A Comprehensive Review on the Application of Large Language Models (LLMs) in Power Systems

Ghafari M., Sami A., Rezapour H., Ghayour S. S., Lin F., BAŞARAN K., ...Daha Fazla

IEEE Access, 2025 (SCI-Expanded, Scopus) identifier

  • Yayın Türü: Makale / Tam Makale
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1109/access.2025.3637226
  • Dergi Adı: IEEE Access
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Anahtar Kelimeler: Artificial Intelligence (AI), Carbon Footprint Accounting, Cybersecurity in Power Systems, Demand Response (DR), Distributed Energy Resources (DERs), Electric Vehicles (EVs), Energy Management, Energy Transition, Explainable AI (XAI), Intrusion Detection Systems (IDS), Large Language Models (LLMs), Multi-Objective Optimization (MOO), Natural Language Processing (NLP), Optimal Power Flow (OPF), Renewable Energy Sources (RESs), Smart Grids, Transformer Models
  • Manisa Celal Bayar Üniversitesi Adresli: Evet

Özet

Nowadays, modern power systems are facing increasing complexity with the rapid growth of renewable energy sources (RESs), the expansion of small and distributed energy resources (DERs) and the evolution towards cyber-physical smart grids. These developments have made the need for intelligent and flexible systems to support the decision-making processes. Advanced large linguistic models (LLM), as a new generation of artificial intelligence (AI), can understand and process complex text data and have been proposed as an innovative solution in the energy industry. These technologies can create a fundamental transformation in power systems management and optimization. This paper analyzes in depth the application of LLM in power systems. The current research tracks the evolution of AI in this field from simple methods, based on basic rules, to more advanced technologies, such as deep learning and transformer models. Within the paper, the basic principles of transformer models are described, and three important capabilities of this technology are emphasized: the ability to interpret the results, the ability to expand for different applications, and the flexibility to face different conditions. The conducted analysis highlights how the new generation of AI can bring a fundamental transformation in the management of power systems.