PMU Analytics for Power Fault Awareness and Prediction

The analysis of electrical wave measurements on an electricity grid obtained through Phasor Measurement Units (PMUs) offers a unique opportunity to detect power system faults in real time. The goal of this study is to evaluate the use of classification and forecasting models to recognize and predict power system faults in streaming PMU data. The evaluation of these models built with simulated PMU data from a real-world power network demonstrates that both classification and forecasting can be successfully used in the detection and prediction of single line and three phase to ground faults. The results obtained indicate that the same methodology can be applied to other types of power system faults.