PMU Placement for Line Outage Identification via Multinomial Logistic Regression

Abstract

We consider the problem of identifying a single line outage in a power grid by using data from phasor measurement units (PMUs). When a line outage occurs, the voltage phasor of each bus node changes in response to the change in network topology. Each individual line outage has a distinctive signature, and a multinomial logistic regression classifier can be trained to distinguish between these signatures reliably. We consider first the ideal case in which PMUs are attached to every bus. We then describe techniques from regularized optimization for placing PMUs selectively on a subset of buses, with the subset being chosen to allow discrimination between as many outage events as possible. Experimental results with synthetic 24-h demand profile data generated for IEEE 14-, 30-, 57-, and 118-bus systems are presented.