Availability modelling of fault tolerant cloud computing system

Abstract

Cloud management organisation is an imperative part of cloud computing platform and serving as the resource manager for cloud platforms. The multifaceted nature of cloud-management base makes its high availability (HA), a standout amongst the most necessities. Different innovations have been produced to build a consistent quality and availability of cloud administration infrastructure. In any case, little work concentrated on quantitative examination of its accessibility. While this ability accomplishes a developed availability with small fault rates, corporate requests conveyed over the autonomous zones may encounter unique Quality of Service (QoS) because of various physical frameworks. The key target of this paper is to show how the Markov-based model can fulfil the client request. For this reason, a few scenarios of the failure rate of virtual machine's practices, for example, single system failure, multiple system failures, power outage are considered by applying the Markov model. The improved repair strategies of accessibility in various circumstances are also investigated. The Queuing models like Markovian and non-Markovian models are examined using phase type expansion and renewal theory keeping in mind the end goal to sufficiently speak to and to assess. The considered element unwavering quality perspectives if there should be an occurrence of the most part dispersed lifetimes and times to repair.