quotAN EFFICIENT LOAD BALANCING APPROACH FOR MAX MIN FAIR SCHEDULING OPTIMIZATION IN GRID WORKFLOW ENVIRONMENT quot

Abstract

newline quotA grid is a collection of computing resources that perform tasks. Grid computing is applying the resources of many computers in a network to a single problem. The distributed resources are useful only if the Grid resources are scheduled. The demand for scheduling is to achieve high performance computing. It is difficult to find an optimal resource allocation for specific job that minimizes the schedule length of jobs. It aims to find a suitable allocation of resources for each job. newline newlineA typical problem which arises during this task is the decision of scheduling. It is about an effective utilization of processor to minimize tardiness time of a job, when it is being scheduled. This research addresses the problem by developing a general framework for grid scheduling using fair scheduling algorithm to improve the decision of scheduling. newline newlineMost of the scheduling algorithms concentrate on reduction in the overall makespan and not the fair scheduling of the tasks to the resources. This research shows the importance of fair scheduling in grid environment such that all the tasks get equal amount of time for their execution such that it will not lead to starvation. The load balancing of the available resources in the computational grid is another important factor. newline newlineThis research considers uniform load to be given to the resources. In order to achieve this, load balancing is also applied after scheduling the jobs. This research work also considers the Execution Cost and Bandwidth Cost for the algorithms used here because in the grid environment the resources are geographically distributed. Proposed algorithm is compared with normal scheduling algorithms such as Earliest Deadline First and other Fair Scheduling algorithm like Simple Fair Task Order, Adjusted Fair Task Order and Max Min Fair Scheduling algorithm. With the implementation of this approach the proposed algorithm reaches optimal solution and minimizes the makes pan as well as the Execution cost and Bandwidth cost. newlinequot newline