Presented by
Mithileysh Sathiyanarayanan
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Deeraj Achunala, Mithileysh Sathiyanarayanan, Babangida Abubakar
Traffic Classification Analysis
using OMNeT++
215
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Introduction
Related Works
Proposed Approach
Experimental Details
Results and Analysis
ConclusionsIntroduction
1/7
Traffic Classification :
There has been a lot of research on effective monitoring and management of the
network traffic, where a large amount of internet traffic requires more accurate
and efficient ways of traffic classification methods and approaches with an aim to
improve network performance.
In our research, we introduce the subject of packet classification in IP traffic
analysis with a simple technique that relies on prototype classifier using
OMNET++ (Optical Modelling Network using C++ programming language)
which unfolds one new possibility for an online classification focusing on
application detection in the absence of payload information.
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Introduction
Related Works
Proposed Approach
Experimental Details
Results and Analysis
ConclusionsRelated Works
2/7
•Deep Packet Inspection
•Traditional methods of classification
•Clustering Algorithms.
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Introduction
Related Works
Proposed Approach
Experimental Details
Results and Analysis
ConclusionsProposed Approach
3/7
In this research, we evaluated our novel IATP (Inter-arrival time and
precision) clustering algorithm with the help of OMNET++ scheduler for
classification of network traffic. The analysis is based on the measure
combined with inter-arrival time and precision which was able to
distinguish fairly as a small different subset of clusters.
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Introduction
Related Works
Proposed Approach
Experimental Details
Results and Analysis
ConclusionsExperimental Details
4/7
Figure: (a) Traffic Classification Model designed in OMNet++.(b) Result of
our classification
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Introduction
Related Works
Proposed Approach
Experimental Details
Results and Analysis
ConclusionsResults and Analysis
5/7
With our implementation of a range of flow attributes, the simulation result
demonstrates the effectiveness of 100% accuracy of classifying packets but does
not constitute the same level of accuracy with real-time traffic classifier
which operates under certain constraints. Accuracy for real-time traffic
might normally vary from 80% to 95% and depends on the type of each application.
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Introduction
Related Works
Proposed Approach
Experimental Details
Results and Analysis
ConclusionsConclusions
6/7
The simulation result demonstrates the effectiveness of 100% accuracy of
classifying packets but does not constitute the same level of accuracy with
real time traffic classifier which operates under certain constraints. Accuracy for
real time traffic might normally vary from 80% to 95% and depends
on the type of each application.
Our future work can include investigating of traffic classification with QoS
since our models have been designed only with performance evaluation
and not with QoS. In future we can evaluate QoS assurance with reliability, delay
and throughput. By observing performance metrics such as classification rate
and build time, a much better differentiation of algorithms can be investigated.
Our future work will depend on the contributions and limitations of the other
researchers work .
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
Introduction
Related Works
Proposed Approach
Experimental Details
Results and Analysis
ConclusionsReferences
7/7
C. Parsons, Deep Packet Inspection in Perspective: Tracing its lineage and
surveillance potentials. Citeseer, 2008.
D. Achunala, “Traffic classification,” thesis, Sep 2012.
M. Sathiyanarayanan and K. S. Kim, “Multi-channel deficit round-robin scheduling
r hybrid tdm/wdm optical networks,” in Proc. of the 4th International Congress
Ultra Modern Telecommunications and Control Systems (ICUMT 2012), St.
tersburg, Russia, Oct. 2012, pp. 552–557.
M. Sathiyanarayanan and B. Abubhakar, “Dual mcdrr scheduler for hybrid
m/wdm optical networks,” in Proc. of the 1st International Conference on Networks
d Soft Computing (ICNSC 2014), Andra Pradesh, India, Aug 2014, pp.
6–470.
M. Sathiyanarayanan and B. Abubakar, “Mcdrr packet scheduling algorithm for
ulti-channel wireless networks,” in Proceedings of 3rd International Conference
Advanced Computing, Networking and Informatics. Springer, 2016, pp. 125–
1.
?
Q and A?
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
?
Q and A?
4th International Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)

Traffic Classification

  • 1.
    Presented by Mithileysh Sathiyanarayanan 4thInternational Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016) Deeraj Achunala, Mithileysh Sathiyanarayanan, Babangida Abubakar Traffic Classification Analysis using OMNeT++ 215
  • 2.
