Fault Monitoring with Sequential Matrix Factorization

• Published in: ACM transactions on autonomous and adaptive systems Vol. 10; no. 3; pp. 1 - 25
• Main Authors: Feng, Dawei, Germain, Cecile
• Format: Journal Article
• Language: English
• Published: Association for Computing Machinery (ACM) 01.10.2015
• Subjects: Autonomous; Computer Science; Distributed, Parallel, and Cluster Computing; Dynamical systems; Factorization; Faults; Heuristic; Machine Learning; Monitoring; Policies; Sampling; Machine Learning Additional Key Words and Phrases: Fault Inference; Categories and Subject Descriptors: [Computer systems organization]: Dependable and fault-tolerant systems and networks—Reliability; Matrix Factorization; [Com-puter systems organization]: Dependable and fault-tolerant systems and networks—Availability General Terms: Grids and Clouds; Active Learning ACM Reference Format
• ISSN: 1556-4665; 1556-4703; 1556-4703
• DOI: 10.1145/2797141

For real-world distributed systems, the knowledge component at the core of the MAPE-K loop has to be inferred, as it cannot be realistically assumed to be defined a priori. Accordingly, this paper considers fault monitoring as a latent factors discovery problem. In the context of end-to-end probing, the goal is to devise an efficient sampling policy that makes the best use of a constrained sampling budget. Previous work addresses fault monitoring in a collaborative prediction framework, where the information is a snapshot of the probes outcomes. Here, we take into account the fact that the system dynamically evolves at various time scales. We propose and evaluate Sequential Matrix Factorization (SMF) that exploits both the recent advances in matrix factorization for the instantaneous information and a new sampling heuristics based on historical information. The effectiveness of the SMF approach is exemplified on datasets of increasing difficulty and compared with state of the art history-based or snapshot-based methods. In all cases, strong adaptivity under the specific flavor of active learning is required to unleash the full potential of coupling the most confident and the most uncertain sampling heuristics, which is the cornerstone of SMF.