Network Topology Classification in SDN Ecosystem using Machine Learning

Abstract

To meet the increasing network demands of enterprise environments and data centers, traditional network architectures have been replaced by software-enabled hardware devices for developing agile, dynamic, and programmable networks. Software Defined Networking (SDN) is a new paradigm shift that abstracts network design and infrastructure in the software and then implements it by using software across hardware devices. SDN is used to build and manage the network in a customized way. SDN architecture offers network virtualization, network programmability, and flexibility by decoupling control and data planes which further enriches the network performance. As such, the SDN controller is a tactical control point in SDN. An SDN normally allows data flow control to the switches and/or routers and the rationale of the application's logic for deploying intelligent networks. SDN with Machine Learning (ML) and Artificial Intelligence (AI) techniques build network models, which essentially can take decisions based on self-learning and self-management capabilities. Accurate classification of topology is of prime importance to satisfy future network prerequisites like unpredictable traffic patterns, dynamic scaling, flexibility, and centralized control. The controller needs to have exact information about the topology of the network in order to configure and manage the network. Subsequently, topology classification is an important component of any Software Defined Network architecture. This paper presents the classification of topologies using different supervised ML algorithms. The accuracy obtained from Support Vector Machine (SVM) and Classification and Regression (CART) is 95% and 90% respectively.  The experimental results show that according to the k Cross-Fold validation technique, SVM algorithm has been found to be the most accurate amongst the other ML algorithms with a mean accuracy value of 85%.