Simulation-Driven Machine Learning for Power Quality Classification in EV-Integrated IEEE 5 Bus Systems

The integration of electric vehicle (EV) loads into the IEEE 5-Bus Distribution System introduces various power quality (PQ) disturbances, such as voltage sags, voltage swells, harmonics, and flicker. These issues can significantly affect grid stability and operational efficiency. This study explores the classification of these PQ disturbances using machine learning (ML) techniques. Two algorithms-Support Vector Machines (SVM) and K-Nearest Neighbors (KNN)-are evaluated and compared based on their classification accuracy and robustness. The results reveal that while both methods are effective in identifying <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$P Q$</tex> issues, SVM consistently outperforms KNN in terms of precision and reliability. Therefore, SVM emerges as the more suitable approach for mitigating PQ challenges in the IEEE 5-Bus system.