Prodigy: Towards Unsupervised Anomaly Detection in Production HPC Systems
Burak Aksar, Efe Sencan, Benjamin Schwaller, Omar Aaziz, Vitus J. Leung, Jim Brandt, Brian Kulis, Manuel Egele, Ayse K. Coskun
Abstract
Performance variations caused by anomalies in modern High Performance Computing (HPC) systems lead to decreased efficiency, impaired application performance, and increased operational costs. While machine learning (ML)-based frameworks for automated anomaly detection (often based on time series telemetry data) are gaining popularity in the literature, practical deployment challenges are often overlooked. Some ML-based frameworks require extensive customization, while others need a rich set of labeled samples, none of which are feasible for a production HPC system.
Topics & Concepts
Anomaly detectionComputer scienceProduction (economics)Anomaly (physics)Artificial intelligenceCondensed matter physicsPhysicsMacroeconomicsEconomicsAnomaly Detection Techniques and ApplicationsScientific Computing and Data ManagementBig Data and Digital Economy