Modeling and prediction of China's electricity consumption using Artificial Neural Network

Abstract

Artificial Neural Networks are proposed to model and predict electricity consumption of China. Multilayer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. Energy demand is modeled as a function of economic indicators such as population, gross national product, imports and exports. Performance comparison among the ANN and multiple linear models is made based on absolute mean square error. The ANN model also has much better RMSE for the forecasted energy demands than multiple linear regressions. Energy demand of China is predicted until 2050 using data from 1990 to 2008 along with other economic indicators. The results show that energy demands would peak during 2026–2035 and decrease gradually. This decreasing trend of energy demand appears very unique because all independent variables are increasing. It is estimated that the ANN model considered the high-nonlinearity of the data, which is not easily detectable using multiple linear regression model.