An Availability Model of a Virtual TMR System with Applications in Cloud/Cluster Computing

Three important factors in dependable computing are cost, error correction and high availability. In this paper we will focus on assessing a proposed model that encapsulates all three important factors and a virtual architecture that can be implemented in the IaaS layer of cloud computing. The proposed model will be assessed against a popular existing architecture (Triple Modular Redundant System TMR) and the availability analysis done with Fault-Trees combined with Markov Chains. These experiments will demonstrate that the virtualization of the TMR system using the architecture that we have proposed, will achieve almost the same level of availability/reliability and cost, along with the inherent advantages of virtual systems. Advantages include faster system restart, efficient use of resources and migration.