Application Aware Self Adaptive Decentralized Management In Software Defined Networking

Abstract

The Software Defined Networking (SDN) will enable the network programmability realization and application-aware networking in network devices based on the separation of data and control planes.  While developing the management architectures based on SDN, this has significant importance for designing a system which will offer consistent updates in real time for the management applications of heterogeneous systems. The management system should scale as the network size grows, minimize the overhead of available resources, provide an accurate network view, and support vacuum applications with low latency requirements. As a result, self-adaptive distributed management will be introduced for applications in software-defined networks. Management functions will be implemented on a case-by-case basis. This concept has the potential to introduce a new node, namely the SDN manager, into the SDN architecture. This presented approach is evaluated based on realistic use case conditions, and a test bed will be set up to compare performance between scenarios with and without mapping, which can show that mapping between network resources and applications results in a significant improvement in performance. This demonstrated management approach will have strong impact on SDN architecture evolution since presented distributed execution filed will be a generic one, so this will be utilized for management as well as application or control functions distribution.