2012-J-AdmissionControlInClouds-JCSS.pdf

SLA-based Admission Control for a Software-as-a-Service Provider in Cloud Computing Environments Linlin Wu, Saurabh Kumar Garg, and Rajkumar Buyya Cloud Computing and Distributed Systems (CLOUDS) Laboratory Department of Computer Science and Software Engineering The University of Melbourne, Australia {linwu, sgrag, raj}@.au Abstract Software as a Service (SaaS) provides access to applications to end users over the Internet without upfront investment in infrastructure and software. To serve their customers, SaaS providers utilise resources of internal data centres or rent resources from a public Infrastructure as a Service (IaaS) provider. In-house hosting can increase administration and maintenance costs whereas renting from an IaaS provider can impact the service quality due to its variable performance. To overcome these limitations, we propose innovative admission control and scheduling algorithms for SaaS providers to effectively utilise public Cloud resources to maximize profit by minimizing cost and improving customer satisfaction level. Furthermore, we conduct an extensive evaluation study to analyse which solution suits best in which scenario to maximize SaaS providers profit. Simulation results show that our proposed algorithms provide substantial improvement (up to 40% cost saving) over reference ones across all ranges of variation in QoS parameters. Keywords: Cloud computing; Service Level Agreement (SLA); Admission Control; Software as a Service; Scalability of Application Services I. INTRODUCTION Cloud computing has emerged as a new paradigm for delivery of applications, platforms, or computing resources (processing power/bandwidth/storage) to customers in a “pay-as-you-go-model”. The Cloud model is cost-effective because customers pay for their actual usage without upfront costs, and scalable because it can be used more or less depending on the customers? needs. Due to its advantages, Cloud has be