An Efficient Technique to Improve Fault Categorization in Transmission Lines

Machine Learning (ML) has become an essential tool for solving complex problems in the domain of electrical engineering. The ability to examine a large dataset, search for paths, and predict trends has enabled much progress. The strength of the research lies in the use of ML algorithms for fault classification in transmission lines. The ML models take into account the presence of a faulty voltage or current while the fault is occurring. This research confirms the efficiency of the algorithms built with ML techniques. A faulted transmission line, simulated in the MATLAB/Simulink environment, is used and techniques such as Decision Tree (DT) and Random Forest (RF) are implemented for classification purposes. The Receiver Operating Characteristic (ROC) curve, Precision-Recall (PR), and confusion matrix demonstrate the efficiency of the proposed algorithm. The converged technique optimizes the fault categorization and increases both precision and effectiveness by detecting faults within the transmission lines.