What Streaming Anomaly Detection Finds (and Misses) in Industrial Time Series

Abstract:EDF relies on continuous monitoring of its power plants to detect anomalies as soon as they occur. Given the absence of a universally optimal streaming method in unsupervised settings, we compare streaming methods with state-of-the-art TSAD models deployed online on a real nuclear power plant dataset. This work also evaluates Automated Anomaly Detection in a streaming context. Results show higher consistency for online TSAD and strong robustness from ensembling strategies.

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2609.39232 [cs.LG]

(or arXiv:2609.39232v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.39232 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.