Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN
This addresses the need for real-time, unsupervised monitoring of power grid anomalies without labeled data, offering a practical solution for grid resilience.
The paper tackles the problem of unsupervised anomaly detection in power grid synchrophasor data by introducing T-BiGAN, a framework combining Transformers and BiGAN, achieving an ROC-AUC of 0.95 and average precision of 0.996 on a hardware-in-the-loop benchmark.
Ensuring power grid resilience requires the timely and unsupervised detection of anomalies in synchrophasor data streams. We introduce T-BiGAN, a novel framework that integrates window-attention Transformers within a bidirectional Generative Adversarial Network (BiGAN) to address this challenge. Its self-attention encoder-decoder architecture captures complex spatio-temporal dependencies across the grid, while a joint discriminator enforces cycle consistency to align the learned latent space with the true data distribution. Anomalies are flagged in real-time using an adaptive score that combines reconstruction error, latent space drift, and discriminator confidence. Evaluated on a realistic hardware-in-the-loop PMU benchmark, T-BiGAN achieves an ROC-AUC of 0.95 and an average precision of 0.996, significantly outperforming leading supervised and unsupervised methods. It shows particular strength in detecting subtle frequency and voltage deviations, demonstrating its practical value for live, wide-area monitoring without relying on manually labeled fault data.