Power distribution load forecasting using artificial neural networks
This paper presents a load forecasting method applied to electricity consumption in Nigde region. The load forecasting method is based on the Multi-Layered Perceptron (MLP) neural network (NN). Three MLP structures are compared for obtaining the best forecasting results. Then, the results of the best MLP structure are compared with the moving average method. The suitability of the proposed method is illustrated through an application to real load shapes form Turkish Electricity Distribution Corporation (TEDAS) in Nigde. The data represents the monthly electricity consumption in Nigde, Turkey. The proposed method is applied to the data from January 1991 to December 2001.