A Deep Learning Approach to Anomaly Sequence Detection for High-Resolution Monitoring of Power Systems
This work provides a more robust and accurate method for power system operators to detect anomalies in high-resolution monitoring data, which is crucial for maintaining grid stability and reliability.
This paper addresses the challenge of detecting anomalies in high-resolution power system measurements, where both normal and anomalous data exhibit unknown temporal dependencies and probability distributions. The proposed deep learning approach transforms anomaly-free observations into uniform i.i.d. sequences using a GAN, enabling anomaly detection via a uniformity test at the sensor level. The method demonstrates significant improvement over state-of-the-art solutions for various bad-data cases using real and synthetic power system datasets.
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 that 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.