See
discussions, stats, and author profiles for this publication at:
https://www.researchgate.net/publication/317606050
Analysis and Performance Evaluation of SDN Queue Model
Conference Paper
in
Lecture Notes in Computer Science · June 2017
DOI: 10.1007/978-3-319-61382-6_3
CITATIONS
32
READS
2,924
6 authors
, including:
Samuel Muhizi
St. Petersburg State University
of Telecommunication
3
PUBLICATIONS
45
CITATIONS
SEE
PROFILE
Ammar Muthanna
Saint-Petersburg State University
of Telecommunications
195
PUBLICATIONS
2,127
CITATIONS
SEE PROFILE
Ruslan Kirichek
St. Petersburg State University of Telecommunication
111
PUBLICATIONS
1,443
CITATIONS
SEE PROFILE
Andrei Vladyko
St. Petersburg State University of Telecommunication
78
PUBLICATIONS
853
CITATIONS
SEE PROFILE
All content following
this page was uploaded by
Andrei Vladyko
on 20 November 2018.
The user has requested enhancement of the downloaded file.
Analysis and Performance Evaluation of SDN
Queue Model
Samuel Muhizi
1
,
Gregory Shamshin
1
, Ammar Muthanna
1
, Ruslan Kirichek
1,2(
✉
)
,
Andrei Vladyko
1
, and
Andrey Koucheryavy
1
1
The Bonch-Bruevich State University of Telecommunication, 22 Prospekt Bolshevikov,
St. Petersburg, Russia
2
Peoples’ Friendship University of Russia (RUDN University), 6 Miklukho-Maklaya Street,
Moscow, Russia
samno1@yandex.ru, reignsword@gmail.com, ammarexpress@gmail.com,
{kirichek,vladyko}@sut.ru, akouch@mail.ru
Abstract.
In this paper, we present an Openflow-SDN based network visuali‐
zation and performance evaluation model that helps in network designing and
planning to examine how networks’ performance will be affected as the traffic
loads and network utilization change. To achieve the aimed goal, as
a research
method, we used AnyLogic Multimethod simulation tool. This is a first of its kind
where SDN performance evaluation is based on queuing model simulation to
monitor change of average packet processing time for various network parame‐
ters. Using presented in this work SDN model, network administrators and plan‐
ners can better predict likely performance changes arising from traffic variation.
This allows them to make prompt decisions to prevent
seemingly small issues
from becoming major bottlenecks.
