Optimizing the Execution Time of the SLA-Based Workflow in the Grid with Parallel Processing Technology

Abstract

Service Level Agreements (SLAs) is currently one of the major research topics in Grid Computing. Among many system components for the supporting of SLA-aware Gridbased workflow, the SLA mapping module receives important positions. Optimizing execution time is an important task of the mapping module as it helps in finding out a feasible solution when the Grid is busy or by eliminating the negative effects of the error. With the previously proposed algorithm for optimizing the execution time of the workflow, the mapping module may, when many requests come in a short period of time, become the bottleneck of the system. This paper presents a parallel mapping algorithm for optimizing the execution time of the workflow, which can cope with the problem. Performance measurements deliver evaluation results on the quality of the method.