Abstract Phasor Measurement Units (PMUs) are widely used in smart grid to provide high-frequency, real-time measurements of the electrical waves, enabling wide-area monitoring and control. These devices generate a significant amount of data on a daily basis, which presents challenges for grid operators to leverage the useful information contained in this data. In this paper, we present an empirical study of applying unsupervised clustering on PMU data for event characterization on the smart grid. We show that although the PMU data are time series in nature, it is more efficient and robust to apply clustering methods on carefully selected features from the data collected at certain instantaneous moments in time. Experiments have been carried out on real PMU data collected by Bonneville Power Administration in their wide-area monitoring system in the pacific northwest, and the results show that our instantaneous clustering method achieves high homogeneity, which provides great potentials for identifying unknown events in the grid without substantial training data. In addition, we also present our initial effort in cluster-specific classification, which incorporates supervised learning in the process to classify event types within individual clusters.
Characterizing Smart Grid Events Using Clustering Methods
2017-01-01
22 pages
Article/Chapter (Book)
Electronic Resource
English
SYSTEMS AND METHODS FOR IDENTIFYING DISTRACTED DRIVING EVENTS USING UNSUPERVISED CLUSTERING
European Patent Office | 2023
|Systems and methods for identifying distracted driving events using unsupervised clustering
European Patent Office | 2023
|SYSTEMS AND METHODS FOR IDENTIFYING DISTRACTED DRIVING EVENTS USING UNSUPERVISED CLUSTERING
European Patent Office | 2023
|