Pattern Mining and Anomaly Detection based on Power System Synchrophasor Measurements
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Real-time monitoring of power system dynamics using phasor measurement units (PMUs) data improves situational awareness and system reliability, and helps prevent electric grid blackouts due to early anomaly detection. The study presented in this paper is based on real PMU measurements of the U.S. Western Interconnection system. Given the nonlinear and non-stationary PMU data, we developed a robust anomaly detection framework that uses wavelet-based multi-resolution analysis with moving-window-based outlier detection and anomaly scoring to identify potential PMU events. Furthermore, candidate events were evaluated via spatiotemporal correlation analysis and classified for a better understanding of event types, resulting in successful anomaly detection and classification of the recorded events.
- Research Organization:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 1493762
- Report Number(s):
- PNNL-SA-131425; ISBN 978-0-9981331-1-9
- Journal Information:
- Proceedings of the Annual Hawaii International Conference on System Sciences, Conference: 51st Hawaii International Conference on System Sciences, Waikoloa Village, HI, 3-6 Jan. 2018; ISSN 2572-6862
- Country of Publication:
- United States
- Language:
- English
Similar Records
Online Anomaly Detection Using Machine Learning and HPC for Power System Synchrophasor Measurements
Demonstration of a Novel Synchrophasor-based Situational Awareness System: Wide Area Power System Visualization, On-line Event Replay and Early Warning of Grid Problems