A Utility-Based Two Level Market Solution for Optimal Resource Allocation in Computational Grid

  • Authors:
  • Chunlin Li

  • Affiliations:
  • Wuhan University of Technology

  • Venue:
  • ICPP '05 Proceedings of the 2005 International Conference on Parallel Processing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper presents a market oriented resource allocation strategy for grid resource. The proposed model uses the utility functions for calculating the utility of a resource allocation. This allows the integration of different optimization objectives into allocation process. This paper is target to solve above issues by using utility-based optimization scheme. We decompose the optimization problem into two levels of subproblems so that the computational complexity is reduced. Two market levels converge to its optimal points; a globally optimal point is achieved. Total user benefit of the computational grid is maximized when the equilibrium prices are obtained through the service market level optimization and resource market level optimization. The economic model is the basis of an iterative algorithm that, given a finite set of requests, is used to perform optimal resource allocation. The experiments show that scheduling based on pricing directed resource allocation involves less overhead and leads to more efficient resource allocation than conventional round robin scheduling.