Performance analysis of Cloud Computing Centers Hamzeh Khazaei 1 , Jelena Miˇ si´ c 2 , and Vojislav B. Miˇ si´ c 2 1 University of Manitoba, Winnipeg, Manitoba, Canada, hamzehk@cs.umanitoba.ca, WWW home page: http://www.cs.umanitoba.ca/ ~ hamzehk 2 Ryerson University, Toronto, Ontario, Canada Abstract. Cloud computing is a computing paradigm in which differ- ent computing resources, including infrastructure, hardware platforms, and software applications, are made accessible to remote users as ser- vices. Successful provision of infrastructure-as-a-service (IaaS) and, con- sequently, widespread adoption of cloud computing necessitates accurate performance evaluation that allows service providers to dimension their resources in order to fulfil the service level agreements with their cus- tomers. In this paper, we describe an analytical model for performance evaluation of cloud server farms, and demonstrate the manner in which important performance indicators such as request waiting time and server utilization may be assessed with sufficient accuracy. Key words: cloud computing, performance analysis, M/G/m queuing system, response time 1 Introduction Significant innovations in virtualization and distributed computing, as well as improved access to high-speed Internet, have accelerated interest in cloud com- puting [15]. Cloud computing is a general term for system architectures that involves delivering hosted services over the Internet. These services are broadly divided into three categories: Infrastructure-as-a-Service (IaaS), which includes equipment such as hardware, storage, servers, and networking components are made accessible over the Internet); Platform-as-a-Service (PaaS), which includes computing platforms—hardware with operating systems, virtualized servers, and the like; and Software-as-a-Service (SaaS), which includes sofware applications and other hosted services [11]. A cloud service differs from traditional hosting in three principal aspects. First, it is provided on demand, typically by the minute or the hour; second, it is elastic since the user can have as much or as little of a service as they want at any given time; and third, the service is fully managed by the provider – user needs little more than computer and Internet access. Cloud customers pay only for the services they use by means of a customized service level agreement (SLA), which is a contract negotiated and agreed between a cus- tomer and a service provider: the service provider is required to execute service