Designing a Dynamic Job Scheduling Strategy for Computational Grid

Abstract

Grid computing is an emerging computing infrastructure which is a collection of computing resources connected by a network, to form a distributed system used for solving complex problems. This system tries to solve these problems or applications by allocating the idle computing resources over a network or the internet commonly known as the computational grid. In Computational Grid main emphasis is given on performance in terms of Execution time. Resources in Computational Grid are heterogeneous and are owned and managed by other organizations with different access policies. This can be achieved by Scheduling. Scheduling algorithms increases performance by reducing the execution time so Scheduling is an important issue. Scheduling is the decision process by which application components are assigned to available resources to optimize various performance metrics. Hence in this paper we have specifically focused on improving Computational grid performance in terms of Execution time. We have first presented a concept of Scheduling in Computational grid. Followed by detailed analysis of two scheduling strategies simulated by GridSim. Next we have proposed a dynamic Scheduling strategy based on this analysis. We are sure that this will improve the performance by reducing execution time.