Authors: Peng Xiao; Zhihang Tang
Addresses: School of Computer and Communication, Hunan Institute of Engineering, Fu-Xing East-Road, Xiangtan 411104, China ' School of Computer and Communication, Hunan Institute of Engineering, Fu-Xing East-Road, Xiangtan 411104, China
Abstract: In cloud platforms, resource pricing is a challenging issue when multiple resources should be efficiently allocated to multiple users. To address this issue, a hybrid gaming-based pricing model is proposed to overcome the demerits of existing price mechanisms in terms of efficiency and fairness. In the proposed pricing model, virtual resource configuration and provision are defined as a two-phrase gaming procedure, in which cooperative gaming model is applied to optimise the resource benefits, and a non-cooperative gaming model is used to balance the user's costs and provider's benefits. The validity and solution of the proposed price model are presented theoretically, and the experimental results indicate that the hybrid gaming model can significantly improve the price negotiation efficiency when a bundle of resources are negotiated concurrently, which in turn reduce the application execution latency caused by conventional price negotiation mechanisms.
Keywords: cloud computing; economic computing; quality of service; QoS; game theory; resource pricing models; cloud platforms; efficiency; fairness; price negotiation; application execution latency.
International Journal of Communication Networks and Distributed Systems, 2015 Vol.14 No.3, pp.256 - 271
Received: 11 Sep 2013
Accepted: 18 Jul 2014
Published online: 30 Mar 2015 *