Fault Detection in Renewable AC Microgrids Using Gaussian Naïve Bayes, Support Vector Machine, and Random Forest

Abstract

Renewable AC microgrids are considered an important component of contemporary power systems since they aid in the incorporation of sustainable energy sources. Although there are many benefits, accurate fault detection is hard because of the inconsistency in the renewable energy sources and relatively low levels of fault currents that limit the efficiency of traditional fault detection techniques. This research work employs Machine Learning (ML)models to detect the faults in Renewable AC Microgrid with Gaussian Naïve Bayes (GNB), Support Vector Machine (SVM) and Random Forest (RF) classifiers is proposed. A detailed model of the microgrid is created in MATLAB for the generation of voltage samples. Some statistical features are selected from the acquired voltage signals for the training and testing of the classifier models. Experimental results indicate that the Random Forest classifier outperforms the other classifiers and provides superior classification accuracy with 98.8%, while it outperforms the GNB and SVM classifiers.