In this paper, a wavelet-neural-network-based forecast model is developed for energy demand in China. Combining qualitative with quantitative analysis, we analyze some main factors affecting energy demand in China. A first order wavelet-neural network forecasting model with time-delay is established, including population, GDP, variation of industrial structure and energy consumption. The simulation result shows that this nonlinear forecasting model is more reasonable and has higher precision than other multiple regression models.
Download Full PDF Version (Non-Commercial Use)