Progressive recovery for network virtualization after large-scale disasters

Abstract

Network virtualization allows users to build cusomized interconnected storage/computing configurations for their business needs. Today this capability is being widely used to improve the scalability and reliability of cloud-based services, including virtual infrastructures services. However, as more and more business-critical applications migrate to the cloud, disaster recovery is now a major concern. Although some studies have looked at network virtualization design under such scenarios, most have only studied pre-fault protection provisioning. Indeed, there is a pressing need to address post-fault recovery, since physical infrastructure repairs will likely occur in a staged progressive manner due to constraints on available resources. Hence this paper studies progressive recovery design for network virtualization and evaluates several heuristic strategies.