Quantifying event correlations for proactive failure management in networked computing systems

Networked computing systems continue to grow in scale and in the complexity of their components and interactions. Component failures become norms instead of exceptions in these environments. Moreover, failure events exhibit strong correlations in the time and space domains. In this paper, we develop...

Full description

Saved in:
Bibliographic Details
Published in:Journal of parallel and distributed computing Vol. 70; no. 11; pp. 1100 - 1109
Main Authors: Fu, Song, Xu, Cheng-Zhong
Format: Journal Article
Language:English
Published: Amsterdam Elsevier Inc 01.11.2010
Elsevier
Subjects:
Applied sciences
Associations
Autonomic management
Clusters
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Correlation
Dynamical systems
Dynamics
Exact sciences and technology
Failure
Failure characterization
Mathematical models
Networked computing systems
On-line systems
Online
Software
Spatial correlation
System availability
Temporal correlation
Autonomic management
Failure characterization
Networked computing systems
Temporal correlation
System availability
Spatial correlation
Availability
Autonomous system
Production system
Probabilistic approach
Grid
Interconnected power system
Time correlation
Network management
Distributed system
Distributed computing
Modeling
Reactive system
Model matching
Covariance
Coalition
Breakdown
Proactive service
ISSN:0743-7315, 1096-0848
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Networked computing systems continue to grow in scale and in the complexity of their components and interactions. Component failures become norms instead of exceptions in these environments. Moreover, failure events exhibit strong correlations in the time and space domains. In this paper, we develop a spherical covariance model with an adjustable timescale parameter to quantify the temporal correlation and a stochastic model to characterize spatial correlation. The models are further extended to take into account the information of application allocation to discover more correlations among failure instances. We cluster failure events based on their correlations and predict their future occurrences. Experimental results on a production coalition system, the Wayne State Computational Grid, show the offline and online predictions made by our predicting system can forecast 72.7–85.3% of the failure occurrences and capture failure correlations in a cluster coalition environment. ► Temporal and spatial failure correlations are modeled and quantified to characterize failure dynamics. ► A prediction mechanism that explores failure correlations is proposed to forecast future failure occurrences. ► High prediction accuracy is achieved in offline and online predictions on a production networked computer system.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0743-7315
1096-0848
DOI:10.1016/j.jpdc.2010.06.010