    4th International Conferenceon Advanced Computing, Networking, and Informatics (ICACNI 2016) Introduction Related Works Proposed Approach Experimental Details Results and Analysis ConclusionsIntroduction 1/7 Traffic Classification : There has been a lot of research on effective monitoring and management of the network traffic, where a large amount of internet traffic requires more accurate and efficient ways of traffic classification methods and approaches with an aim to improve network performance. In our research, we introduce the subject of packet classification in IP traffic analysis with a simple technique that relies on prototype classifier using OMNET++ (Optical Modelling Network using C++ programming language) which unfolds one new possibility for an online classification focusing on application detection in the absence of payload information.
  • 3.
    4th International Conferenceon Advanced Computing, Networking, and Informatics (ICACNI 2016) Introduction Related Works Proposed Approach Experimental Details Results and Analysis ConclusionsRelated Works 2/7 •Deep Packet Inspection •Traditional methods of classification •Clustering Algorithms.
  • 4.
    4th International Conferenceon Advanced Computing, Networking, and Informatics (ICACNI 2016) Introduction Related Works Proposed Approach Experimental Details Results and Analysis ConclusionsProposed Approach 3/7 In this research, we evaluated our novel IATP (Inter-arrival time and precision) clustering algorithm with the help of OMNET++ scheduler for classification of network traffic. The analysis is based on the measure combined with inter-arrival time and precision which was able to distinguish fairly as a small different subset of clusters.
  • 5.
    4th International Conferenceon Advanced Computing, Networking, and Informatics (ICACNI 2016) Introduction Related Works Proposed Approach Experimental Details Results and Analysis ConclusionsExperimental Details 4/7 Figure: (a) Traffic Classification Model designed in OMNet++.(b) Result of our classification
  • 6.
    4th International Conferenceon Advanced Computing, Networking, and Informatics (ICACNI 2016) Introduction Related Works Proposed Approach Experimental Details Results and Analysis ConclusionsResults and Analysis 5/7 With our implementation of a range of flow attributes, the simulation result demonstrates the effectiveness of 100% accuracy of classifying packets but does not constitute the same level of accuracy with real-time traffic classifier which operates under certain constraints. Accuracy for real-time traffic might normally vary from 80% to 95% and depends on the type of each application.
  • 7.
    4th International Conferenceon Advanced Computing, Networking, and Informatics (ICACNI 2016) Introduction Related Works Proposed Approach Experimental Details Results and Analysis ConclusionsConclusions 6/7 The simulation result demonstrates the effectiveness of 100% accuracy of classifying packets but does not constitute the same level of accuracy with real time traffic classifier which operates under certain constraints. Accuracy for real time traffic might normally vary from 80% to 95% and depends on the type of each application. Our future work can include investigating of traffic classification with QoS since our models have been designed only with performance evaluation and not with QoS. In future we can evaluate QoS assurance with reliability, delay and throughput. By observing performance metrics such as classification rate and build time, a much better differentiation of algorithms can be investigated. Our future work will depend on the contributions and limitations of the other researchers work .
  • 8.
    4th International Conferenceon Advanced Computing, Networking, and Informatics (ICACNI 2016) Introduction Related Works Proposed Approach Experimental Details Results and Analysis ConclusionsReferences 7/7 C. Parsons, Deep Packet Inspection in Perspective: Tracing its lineage and surveillance potentials. Citeseer, 2008. D. Achunala, “Traffic classification,” thesis, Sep 2012. M. Sathiyanarayanan and K. S. Kim, “Multi-channel deficit round-robin scheduling r hybrid tdm/wdm optical networks,” in Proc. of the 4th International Congress Ultra Modern Telecommunications and Control Systems (ICUMT 2012), St. tersburg, Russia, Oct. 2012, pp. 552–557. M. Sathiyanarayanan and B. Abubhakar, “Dual mcdrr scheduler for hybrid m/wdm optical networks,” in Proc. of the 1st International Conference on Networks d Soft Computing (ICNSC 2014), Andra Pradesh, India, Aug 2014, pp. 6–470. M. Sathiyanarayanan and B. Abubakar, “Mcdrr packet scheduling algorithm for ulti-channel wireless networks,” in Proceedings of 3rd International Conference Advanced Computing, Networking and Informatics. Springer, 2016, pp. 125– 1.
  • 9.
    ? Q and A? 4thInternational Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)
  • 10.
    ? Q and A? 4thInternational Conference on Advanced Computing, Networking, and Informatics (ICACNI 2016)