Availability Modelling of Software-Defined Backbone Networks

Abstract

Software-Defined Networking (SDN) promises to improve the programmability and flexibility of networks, but it may also bring new challenges that need to be explored. The main objective of this paper is to present a quantitative assessment of the properties of SDN backbone networks to determine whether they can provide similar availability to the traditional IP backbone networks. To achieve this goal, we have completed the following steps: i) we formalized a two-level availability model that is able to capture the global network connectivity without neglecting the essential details; ii) we proposed Markov models for characterizing the single network elements in both SDN and traditional networks; iii) we carried out an extensive sensitivity analysis of a national and a world-wide backbone networks. The results have highlighted the considerable impact of operational and management (O&M) failures on the overall availability of SDN. High O&M failure intensity may reduce the availability of SDN as much as one order of magnitude compared to traditional networks. Moreover, the results show that the impact of software and hardware failures on the overall availability of SDN can be significantly reduced through proper overprovisioning of the SDN controller(s).