Power quality disturbance source identification using self-organising maps

Power quality (PQ) is becoming increasingly important owing to the increasing use of power electronic devices, coupled with the increasing penetration of loads, which are sensitive to voltage disturbances. As a result of the problems caused by the confluence of these two trends, there is an increasing need for PQ to be monitored in order to diagnose its nature and locate the source of the disturbance, allowing remedial measures to be taken. While automated systems for diagnosis of PQ events have been developed, identifying the location of the source of a disturbance is a problem, which has not been fully addressed to date; in particular the question of locating a non-stationary disturbance. In this study, a novel approach to identify the location of the source of a PQ disturbance is described, using a form of artificial neural network known as a self-organising map. The proposed technique is verified via simulation of the IEEE 14-bus model in PSCAD and an experimental system based on the IEEE 6-bus model. This approach provides a mean of locating the source of PQ events, including transient disturbances.