Log Anomaly Detection on EuXFEL Nodes

Publikationstyp
Preprint
Publikationsdatum
2023-10-13
Author
Sulc, Antonin 
Eichler, Annika 
Control Systems E-14 
Wilksen, Tim
TORE-URI
https://hdl.handle.net/11420/45106
Citation
arXiv: 2310.08951 (2023)
Publisher DOI
10.48550/arXiv.2310.08951
ArXiv ID
2310.08951v1
This article introduces a method to detect anomalies in the log data generated by control system nodes at the European XFEL accelerator. The primary aim of this proposed method is to provide operators a comprehensive understanding of the availability, status, and problems specific to each node. This information is vital for ensuring the smooth operation. The sequential nature of logs and the absence of a rich text corpus that is specific to our nodes poses significant limitations for traditional and learning-based approaches for anomaly detection. To overcome this limitation, we propose a method that uses word embedding and models individual nodes as a sequence of these vectors that commonly co-occur, using a Hidden Markov Model (HMM). We score individual log entries by computing a probability ratio between the probability of the full log sequence including the new entry and the probability of just the previous log entries, without the new entry. This ratio indicates how probable the sequence becomes when the new entry is added. The proposed approach can detect anomalies by scoring and ranking log entries from EuXFEL nodes where entries that receive high scores are potential anomalies that do not fit the routine of the node. This method provides a warning system to alert operators about these irregular log events that may indicate issues.
Schlagworte
cs.CR