Anomaly Detection and Localization via Graph Learning

Phasor measurement units (PMUs) are being installed at an unprecedented rate on power systems, offering unique situation awareness capability. This paper presents a graph learning-based method for detecting and locating anomalies using PMU data. In this method, the graph learning technique is used t...

Full description

Saved in:
Bibliographic Details
Main Authors: Olabode Amusan, Di Wu
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/6/1475
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205126595182592
author Olabode Amusan
Di Wu
author_facet Olabode Amusan
Di Wu
author_sort Olabode Amusan
collection DOAJ
description Phasor measurement units (PMUs) are being installed at an unprecedented rate on power systems, offering unique situation awareness capability. This paper presents a graph learning-based method for detecting and locating anomalies using PMU data. In this method, the graph learning technique is used to characterize the spatiotemporal relationship of distributed PMU data by constructing a spatiotemporal graph. Then, graph analysis is used to detect and locate anomalies by evaluating the global connectivity of spatiotemporal graphs at different times and the local connectivity of nodes in the relevant spatiotemporal graphs. The proposed method was verified using the IEEE-39 bus system and realistic PMU data. The method accurately identifies anomalies with an accuracy of 97% with a precision and recall of 80% and 100%, respectively. The results show the superiority and robustness of the proposed method as a powerful tool for detecting and locating anomalies using PMU data.
format Article
id doaj-art-a95e160e0f524c48aa2d8097e236c35a
institution OA Journals
issn 1996-1073
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-a95e160e0f524c48aa2d8097e236c35a2025-08-20T02:11:09ZengMDPI AGEnergies1996-10732025-03-01186147510.3390/en18061475Anomaly Detection and Localization via Graph LearningOlabode Amusan0Di Wu1Department of Electrical and Computer Engineering, North Dakota State University, Fargo, ND 58105, USADepartment of Electrical and Computer Engineering, North Dakota State University, Fargo, ND 58105, USAPhasor measurement units (PMUs) are being installed at an unprecedented rate on power systems, offering unique situation awareness capability. This paper presents a graph learning-based method for detecting and locating anomalies using PMU data. In this method, the graph learning technique is used to characterize the spatiotemporal relationship of distributed PMU data by constructing a spatiotemporal graph. Then, graph analysis is used to detect and locate anomalies by evaluating the global connectivity of spatiotemporal graphs at different times and the local connectivity of nodes in the relevant spatiotemporal graphs. The proposed method was verified using the IEEE-39 bus system and realistic PMU data. The method accurately identifies anomalies with an accuracy of 97% with a precision and recall of 80% and 100%, respectively. The results show the superiority and robustness of the proposed method as a powerful tool for detecting and locating anomalies using PMU data.https://www.mdpi.com/1996-1073/18/6/1475phasor measurement unitgraph learningspatiotemporal relationshipanomaly detectionanomaly localization
spellingShingle Olabode Amusan
Di Wu
Anomaly Detection and Localization via Graph Learning
Energies
phasor measurement unit
graph learning
spatiotemporal relationship
anomaly detection
anomaly localization
title Anomaly Detection and Localization via Graph Learning
title_full Anomaly Detection and Localization via Graph Learning
title_fullStr Anomaly Detection and Localization via Graph Learning
title_full_unstemmed Anomaly Detection and Localization via Graph Learning
title_short Anomaly Detection and Localization via Graph Learning
title_sort anomaly detection and localization via graph learning
topic phasor measurement unit
graph learning
spatiotemporal relationship
anomaly detection
anomaly localization
url https://www.mdpi.com/1996-1073/18/6/1475
work_keys_str_mv AT olabodeamusan anomalydetectionandlocalizationviagraphlearning
AT diwu anomalydetectionandlocalizationviagraphlearning