Fuzzy Wavelet Neural Networks for City Electric Energy Consumption Forecasting

Abstract

In view of the defects of the prediction model based on neural network, such as when doing prediction of nonlinear sequence, it is likely to fall into local hypo-strong point, and the rate of training is very slow. This paper presents a fuzzy wavelet neural network (FWNN) approach for annual electricity consumption in high energy consumption city. It is claimed that, due to high fluctuations of energy consumption in high energy consumption cities, conventional regression models do not forecast energy consumption correctly and precisely. Although ANNs have been typically used to forecast short term consumptions, this paper shows that it is a more precise approach to forecast annual electricity consumption. Furthermore, the FWNN approach based on ANN is used to show it can estimate the annual consumption with less error. Actual data from high energy consuming (intensive) from 1983 to 2003 is used to illustrate the applicability of the FWNN approach. This is the first study to present an algorithm based on the ANN and wavelet for forecasting long term electricity consumption in high energy consuming city. The prediction effect of wavelet neural network prediction model is proved in matlab7.0 simulation environment. A better prediction result is gained, and the defect of falling into local hypo-strongpoint is overcome, at the same time, the rate of training is raised compared with the prediction model based on artificial neural network. The calculation result shows that the presented model is effective.