Competitive proportional resource allocation policy for computational grid

Abstract

This paper presents a competitive proportional resource allocation in computational grid. A system model is described that allows agents representing various grid resources, which owned by different real world enterprises, to coordinate their resource allocation decisions without assuming a priori cooperation. The grid task agents buy resources to complete tasks. Grid resource agents charge the task agents for the amount of resource capacity allocated. Two types of optimization problems related to grid task agent are proposed. Given grid resource agent’s pricing policy, the task agent optimization problem is to complete its job as quickly as possible when spending the least possible amount of money. Given specified amount of time to complete jobs, the task agent optimization problem is to minimize the cost accrued. This paper provides a price-directed proportional resource allocation algorithm for solving the grid task agent resource allocation problem. Experiments are made to compare the performance of the price-directed resource allocation with conventional Round-Robin allocation. The results of experiment show the price-directed allocation has better performance than usual Round-Robin allocation.