Probabilistic versus possibilistic risk assessment models for optimal service level agreements in grid computing

Authors:
Christer Carlsson;Robert Fullér
Affiliations:
IAMSR, Åbo Akademi University, Turku, Finland 20520;IAMSR, Åbo Akademi University, Turku, Finland 20520 and Institute of Intelligent Engineering Systems, John von Neumann Faculty of Informatics Óbuda University, Budapest, Hungary 1034
Venue:
Information Systems and e-Business Management
Year:
2013

Citing 9
Cited 0

Fuzzy least squares

Information Sciences: an International Journal
Fuzzy Reasoning in Decision Making and Optimization

Fuzzy Reasoning in Decision Making and Optimization
Monte Carlo Statistical Methods (Springer Texts in Statistics)

Monte Carlo Statistical Methods (Springer Texts in Statistics)
A large-scale study of failures in high-performance computing systems

DSN '06 Proceedings of the International Conference on Dependable Systems and Networks
Fuzzy nonparametric regression based on local linear smoothing technique

Information Sciences: an International Journal
Distributed and Heuristic Policy-Based Resource Management System for Large-Scale Grids

AIMS '07 Proceedings of the 1st international conference on Autonomous Infrastructure, Management and Security: Inter-Domain Management
On the dynamic resource availability in grids

GRID '07 Proceedings of the 8th IEEE/ACM International Conference on Grid Computing
Cloud computing - The business perspective

Decision Support Systems
Architectural Requirements for Cloud Computing Systems: An Enterprise Cloud Approach

Journal of Grid Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a probabilistic and a possibilistic model for assessing the risk of a service level agreement for a computing task in a cluster/grid environment. These models can also be applied to cloud computing. Using the predictive probabilistic approach we develop a framework for resource management in grid computing, and by introducing an upper limit for the number of failures we approximate the probability that a particular computing task is successful. In the predictive possibility model we estimate the possibility distribution of the future number of node failures by a fuzzy nonparametric regression technique. Then the resource provider can use the probabilistic or the possibilistic model to get alternative risk assessments.