Artificial Intelligence (AI) is increasingly being applied in power systems, enabling faster and more efficient data analysis, resource optimization, and real-time decision-making. This paper provides an overview of modern AI techniques used in operational management, control, and planning of power grids, with a special focus on neural networks, optimization algorithms (genetic algorithm, particle swarm optimization), and fuzzy logic. The advantages of AI methods over conventional approaches are analyzed, including reduced computation time, improved prediction accuracy, and enhanced system stability. Specific challenges to broader AI implementation in power systems are identified, including limited availability of high-quality labeled data for model training, complexity of integrating AI solutions into existing SCADA/EMS and DMS systems, lack of explainability in neural network outputs, and regulatory uncertainties that limit operational deployment. The paper offers perspectives for future development and research directions, including further integration of AI into smart grids, development of hybrid models for solving complex optimization problems, and the use of neural networks for local marginal price (LMP) prediction.
Bečejac et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: