Secure Requirement Prioritized Grid Scheduling Model

Abstract

Grid computing is a high performance computing environment to solve larger scale computational demands. Grid computing contains resource management, task scheduling, security problems, information management and so on. Task scheduling in an important aspect of distributed computing. As grid computing is a form of distributed computing with heterogeneous resources working in a shared environment with no central control. The main aim of Grid scheduling is to increase the system throughput and to satisfy the job requirements from the available resources. This work proposes a secure requirement (SRP) prioritized task-scheduling algorithm for grid computing. This algorithm is based on scheduling the jobs based on the resource requirement of the jobs which considers the memory requirement as the resource requirement of the jobs. It is named as the secure requirement prioritized (SRP) scheduling algorithm as the jobs memory requirement is passed to scheduler in encrypted form. It is compared with one of the widely used grid scheduling algorithm MinMin and has been tested in simulated grid environment. The experimental results showed a significant improvement in terms of makespan and system utilization.