Investigating Anomalies in Compute Clusters: An Unsupervised Learning Approach

Conference · Wed Nov 01 04:00:00 EDT 2023

DOI:https://doi.org/10.2172/2439937· OSTI ID:2439937

Lu, Yiyang ^[1]; Ren, Jie ^[1]; Alanazi, Yasir ^[2]; Mohammed, Ahmed ^[2]; McSpadden, Diana ^[2]; Hild, Laura ^[2]; Jones, Mark ^[2]; Moore, Wesley ^[2]; Schram, Malachi ^[2]; Hess, Bryan ^[2]; Smirni, Evgenia ^[1]

---

1. College of William and Mary, Williamsburg, VA (United States)
2. Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States)

As compute clusters continue to grow in scale and complexity, the frequency of detected anomalies in their operation significantly increases. Timely detection of anomalous events is vital to maintain system efficiency and availability. This study presents an attentionbased graph neural network (GNN) for detecting anomalies in clusters at the compute node level and for providing detailed root cause analysis. We show the effectiveness of attention-based GNNs to accurately detect and localize anomalies on real-world datasets.

• Research Organization: Thomas Jefferson National Accelerator Facility, Newport News, VA (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Nuclear Physics (NP)
• DOE Contract Number: AC05-06OR23177
• OSTI ID: 2439937
• Report Number(s): JLAB-CST-23-4174; DOE/OR/23177-7647
• Country of Publication: United States
• Language: English