Effect of Scheduling Policies on Resource Allocation in Market Oriented Grid

Abstract

Grid computing is concern with coordinated resource sharing and problem solving in dynamic, multi-institutional virtual organization. The dynamic nature of resources on grids raises the question of an efficient scheduling process, which mainly consist of resource selection and allocation. In grid, users defined their job requirements and compete to access the most efficient and cheapest resources. Traditional resource management systems do not take into account individual requirement and interests. Economics inspired models have shown to efficiently allocate resources and services, scaling up well as they are decentralized. The current research work aims to develop a grid resource allocation method based on market model that makes optimum allocation of resources among the users so as to minimize the user spending and maximize the throughput.