This study aims to improve the accuracy of energy forecasting in China’s food manufacturing industry by addressing the challenges posed by the fixed parameters of grey Gompertz models. A Kernel Function Augmented Dynamic Fractional-Order Grey Gompertz Model (KFDGGM) is proposed to overcome the limitations of existing grey forecasting approaches.
The proposed KFDGGM model combines the Gompertz model with a fractional-order accumulation operator and a kernel function to enable dynamic parameter adjustment. Validation is conducted using energy consumption data from China’s food manufacturing sector, and the model’s performance is compared with that of other models.
Empirical results validate KFDGGM’s superior accuracy over traditional models in forecasting China’s food manufacturing energy consumption. Predictions show rising total energy demand but declining diesel/gasoline use, reflecting a clean energy substitution trend.
This study proposes a novel integration of fractional-order accumulation operators and kernel functions into the grey Gompertz framework, overcoming traditional limitations of fixed parameters and large dataset dependencies. KFDGGM’s dynamic mechanisms enable precise forecasting in data-scarce environments, offering methodological innovations for low-carbon transitions and data-driven energy policy optimization in food manufacturing.
