AN EFFICIENT FAULT TOLERANT CLUSTERING FOR SCIENTIFIC WORKFLOW

Abstract

An effective method for the reduction of execution overhead and for improving the computational granularity of scientific workflow tasks that are executing on distributed resources is Task clustering. A job is composed of many tasks and may have a higher risk of suffering from failures than in executing a single task job. In this paper, we direct a hypothetical investigation of the effect of transient failures on the runtime execution of logical work process executions .This system proposes a maximum likelihood estimation-based parameter algorithm which is used for a general task failure modeling framework to model the workflow performance. In this paper, the system proposed here is Dynamic Balanced clustering method which combines the methods of vertical clustering, horizontal clustering and dynamic clustering to reduce the execution overhead for the scientific workflow task execution.