Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

A Graph Convolutional Network for Active Distribution System Anomaly Detection Considering Measurement Spatial-Temporal Correlations

Conference ·

The accuracy of distribution system state estimation may be significantly impacted by the existence of bad measure-ments and unexpected topology errors. This paper proposes a data-driven Graph Convolutional Network (GCN) for anomaly detection, including bad measurements and topology change events. Compared to many existing machine learning approaches, the proposed approach embeds both spatial-temporal measure-ment correlations, which allows us to detect and distinguish different anomalies. Numerical results carried out on the IEEE 37-node system demonstrate that the proposed-based method can obtain high accuracy in detecting bad data and topology changes as compared to other approaches, even in the presence of high PV penetrations.

Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office; Eversource Energy
DOE Contract Number:
AC36-08GO28308
OSTI ID:
2281824
Report Number(s):
NREL/CP-5D00-88579; MainId:89358; UUID:5c06f3ff-2e3c-4a5d-8ef1-8d4b1f916071; MainAdminID:71578
Resource Relation:
Conference: Presented at the North American Power Symposium, 15-17 November 2023, Asheville, North Carolina
Country of Publication:
United States
Language:
English

References (15)

Multi-fidelity Gaussian Process for Distribution System Voltage Probabilistic Estimation with PVs conference November 2022
Denoising and Bad Data Detection in Distribution Phasor Measurements using Filtering, Clustering and Koopman Mode Analysis conference October 2021
Bad data detection, identification and correction in distribution system state estimation based on PMUs journal October 2021
Spatio-Temporal Correlation Analysis of Online Monitoring Data for Anomaly Detection and Location in Distribution Networks journal March 2020
Bad Data Detection Algorithm for PMU Based on Spectral Clustering journal January 2020
Improving the Accuracy of Bus Load Forecasting by a Two-Stage Bad Data Identification Method journal July 2014
Bayesian Inference Approach for Information Fusion in Distribution System State Estimation journal January 2022
Effects of Measurements and Pseudomeasurements Correlation in Distribution System State Estimation journal December 2014
Image super-resolution via channel attention and spatial graph convolutional network journal April 2021
Community-based anomaly detection in evolutionary networks journal October 2011
Simultaneous Robust State Estimation, Topology Error Processing, and Outage Detection for Unbalanced Distribution Systems journal May 2023
Dynamic state estimation including anomaly detection and identification for power systems journal January 1982
Placement of PMUs to Enable Bad Data Detection in State Estimation journal November 2006
Doubly-fed Deep Learning Method for Bad Data Identification in Linear State Estimation journal January 2020
Ensemble-Based Algorithm for Synchrophasor Data Anomaly Detection journal May 2019