Comparative Analysis of Artificial Intelligence Techniques for Line Fault Detection in On-Grid Solar Microgrids

On-grid solar microgrids (SMGs) are increasingly deployed to support sustainable and distributed energy generation. However, the low fault current levels, power-electronic interfaces, and dynamic operating conditions of SMGs create significant challenges for conventional protection systems, which may struggle to accurately detect and locate line faults (LFs). While artificial intelligence (AI) has shown promise in addressing these challenges, there remains limited comparative evidence regarding the suitability of different AI techniques for LF detection in on-grid SMGs under identical operating conditions. Therefore, this study investigates and compares the performance of four AI techniques, namely, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Support Vector Machine (SVM), and Random Forest (RF), for LF detection in on-grid SMGs. An on-grid SMG test system based on the IEEE 6-bus benchmark is implemented in MATLAB/Simulink 2025a to simulate various LF conditions and generate voltage and current datasets for model training and testing. All models are trained and evaluated under identical performance metrics, including accuracy, precision, recall, F1-score, noise robustness, and computational speed. The results show that deep learning (DL) models outperform classical machine learning approaches, with CNN achieving the highest performance of 99.79% accuracy and a 99.78% F1-score, followed by LSTM with 98.97% accuracy and a 98.92% F1-score. SVM and RF achieved accuracies of 98.25% and 95.75%, respectively, while requiring less than three minutes of training time, highlighting their suitability for real-time and resource-constrained applications. These findings provide a robust comparative benchmark for AI-based LF detection in on-grid SMGs and offer practical guidance for selecting appropriate AI techniques based on performance and computational requirements.