Title: Resource co-allocation framework based on hybrid gaming model in grid environments

Authors: Peng Xiao; Dongbo Liu; Xilong Qu

Addresses: School of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, China ' School of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, China ' School of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, China

Abstract: Resource co-allocation is a fundamental infrastructure to aggregate heterogeneous and distributed resources in grid environments. Although it has been widely investigated, co-allocation under multiple QoS constraints still remains an open issue. To address the issue of resource co-allocation with constraints to budget and deadline, a game-based co-allocation framework is proposed. This framework optimises resources deployment and prices scheme by a three-side co-allocation mechanism; meanwhile, it provides quantitative deadline guarantees for applications by applying queuing system to model the working of grid resources. The validity and solutions of the framework are presented theoretically. Experimental results show that the proposed framework can significantly reduce the deadline missing rate and resource costs for those applications with constraints to cost and deadline.

Keywords: grid computing; resource co-allocation; resource allocation; utility computing; computing economy; gaming theory; QoS; quality of service; queuing systems; modelling; grid resources.

DOI: 10.1504/IJGUC.2013.054491

International Journal of Grid and Utility Computing, 2013 Vol.4 No.1, pp.60 - 69

Received: 06 Jan 2012
Accepted: 09 May 2012
Published online: 18 Sep 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article