Load forecasting method with feedback chaos item

To describe the non-linear relation of load time series, a improved centroid method with non-liner feedback chaos item is presented. The method is realized by a fuzzy neural networks model which is not entirely linked. The defuzzification of the model adopts centroid method. In order to extend the scope of weight acting, the non-linear feedback item of weight value is employed to form chaos learning algorithm, which can make the system find the global minimal point or its approximation quickly and enhance the stability of the model. The simulation results show preferable forecasting capability of the model.