Short-Term Load Forecasting Based On Fuzzy Neural Network

The short-term load forecast of electric power system is an important routine for power dispatch and load management. Its precision will influence the economic and secure operation of power systems and quality of power supply. The features of short-term load forecast can be generalized as followings: many data need to be forecasted, the physical factors which influence forecast are complicated and random, and high precision of forecast is demanded. Due to the complicacy and uncertainty of load forecast, electric power load is difficult to be forecasted precisely if we apply analysis model and numerical value algorithm model.Combined with the problem in short-term load forecasting, two new methods based fuzzy neural network(FNN) and artificial neural network(ANN) are given in this paper respectively.The BP algorithm is used in load forecasting. It takes full use of the powerful learning ability and nonlinear reflecting functions of the artificial neural networks and combines the weather factors, special days and historical load data. Under the condition of possessing enough training samples, the models for forecasting are reasonably classified and the different seasons and day type load forecasting models for are constructed. In the meanwhile, the selection of input variables is discussed.This paper presents the development of a fuzzy system for short-term load forecasting. This fuzzy system combines the fuzzy inference principles with the neural network structure and learning abilities into an integrated neural...