Fahturomi Anjar Septian, Divala Zahra Oktavia, Mufid Athooyaa, Mirza Putra Firmansyah, Salsa Queennya Ratna Siwi, Rizky Ajie Aprilianto
Artificial intelligence (AI) has become a crucial technology for supporting smart grid systems, particularly in fault detection within electric transmission networks. AI offers predictive analysis and real-time decision-making capabilities that conventional methods lack. This study conducts a Systematic Literature Review (SLR) of 39 selected articles from 983 screened studies, applying the Population, Intervention, Comparison, Outcome, Context (PICOC) framework and PRISMA methodology. The objective is to identify recent trends, evaluate the effectiveness, and explore challenges in AI-based fault detection. The results show that AI models, particularly Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM), achieve high accuracy levels, with ANN reaching up to 99.74 %, CNN up to 98. 90%, and LSTM up to 97. 65% in fault classification tasks. These findings highlight the potential of AI to enhance real-time monitoring, predictive maintenance, and operational efficiency in transmission networks because practical implementation faces challenges such as data quality, computational complexity, and scalability. Hence, this review provides comprehensive insights to guide future development of robust and scalable AI solutions for improving smart grid reliability. © 2025 IEEE.
Universitas Negeri Semarang, Department of Electrical Engineering, Semarang, Indonesia
