An Open-Access Repository of Synchrophasor Data Quality Examples: Curation and Example Applications

Synchrophasor measurements are critical in providing wide-area situational awareness to power system operators. However, data artifacts may be introduced in these measurements due to various factors such as loss of communication, loss of GPS signal, internal clock error, and vendor-specific implementation of phasor estimation algorithms. Tools designed to provide actionable insights from synchrophasor data, hence, must be designed to be robust to these data quality issues. To test the performance of algorithms in the presence of bad data encountered in field measurements, researchers need access to real-world examples of such data artifacts. To address this need, two years of synchrophasor data sourced from multiple electric utilities in the United States were analyzed to identify examples of data quality problems. These examples were then labeled and published in the Grid Event Signature Library, a publicly available repository of power system measurements hosted by the Oak Ridge National Laboratory. This paper describes the data curation process, and illustrates two application use cases where the dataset can be valuable to the research community. In the first use case, a random forest (RF) classifier is trained to distinguish power system disturbance signatures from data anomalies introduced in synchrophasor measurements due to clock errors. With optimally tuned class weights, the RF classifier achieves an F1 score of 0.999. The second use case studies the impact of data quality issues on an example synchrophasor application (specifically, event start time determination). It is found that the introduction of quantization noise and intermittent data anomalies can increase the root mean square error for event start time determination by 1-4 seconds. The use cases demonstrate how the repository curated in this work can be valuable for developing and testing tools aimed at analyzing synchrophasor measurements.