A new fault-tolerance framework for grid computing

Article type: Research Article

Authors: Derbal, Youcef

Affiliations: School of Information Technology Management, Ryerson University, 350 Victoria Street, Toronto, ON, M5B 2K3, Canada. Tel.: +1 416 979 5000 x7918; E-mail: [email protected]

Abstract: Fault detection and propagation in a computational grid requires a comprehensive framework that takes in consideration the various grid environmental conditions such as the asynchronous nature of communication and the uncertainty on the disseminated fault information. The paper presents a fault-tolerance framework that provides the necessary models to manage the local faulty behavior associated with the operation of hosted services. The framework includes a quantification mechanism of the fault vulnerability of grid nodes and their hosted services. The resulting measures of fault vulnerability are globally disseminated to enable the synthesis of decentralized fault-tolerant decision making strategies.

Keywords: Computational grid, fault-tolerance, fault detector, reliability, service request

DOI: 10.3233/MGS-2006-2203

Journal: Multiagent and Grid Systems, vol. 2, no. 2, pp. 115-133, 2006