Authors: S. Jaya Nirmala; N. Tajunnisha; S. Mary Saira Bhanu
Addresses: Department of Computer Science and Engineering, National Institute of Technology, Tiruchirappalli, Tamilnadu, India ' Intel Technologies, Bengaluru, Karnataka, India ' Department of Computer Science and Engineering, National Institute of Technology, Tiruchirappalli, Tamilnadu, India
Abstract: Resource provisioning is a very important and challenging task in cloud computing. The techniques employed for resource provisioning needs to avoid under-provisioning and over-provisioning of resources. It also needs to ensure the cloud providers that the required SLAs are met. In this paper, an efficient resource provisioning and scheduling algorithm is proposed to schedule service requests in IaaS clouds. Service requests in the cloud are of four types: immediate, best-effort, advance reservation and deadline sensitive. In the proposed work, advance reservation requests with flexible start times (flexible advance reservation requests) are considered. The experiments are conducted in a cloud environment developed using OpenNebula. The proposed algorithm is compared with the existing algorithms of Haizea and SAB. The experimental results indicate that the proposed algorithm gives better request acceptance rate and reduced resource fragmentation than the existing ones.
Keywords: cloud computing; service provisioning; resource provisioning; scheduling; virtual machines; flexible advance reservation; request acceptance rate; OpenNebula; resource fragmentation; IaaS cloud; infrastructure as a service; SLAs; service level agreements.
International Journal of Big Data Intelligence, 2016 Vol.3 No.3, pp.154 - 162
Received: 21 May 2015
Accepted: 27 Jul 2015
Published online: 10 Aug 2016 *