Preliminary Work to Classify the Disturbance Events Recorded by Phasor Measurement Units

With increasing use of phasor measurement units in power system, an enormous amount of data is being stored in phasor data concentrators (PDCs). PDCs have the capability to store disturbance files separately. Over a period of time, the number of such disturbance files keeps increasing. However, these files are not really mined for data and mapped to actual events that may have caused the disturbance. This paper uses actual disturbance files from a PDC in the Public Service Company of New Mexico (PNM) system that collects data from four PMUs, and shows how the data needs to be preprocessed before it can be used. It also evaluates the performance of a feature extraction and classifier tool on some limited data files that store data for known disturbances logged by PNM. Based on these initial results, effectiveness of the classifier tool is evaluated, and future work is proposed that may ultimately lead to real time identification of disturbance events immediately after the disturbance files are created.