Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN

arXiv:2509.25612v2 Announce Type: replace-cross Abstract: 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.

Related

• Enabling Predictive Maintenance in District Heating Substations: A Labelled Dataset and Fault Detection Evaluation Framework based on Service Data
• DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs
• GTCN-G: A Residual Graph-Temporal Fusion Network for Imbalanced Intrusion Detection
• Matrix Profile for Anomaly Detection on Multidimensional Time Series

Source: arXiv cs.AI | 2026-04-14