Forecasting total energy demand based on the DGM(1,N) model

Purpose This study aims to explore the key drivers affecting China’s total energy demand through quantitative analysis methods, and to construct a high-precision grey prediction model to forecast China’s total energy demand, with a view to providing a scientific basis for optimizing the energy demand structure and formulating sustainable development policies. Design/methodology/approach The study selects the national total energy demand and related macro indicators (GDP overall amount, total population, coal demand, the proportion of secondary industry output and the elasticity coefficient of energy demand) from 2010 to 2021, screens the core influencing factors through grey relational analysis and establishes a DGM(1,4) model to make predictions. Findings Grey relational analysis shows that GDP overall amount (correlation 0.9281), total population (0.8386) and coal demand (0.8061) have the most significant effect on total energy demand, while the elasticity coefficient of energy demand, the proportion of secondary industry output and the elasticity coefficient of energy demand have lower correlations. The prediction results of the DGM(1,4) model are well fitted to the true values, and the mean absolute percentage error (MAPE) is 0.06%, indicating that the model has high prediction accuracy. Originality/value GDP overall amount, total population and coal demand are the core factors driving the growth of energy demand in China, and the DGM(1,4) model is suitable for medium- and long-term energy demand forecasting, but the accuracy can be further improved by introducing time lag effects or intelligent optimization algorithms. This study provides data support for energy policymaking, and the model can be optimized in the future by combining more dynamic factors to achieve more accurate forecasting analysis.