.png){kind=icon}
.png){kind=icon}
Return
A Real Time Event Detection, Classification and Localization Using Synchrophasor Data
.png){kind=icon}
OA
AI
DOI：10.1109/TPWRS.2020.2986019.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
With an increasing number of extreme events, grid components and complexity, more alarms are being observed in the power grid control centers. Operators in the control center need to monitor and analyze these alarms to take suitable control actions, if needed, to ensure the system's reliability, stability, security, and resiliency. Although existing alarm and event processing tools help in monitoring and decision making, synchrophasor data along with the topology and component location information can be used in detecting, classifying and locating the event, which is the focus of this work. Phasor Measurement Unit's (PMU's) data quality issue is also addressed before using data for event analysis. The developed algorithms include statistic, clustering, and Maximum Likelihood Criterion (MLE) based anomaly detection, Density-based spatial clustering of applications with noise (DBSCAN) for event detection and physics-based rule/ decision tree for event classification. Further, topology information, statistical techniques, and graph search algorithms are used for event localization. Developed algorithms have been validated with satisfactory results for IEEE 14 bus and 39 Bus as well as with real PMU data from the western US interconnection (WECC).
Keywords:
Phasor measurement units
Event detection
Detectors
Anomaly detection
Microsoft Windows
Clustering algorithms
Maximum likelihood estimation
PMU
anomaly detection
event detection
DBSCAN
MLE
graph theory
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.2
Papers:
1.1W
Citations:
5.0W