Performance Analysis of Congestion Control Mechanism in Software Defined Network (SDN)

Badlishah, Ahmad and Rahman, M.Z.A and Yaakob, N and Amir, A and Ahmad, R and Yoon, S.K and Abd Halim, A.H (2017) Performance Analysis of Congestion Control Mechanism in Software Defined Network (SDN). In: 1st International Conference on Emerging Electronic Solutions for IoT, ICEESI 2017, 9-10 October 2017, Penang, Malaysia.

[img] Image
FH03-FIK-18-12292.jpg
Restricted to Registered users only

Download (157kB)

Abstract

In the near future, the traditional networks architecture will be difficult to be managed. Hence, Software Defined Network (SDN) will be an alternative in the future of programmable networks to replace the conventional network architecture. The main idea of SDN architecture is to separate the forwarding plane and control plane of network system, where network operators can program packet forwarding behaviour to improve the network performance. Congestion control is important mechanism for network traffic to improve network capability and achieve high end Quality of Service (QoS). In this paper, extensive simulation is conducted to analyse the performance of SDN by implementing Link Layer Discovery Protocol (LLDP) under congested network. The simulation was conducted on Mininet by creating four different fanout and the result was analysed based on differences of matrix performance. As a result, the packet loss and throughput reduction were observed when number of fanout in the topology was increased. By using LLDP protocol, huge reduction in packet loss rate has been achieved while maximizing percentage packet delivery ratio.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Informatics & Computing
Depositing User: Muhammad Akmal Azhar
Date Deposited: 10 Nov 2020 03:40
Last Modified: 10 Nov 2020 03:40
URI: http://eprints.unisza.edu.my/id/eprint/1189

Actions (login required)

View Item View Item