Research Posters Archive

Investigating Anomalies in Compute Clusters: An Unsupervised Learning Approach

Authors: Yiyang Lu and Jie Ren (College of William & Mary); Yasir Alanazi, Ahmed Mohammed, Diana McSpadden, Laura Hild, Mark Jones, Wesley Moore, Malachi Schram, and Bryan Hess (Thomas Jefferson National Accelerator Facility); and Evgenia Smirni (College of William & Mary)

Abstract: As compute clusters used for running batch jobs continue to grow in scale and complexity, the frequency of anomalies significantly increases. Timely detection of anomalous events has become vital to maintain system efficiency and availability. Our study presents an attention-based graph neural network (GNN) to detect anomalies in clusters at the compute node level and provide detailed root cause analysis to pinpoint issues. Evaluating on real-world datasets, attention-based GNN shows its ability to accurately detect and localize anomalies.

Best Poster Finalist (BP): no

Poster: PDF
Poster summary: PDF


Back to Poster Archive Listing