Application of Elman Neural Network in Short-Term Load Forecasting

An Elman neural network with a weather component is proposed for the power load forecasting. Elman neural network can meet nonlinear recognition and process prediction of the dynamic system, and make power system having the ability to adapt to time-varying characteristics in mechanism. It is proved by simulation results that this model has a good performance in increasing forecasting accuracy because of its inherent dynamic behavior and memory behavior. The forecasting ability of Elman neural network are better than BP neural network. dynamic system, and has better adaptability to dynamic forecasting and prediction problem in mechanism. The RBF centres are determined by the orthogonal least squared (OLS) learning procedure. The effectiveness of the model and algorithm with the example of power load forecasting have been proved and approximation capability and learning speed of RBF neural network is better than BP neural network.