper. The suitability and the validation of the proposed model is investigated and compared with a feed forward back-propagation ANN model.