Multi-energy load forecasting incorporating AI algorithms: research status and trends in integrated energy systems

Against the background of accelerated transformation of the global energy structure towards decarbonization and cleanliness, Integrated Energy Systems (IES) has achieved rapid development, but at the same time, it is also facing a number of challenges and problems that need to be solved. High-precision multi-energy load forecasting, as the basic guarantee for stable operation and demand response of IES system, has become a hot direction of current research. This study aims to sort out and analyze the research lineage and development trend of multi-energy load forecasting in the context of IES. First, the development history and research hotspots of multi-energy load forecasting were reviewed by analyzing the keyword co-occurrence of related literature with the help of CiteSpace software. Second, it systematically summarizes the latest progress in the application of artificial intelligence (AI) algorithms in this field, focuses on the analysis of methods and techniques to improve the prediction accuracy, and explores the coupling relationship and interdependence mechanism between different energy loads. It has been shown that feature extraction, data preprocessing, and model optimization strategies play a key role in improving prediction performance. Finally, this paper further explores the potential and application prospects of emerging AI methods in addressing the challenges of multi-energy load forecasting in IES, providing theoretical support and reference directions for related research.