NORMA eResearch @NCI Library

Optimization of SDN data plane traffic by regulating elephant and mice flows using link bandwidth and delay aware algorithm

Rodrigues, Joel Clinton John (2020) Optimization of SDN data plane traffic by regulating elephant and mice flows using link bandwidth and delay aware algorithm. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview

Abstract

Software-Defined Networking (SDN) is based on the centralized architecture of the network. It enables to centrally manage the whole network while making the IT networks become more flexible and agile. Network traffic congestion and underutilization of redundant links are some of the biggest challenges faced by large service providers today. With the rise in number of connected devices on the internet and the humungous amount of data traffic being generated by billions of users every day, it is becoming essential to find ways for optimizing the data paths in networks. This paper proposes an algorithm that identifies the different data flows in the network and routes them through the optimized path according to their flow type. If the identified flows are the elephant flows that consume high network bandwidth, then the best path used for forwarding will be the highest bandwidth path. In case, the identified flows are mice fkows that are delay-sensitive traffic then, in that case, best path to the destination will be the lowest delay path. This experiment involves the use of the Mininet tool, POX controller and OpenFlow vSwitch. The results and analysis of this study show that, the proposed algorithmimproves the SDN network performance by routing the data traffic intelligently based on the flow type.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

T Technology > T Technology (General) > Information Technology > Cloud computing
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 20 Mar 2020 14:29
Last Modified: 20 Mar 2020 14:29
URI: http://trap.ncirl.ie/id/eprint/4136

Actions (login required)

View Item View Item