Dragonfly addressing model for software defined networks based on datacenters release_4fsseghkcbfjza34eltcpplcui

by Heba Hassan, Amr Al-Awamry, Mohammed Abdelhalim

Published in International Journal of Engineering & Technology by Science Publishing Corporation.

2018   p657

Abstract

With the advancement of technology, virtualization has become very important for Information Technology (IT) experts. Network Functions Virtualization (NFV) means to address issues resulting from complex hardware-based appliances by developing standard IT virtualization technologies. Software Defined Networking (SDN) solidifies the advantages of datacenter virtualization, increases resource flexibility and utilization, and reduces infrastructure costs and overhead. Datacenter networks should have the ability to guarantee high throughput and resiliency. For such reasons, typical datacenter networks (e.g. Fat Tree) have been evolved to high-radix networks (e.g. Dragonfly). This work aims to investigate how SDN and NFV can improve the advantages of datacenter virtualization by utilizing datacenter topologies such as Dragonfly (DF) topology and Fat Tree (FT) topology in SDN, thus expanding resource flexibility and utilization and diminishing infrastructure costs and overhead. By using Dragonfly topology, the cost is reduced and better scalability is introduced compared to the folded clos networks such as Fat Tree. Here in, a novel addressing scheme is proposed for Dragonfly topology with simulation results included utilizing Mininet, which incorporates MiniEdit that is used to create and run network simulations.
In application/xml+jats format

Archived Files and Locations

application/pdf  568.3 kB
file_azgqhkulcrdw7mf3jdi6hqh3ui
web.archive.org (webarchive)
www.sciencepubco.com (publisher)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2018-04-30
Journal Metadata
Open Access Publication
Not in DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  2227-524X
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 34b88f52-802c-4a5c-945b-bdf12bf9394a
API URL: JSON