Development and performance analysis of grid resource allocation methods

Abstract

A ‘grid’ is an infrastructure for resource sharing. A computational grid has the potential for solving large scale problems using heterogeneous and distributed resources. Resource allocation is a fundamental issue in achieving high performance on computational grids. Many methods have been developed for grid resource allocation. In this paper, we propose a new grid resource allocation method (modified least cost method) that assigns tasks to computing nodes in a way that is close to the optimum. This paper also proposes a linear programming model for grid scheduling and includes a comparative performance analysis of our proposed resource allocation method with other well known methods. To facilitate the research, a software tool has been developed which produces a comprehensive simulation of a number of grid resource allocation methods. The experimental results show that our proposed method yields improvements in terms of performance and results in a lower computational cost.