GraphPMU: Event Clustering via Graph Representation Learning Using Locationally-Scarce Distribution-Level Fundamental and Harmonic PMU Measurements
Armin Aligholian, Hamed Mohsenian‐Rad · IEEE Transactions on Smart Grid · 2022
This paper is concerned with the complex task of identifying thetypeandcauseof the events that are captured by distribution-level phasor measurement units (D-PMUs) in order to enhance situational awareness in power distribution systems. Our goal is to address two fundamental challenges in this field: a)scarcity in measurement locationsdue to the high cost of purchasing, installing, and streaming data from D-PMUs; b)limited prior knowledge about the event signaturesdue to the fact that the events are diverse and infrequent, and have unknown characteristics. To tackle these challenges, we propose anunsupervised graph-representation learningmethod, called GraphPMU, to significantly improve the performance in event clustering underlocationally-scarce data availabilityby proposing the following two new directions: 1) using thetopological informationabout therelative locationof the few available phasor measurement units on the graph of the power distribution network; 2) utilizing not only the commonly usedfundamentalphasor measurements, bus also the less exploredharmonicphasor measurements in the process of analyzing the signatures of various events. Through a detailed analysis of several case studies, we show that GraphPMU can highly outperform the prevalent methods in the literature.