Performance Analysis and Classification of Transmission Line Faults Using Machine Learning Algorithms

Abstract

Transmission line faults play a significant role in affecting power systems' reliability, stability, and security. This paper presents a fault classifying structure based on PMU, which diagnoses transmission line faults accurately through utilizing machine learning methods. The real-time measured and synchronized multiple times plan composed of phase currents, phase voltages, voltage magnitude, current magnitude, phase angles, and frequency parameters extracted from Phasor Measurement Units (PMUs). Support Vector Machine (SVM), XGBoost, and CatBoost were chosen as machine learning algorithms to classify faults. In addition, this paper develops a hybrid model based on combining these classifiers to enhance prediction performance. In conclusion, this system classifies five kinds of transmission line conditions including NF, LG, LL, LLG, and LLLG fault. Simulation results indicate that the proposed hybrid method achieved 99.98% classification accuracy and the individual classifiers obtain less than that. Besides, feature importance analysis found that voltage phase angle, current magnitude, and voltage magnitude were the most important parameters for fault diagnosis. The proposed method provides an efficient and reliable solution for smart grid monitoring, real-time fault diagnosis, and power system protection applications.