Emulating enterprise network environments for fast transition to software-defined networking

Abstract

Software Defined Networks are emerging as a new paradigm in data networks. While most corporate networks and datacenters (like Google, Cisco, Big Switch, etc.) are already on OpenFlow protocol utilizing SDN, a number of emulation platforms have emerged, such as Mininet. In this paper we propose an emulated enterprise/university Software-Defined network using Python and Mininet; we have also built a conventional network using ns-3 with the same number of nodes, topology, etc. Our tests show that our proposed network model outperforms the conventional/existing model in parameters like minimum and mean delay for ICMP and HTTP packets, as well as minimum and maximum convergence time, and therefore are a best solution to transition corporate networks with hundreds or more nodes, mainly due to the fast propagation of routing policies from the central controller.