An Improve BP Neural Networks For Forecasting Electricity Price Based On Chaos

Electricity Price issues are the key problems in the markets and how to price the special commodity-electricity is essential for the smooth market operation. So using the relative historic data in predicting the future electricity Price is a very meaningful work.The neural network technique has gained high recognition in recent twenty years and has acquired abundant accomplishment. BP feed-forward networks can be applied to nonlinear modeling, function pattern association and pattern classification. As to actual problem, there is no system method to solve network architecture and neurons, quite a few experiments must be made. The paper introduces the way to create a network, train a network and simulate a network with MATLAB language. Some cautions are introduced too.Chaotic theory has been proved to be an important and useful theory algorithm. The natural tightly was connected between chaos and Fractal due to the infinite similarities of strange attractor of chaotic dynamic system. Nonlinear time series analysis based on chaotic theory cross through traditional frame of subjective model,draw out Prediction on the inner rules of chaotic time series data.This thesis advances a short-term price forecasting method based on Lyapunov exponent after comprehensively analyzes the relative factors. The method combines with the chaos theory and artificial neural networks and presents an improved BP neural networks model Based on chaotic analysis in the phases pace. Testing on California's electricity market proves this method's efficiency.