Journal
IEEE TRANSACTIONS ON POWER SYSTEMS
Volume 38, Issue 1, Pages 4-13Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRS.2022.3168529
Keywords
System event detection; continuous point-on-wave (CPOW) measurements; bad-data detection; distributed anomaly detection; generative adversary networks (GAN)
Categories
Ask authors/readers for more resources
A deep learning approach is proposed for detecting data and system anomalies using high-resolution continuous point-on-wave (CPOW) or phasor measurements. The proposed approach assumes unknown temporal dependencies and probability distributions for both the anomaly and anomaly-free measurement models. By applying a generative adversarial network, the approach transforms anomaly-free observations into uniform independent and identically distributed sequences for uniformity test-based anomaly detection at the sensor level. A distributed detection scheme is also proposed to combine sensor-level detections for more reliable results. Numerical results demonstrate significant improvement compared to state-of-the-art solutions for various bad-data cases using real and synthetic CPOW and PMU data sets.
A deep learning approach is proposed to detect data and system anomalies using high-resolution continuous point-on-wave (CPOW) or phasor measurements. Both the anomaly and anomaly-free measurement models are assumed to have unknown temporal dependencies and probability distributions. Historical training samples are assumed for the anomaly-free model, while no training samples are available for the anomaly measurements. By transforming the anomaly-free observations into uniform independent and identically distributed sequences via a generative adversarial network, the proposed approach deploys a uniformity test for anomaly detection at the sensor level. A distributed detection scheme that combines sensor level detections at the control center is also proposed which combines local detections to form more reliable detections. Numerical results demonstrate significant improvement over the state-of-the-art solutions for various bad-data cases using real and synthetic CPOW and PMU data sets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available