Cloud and network orchestration in SDN data centers: Design principles and performance evaluation

Abstract

The oversubscription of Data Center network links and the high volatility of Virtual Machine (VM) deployments call for a flexible and agile control of Data Center networks, coordinated with computing resource control (i.e., cloud resource management). The Software-Defined Network (SDN) paradigm opens up new opportunities to design convergent resource management systems able to address the provisioning of cloud services while meeting dynamically changing traffic demands of running VMs.This paper presents the architectural design of an SDN-based orchestration system which is able to coordinate the provision of composite cloud and network services while assuring computational requirements as well as a better than best effort VM data delivery. The proposed orchestration system is able to perform VM allocations also based on estimations of switch/link and server loads as result of the synergistic interwork of the following functions: (i) resource selection and composition functions, (ii) coordinated resource configuration and management functions, (iii) monitoring and registration functions of resource status. A set of resource selection and composition strategies and estimation schemes have been also specified.The orchestration process has been thoroughly evaluated through a comprehensive set of simulations that clearly show an increasing acceptance rate of service requests, an improved utilization of network capabilities while effectively preventing significant degradations of the user experience despite the oversubscription of data center network links.