Description

Abstract:

Fault-tolerant scheduling is an important issue for computational grid systems, as grids typically

consist of strongly varying and geographically distributed resources. The main scheduling strategy

of most fault-tolerant scheduling systems depends on the response time and fault index when

selecting a resource to execute a certain job. In this paper, a scheduling system is presented that

dep ends on a new factor called scheduling indicator in selecting resources. This factor comprises

of the response time and the failure rate of grid resources. Whenever a grid scheduler has jobs to

schedule on grid resources, it uses the scheduling indicator to generate the scheduling decisions.

The main scheduling strategy of the system is to select resources that have the lowest tendency to

fail. Extensive simulation experiments are conducted to quantify the performance of the pro-posed

system.