Dynamic fault tolerant scheduling policy for workflows in Grid computing

摘要

More and more complex scientific workflows are now executed on computational Grids. In addition to the challenges of managing and scheduling resources, reliable challenges arise because the Grid infrastructure is unreliable. Current Grid systems mainly exploit fault tolerance mechanisms to guarantee the dependable workflow execution, which wastes system resources. In this paper, we have chosen an alternative way for reliable workflow scheduling, schedule tasks replicas to resources with the objective of meeting a reliability requirement, in such a way that all tasks are replicated with less resource consumption, using Passive Dynamic Replication of Tasks method namely (PDRT).