A Hybrid Model Forecasting Study of Short-Term Electricity Load for Regional Integrated Energy Systems

Integrated Energy Systems (IES), as a crucial direction for future energy development, are dedicated to achieving the coordinated supply, optimized dispatch, and efficient utilization of multiple energy sources. Against the backdrop of the “dual carbon” goals, IES demonstrate broad prospects for development. Typically encompassing subsystems such as electricity, heat, and gas, IES enhance system flexibility and reliability through coupling conversion devices and energy storage units, providing key support for the construction of intelligent, low-carbon, and highly efficient energy systems. In this paper, the hybrid model is applied to the short-term load forecasting scenario of a practical regional integrated energy system. Empirical validation is conducted using hourly load data from Province <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$Y$</tex> in 2024. The results show minimal prediction errors and high forecasting accuracy, outperforming current mainstream prediction models. This not only verifies the model's effectiveness but also provides reliable data support for subsequent optimization of regional energy system dispatch, contributing positively to advancing the intelligent development of integrated energy systems.