Artificial intelligence and quantum computing models for forecasting processes in power supply systems

Accurate forecasting of power supply parameters is one of the most fundamental tasks in modern energy system management [1]. The increasing penetration of renewable energy sources, the variability of consumer demand, and the transition to decentralized smart grids have introduced unprecedented complexity into the operation of power systems. Traditional forecasting methods, including statistical regression, time series analysis, and classical machine learning algorithms, often struggle to capture the nonlinear and transient dynamics of such systems.