Load Forecasting Using Multi-Layer Perceptron Neural Network

Load forecasting has become one of the major areas of research in electrical engineering and is an important problem in operation and planning of electric power generation. Load forecasting is the technique for prediction of electrical load. STLF (Short term load forecast) is essential for Power system planning. In a deregulated market it is much need for a generating company to know about the market load demand for generating near to accurate power. If the generation is not sufficient to fulfill the demand, there would be problem of irregular supply and in case of excess generation the generating company will have to bear the loss. Neural network techniques have been recently suggested for short-term load forecasting by a large number of researchers. In this paper half hourly load data is collected from the New South Wales (NSW), Australia and application of short term load forecasting (STLF) using multilayer feed forward network (MLFFN) is used in MATLAB environment. The results shows that this method is simple and more accurate with the minimum error and can be used for short term load forecasting. The network will be trained with Levenberg Marquardt back propagation algorithm. In order to investigate the result, have to check the performance of model during training, validation and testing. Our aim is to develop best suited model for New South Wales (NSW),Australia by critically evaluating the ways in which the neural network is proposed.