A Deep Learning Approach to Anomaly Sequence Detection for High-Resolution Monitoring of Power Systems

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.

Automated summary

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.