Title: Virtual resource provision based on elastic reservation in cloud computing
Authors: Hong He
Addresses: Department of Computer and Communication, Hunan Institute of Engineering, Hunan Province, Xiangtan City, China
Abstract: In cloud platforms, resource provision service plays an important role to provide flexible and reliable IT-infrastructure for various kinds of applications. Unfortunately, current resource provision service seldom support resource reservation which is generally applied for improving the quality of service (QoS) in high-performance systems. To address this problem, a virtual machine provision policy based on elastic reservation mechanism is proposed. It extends the conventional 'on-demand provision' by introducing a novel elastic reservation mechanism, which allows cloud providers to accept user's over-reservation requests under certain conditions so as to improve the resource effective utilisation and user's satisfaction. Theoretical analysis presents the approach to calculating the probability of elastic reservation, and experimental evaluation validates the effectiveness of the proposed policy and the effects of key parameter on system performance. The results show that comparing with existing techniques, elastic reservation-based resource provision policy can significantly increase the resource effective utilisation, and decrease the 'short-term resource under-provision' caused by excessively reservations.
Keywords: cloud computing; virtual machines; resource provision; quality of service; QoS; virtual resources; elastic reservation; resource underprovision; cloud services.
DOI: 10.1504/IJNVO.2015.069295
International Journal of Networking and Virtual Organisations, 2015 Vol.15 No.1, pp.30 - 47
Received: 08 Nov 2014
Accepted: 23 Jan 2015
Published online: 09 May 2015 *