GraphPMU: Event Clustering via Graph Representation Learning Using Locationally-Scarce Distribution-Level Fundamental and Harmonic PMU Measurements
Armin Aligholian, Hamed Mohsenian‐Rad
Abstract
This paper is concerned with the complex task of identifying the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">type</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cause</i> of 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) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scarcity in measurement locations</i> due to the high cost of purchasing, installing, and streaming data from D-PMUs; b) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">limited prior knowledge about the event signatures</i> due to the fact that the events are diverse and infrequent, and have unknown characteristics. To tackle these challenges, we propose an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">unsupervised graph-representation learning</i> method, called GraphPMU, to significantly improve the performance in event clustering under <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">locationally-scarce data availability</i> by proposing the following two new directions: 1) using the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">topological information</i> about the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">relative location</i> of the few available phasor measurement units on the graph of the power distribution network; 2) utilizing not only the commonly used <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">fundamental</i> phasor measurements, bus also the less explored <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">harmonic</i> phasor 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.