Skip to Main Content
Forecasting the annual energy demand of a country has important implications for the policy makers and investors. Annual energy demand of a country is strongly related with its economic structure and performance. This paper presents a model based on multilayer feedforward neural network to forecast the energy demand for China. The model has four independent variables, such as gross domestic product, population, import, and export amounts. The proposed model better estimated energy demand than a linear regression model in terms of root mean squared error (RMSE). The model also forecasted better than the linear model in terms of RMSE without any over-fitting problem. Further testing based upon reliable source data showed unanticipated results. Instead of growing permanently, the energy demands peaked at certain points, and then decreased gradually. This trend is quite different from the results by regression.