Аннотация
The growing global focus on mitigating climate change has emphasized the need for efficient strategies that integrate renewable energy sources (RES) while minimizing emissions. This paper explores the application of various intellectual methods-Energy System Models (e.g., TIMES, LEAP), Multi-Objective Optimization, Computable General Equilibrium (CGE) Models, Life Cycle Assessment (LCA), and Machine Learning (ML)-for analysing energy balances and developing low-emission strategies. These methods offer distinct capabilities in balancing technological, economic, and environmental aspects of energy systems. The paper examines how these approaches facilitate the integration of RES, address operational challenges, and handle uncertainties in energy demand and supply. Case studies demonstrate how AI and ML techniques optimize energy dispatch and demand forecasting, while system models provide long-term planning solutions. A comprehensive comparison of these methods is presented, highlighting their strengths and limitations in transitioning towards sustainable and low-emission energy systems.