Performability Evaluation of a Cloud-Based Disaster Recovery Solution for IT Environments

An increasing number of organizations are relying on cloud-based Disaster Recovery (DR) solutions to ensure high availability of Information Technology (IT) environments. The flexibility of the cloud resources as well as their pay-as-you-go pricing model has enabled organizations to adopt cost-effective yet reliable DR services. Although cloud-based DR solutions have been used in many organizations, such DR solutions have not been properly assessed in terms of their capacity to meet user demand under disaster occurrences, and the possibility of using the DR cloud for performance improvements. In this work, we present a Stochastic Petri Net (SPN) approach for evaluating cloud-based DR solutions for IT environments. Our approach allows evaluating various performability metrics (e.g., response time, throughput, availability and others), and thus, can help DR coordinators to choose the most appropriate DR solution. A real-world case study is presented to demonstrate the applicability of the approach. We also validate the accuracy of our analytic approach by comparing analytic results with the ones obtained from the cloud simulator CloudSim Plus.