Abstract
Real-time anomaly detection is a critical monitoring task for power systems. Most studies of power network detection fail to identify small fault signals or disturbances that might lead to damages or system-wide blackout. This work presents a methodology for analyzing high-dimensional PMU data and detecting early events for large-scale power systems in a non-Gaussian noise environment. Also, spatio-temporal correlations of PMU data are explored and determined by the factor model for anomaly detection. Based on random matrix theory, the factor model monitors the variation of spatio-temporal correlations in PMU data and estimates the number of dynamic factors. Kullback-Leibler Divergence is employed to measure the deviation between two spectral distributions: the empirical spectral distribution of the covariance matrix of residuals from online monitoring data and its theoretical spectral distribution determined by the factor model. Using IEEE 57-bus, IEEE 118-bus, and Polish 2383-bus systems, three different case studies demonstrate that the proposed method is more effective in identifying early-stage anomalies in high-dimensional PMU data collected from large-scale power networks. Performance evaluations validate that this method is sensitive and robust to small fault signals compared with other statistical approaches. The proposed method is a data-driven approach that doesn’t require any prior knowledge of the topology of power networks.
Highlights
Anomalies in power systems include deviations from expected measurements resulting from grid faults, such as load fluctuations and system oscillations
fault-to-noise ratio (FNR) is defined as: FNR = 10 × log ƒ where #\ and #ƒ are estimated variances. #\ is related to changes due to fault occurrence, #ƒ is estimated by phasor measurement unit (PMU) data collected from a fault-free environment
This paper proposes the FKLD method to analyze high-dimensional PMU data and detect early fault events in a non-Gaussian noise environment
Summary
Anomalies in power systems include deviations from expected measurements resulting from grid faults, such as load fluctuations and system oscillations. A deep learning scheme has been successfully applied to anomaly detection for large-scale power systems, including long short-term memory (LSTM) [10, 11], graph neural networks (GNN) [12], deep neural network (DNN) [13] Calculations of these methods are growing exponentially with the depth and complexity of networks. The factor model is used to analyze high-dimensional PMU data and study the spatio-temporal correlation of power systems. Under the random matrix theory framework, this paper proposes a factor model-based KLD method (FKLD) to detect early fault events in large-scale power systems. The main contributions of this paper are as follows: 1) Propose an early anomaly detection method for large-scale power systems based on the KLD technique. 2) The method in this paper captures the correlation properties of high-dimensional power grid data by using factor model analysis.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: American Journal of Electrical Power and Energy Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
