Accurately forecasting energy production and consumption is a critical challenge due to the inherent complexities and nonlinear behaviours of energy systems. Traditional grey forecasting models, while widely utilized, often struggle to adapt to these complexities. This study addresses these limitations by proposing a novel grey forecasting model, the Grey Von Bertalanffy Model (GVBM) model, which integrates Von Bertalanffy’s growth equation with Artificial Intelligence (AI)-based metaheuristic optimization techniques. The existing gap in the flexibility and adaptability of grey models is identified, and our approach introduces two additional parameters to better capture the dynamic behaviour of energy systems, especially for short-term forecasts. The primary aim of this research is to enhance the precision and reliability of energy forecasting by combining grey system theory with AI-driven optimization. The proposed GVBM leverages AI metaheuristic algorithms to fine-tune key parameters, thereby overcoming the structural limitations of traditional models. This method significantly improves the model’s ability to forecast energy production and consumption time series data with higher accuracy and adaptability. The is validated through application to six real-world energy scenarios involving electricity consumption and gas production. Across eight statistical metrics, the model consistently outperforms established grey forecasting models, demonstrating its superior forecasting accuracy, robustness, and adaptability. These results highlight the effectiveness of integrating AI with grey forecasting, offering a powerful tool for energy resource management and policy development.

Keywords