The rapid integration of renewable energy sources, distributed generation, and bidirectional power flows has significantly increased the complexity of modern power systems. Conventional analytical and numerical techniques often face limitations when dealing with system uncertainties, nonlinear behavior, and real-time operational requirements. In this context, Artificial Intelligence (AI) has emerged as an effective alternative, offering robust solutions for forecasting, state estimation, fault detection, stability assessment, and system optimization. This paper presents a comprehensive review along with an implementation-oriented discussion of AI-based techniques applied to power system analysis. Various methods, including machine learning, deep learning, fuzzy logic systems, and hybrid AI models, are critically evaluated for applications such as load forecasting, voltage stability assessment, optimal power flow, and fault identification. Simulation results and selected case studies demonstrate that AI-based approaches provide superior accuracy, adaptability, and computational efficiency compared to conventional methods, making them highly suitable for modern and future power system applications.
Kadam et al. (2026) studied this question.