A SHORT-TERM LOAD FORECASTING SYSTEM BASED ON BP ARTIFICIAL NEURAL NETWORK
Zhou Dian · Power System Technology · 2002
Load forecasting is an important task in the production of electric energy. In this paper, BP artificial neural network is applied in short term load forecasting.Under the condition of possessing enough training samples the models for forecasting are reasonably classified,the weekly and daily load forecasting models for different seasons are constructed. The selection of input variables, especially the selection of temperature, is discussed. In the training of neural network the over fitting often appears which affects the result of forecasting. To prevent this problem the entire data set is divided into training set and validation set. The result of typical calculation examples shows that the presented method is effective.