Auction-Based Resource Allocation in Computational Grids

Abstract

Auction techniques have been becoming the key methods in grid resource allocation. In this paper, we propose the multi-attribute reverse auction models for computational grid resource based on the designed satisfaction degree function. The fairness is also introduced into the models and protocols to match the reality. Two auction-based protocols are presented, i.e., the offline multi-attribute auction-based protocol and the on-line multi-attribute auction-based protocol. The goal is to help the resource user make multi-attribute decisions with complete information or incomplete information. Results from simulation experiments show that these two protocols can achieve market efficiency and fairness in most instances.