Site Loader

   Mr THANIGAVEL M_1,Ms .JAYASREE K2_,Ms.KOWSALYA.S_3,Ms.
PRIYADHARSCINI S_4

                               1Assistant
Professor, Dept. of Information Technology, Prathyusha Engineering College.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

                                       2 3 4 Students, Dept. of
Information technology, Prathyusha Engineering College.

                                                                                                            

ABSTRACT:

                 Traffic classification is a
central topic in the field of computer science. The Classification and the
analysis of the network traffic is useful to avoid the traffic congestion while
transferring the data. The traffic classification refers to categorizing the
traffic according to its various application type and also helps in managing
the overall performance of a network. . The Traffic flow analysis is an
essential piece of knowledge for engineering a network. However, with the rapid
evolution of the internet applications the effectiveness of the traditional
methods like port based, payload based. The Machine learning algorithms has
achieved high accuracy and best results. The use of Hello Packet for the
classification makes easier in analysing the real-time network which adds
accuracy to the existing system. The accurate classification is achieved using
the hello packet which classifies the network in a effective way and transfers
the data through the easier and the shortest path.

Keywords:
 Traffic Classification, Hello Packet, Traffic
Flow Analysis.

                 I.INTRODUCTION

 Network Traffic
classification is an important topic nowadays in the field of communication and
computer science.

This
is useful for the Internet Service Providers(ISPs) to manage the network performance.
Traffic classification is the first step in identifying and classifying the
unknown network classes.

The
Network traffic classification plays a vital role in network security and
management such as the Intrusion Detection and Quality of Service ( QoS) There
are several techniques have been proposed classifying and analysing the network
traffic which includes the traditional techniques like port based method
payload based techniques these techniques

.Port
based technique is a great technique for network classification .  This technique failed due to increase of peer
to peer applications.

 The Payload based Technique which is also
called Deep  Packet Inspection (DPI) is effective
in classification but it cannot be applied to encrypted data network
applications as numerous data network applications use encrypted techniques to
protect the data from detection . The DPI technique failed due to use of
encrypted flow of applications . The researchers then proposed Machine
Learning  Technique to classify the
internet traffic as well as to know the type of applications flow in the
network.

 

      
II.PROBLEM STATEMENT

                The evolution in the internet
applications has led to different methods of classifying the network traffic. The
port based, payload based techniques has efficient classification but comparatively
has low accuracy.

                      These techniques failed
for the encrypted data network applications. The port based technique failed
due to dynamic port numbers. Dynamic port number means unregistered number with
the (Internet Assign Number Authority). The classification results in a better
way but it doesn’t compare the results of those algorithms. The port based
technique has failed due to increase of peer to peer communication.

            III.EXISTING SYSTEM

                 The network classification has
several traditional techniques to classify the network traffic such as the
payload method and port-based method which does not support for encrypted data
network applications as numerous network applications use encrypted network to
protect data from detection. Port based techniques failed due to increase of
peer to peer applications. The port based and the payload based techniques have
achieved in classifying the network effectively but has failed when applied to
encrypted data applications.

              

        IV.PROPOSED SYSTEM

 

TIE recommends a unified representation of
classification results.It defines IDs for application classes and associates
them with group classes.The comparison of traffic classifiers which have application-level
protocol.It uses the Hello Packet to compute the distance from the source to
destination. The hello packet establishes and confirms network
relationship.It distinguishes the traffic as per its constraints.

The
TIE is also used to compute the following  Duration of a video or audio stream 

Voice
or video quality of experience

Counts
of the number of events

Tracking
of “top” items (e.g., most frequently requested URLs, most popular video
providers, etc.) 

 Summations (e.g., adding up a number of
events).

                      IV.OBJECTIVE

The
main aim of the project is to transfer the data without traffic congestion. This
analyses the traffic and classifies the network traffic and transfers the data
over the shortest path. The shortest path is computed using the Machine
Learning algorithms.

The
Machine Learning algorithm is used as it achieves high accuracy. The Hello
Packet is used to easily classify the network traffic and transfers the data
via the free and the shortest Path.

                       V.METHODOLOGY

            
 Hello Packet implementation along
with the machine learning algorithms provide higher accuracy compared to
previous classification techniques.

Hello
Packet is a special packet that is sent from a router which is used to
establish and confirms the network adjacency relationships.

The
Hello Packet classifies the network traffic and transfers the data via the
shortest path. The shortest path is computed using the Machine Learning algorithms.
The path is classified as traffic free network and network with traffic and it
then chooses the easier and the shortest path.

 

 

ARCHITECTURE DIAGRAM

 

 

 

 

 

 

 

 

The
Sender analyses and captures the available ip on the network from which the
sender ip is been selected. The File to be sent is been attached and the file
is sent.The analyser is that finds the available nodes and lists all the
routers.The free router from that is chosen to transfer the file.

The
classifier classifies the path based on the implemented machine learning
algorithms and finds the shortest path from that of the available routers.This
automatically identifies the path or it can be done manually by the sender by
which the path can be selected by the sender itself. The file that is
transferred is received at the receiver’s end.

`

 

VI. NETWORK TRAFFIC   CLASSIFICATION MODEL

 

 

                       

                     

                                                                                                                                                                                              

                      

                        

 

 

 

 

A.Captures
the IP

                   This is the first and the
foremost step, it captures the ip address of the sender. The File to be
transmitted is selected. The content of the file is obtained it also lists the
packet length and size. The packet filter displays the size of the packet to be
transmitted then the file is sent.

 B. Traffic Classification

                   The system starts analysing
the network traffic by which it identifies the ways to send the file. It
distinguishes the free network from that of the path with traffic and makes the
communication easier.

 C. Identifying the Path

                  The  Routers are listed which are used to transfer
the file selects the path based on the machine learning algorithms .It finds
the shortest path and the free path among the available routers and displays
those routers.

D.
File Transfer

After
the process of finding the path the data that is selected is been sent through
the free router and the file is been transferred to the receiver.

 

                 After the process of finding
the path the data that is selected is been sent through the free router and the
file is been transferred to the receiver.

                   The Receiver then receives
the transferred file from the sender this also lists the contents of the file..

        VII.RESULTSAND OBSERVATION

The
Implementation of  Algorithms used here
achieve high accuracy. There are four algorithms used to find the shortest path
on the network. They are C45, SVM, Bayes Net, Naive Bayes algorithms. The
comparison of the accuracy is shown below. The file transfer is made easier.
The use of the Hello packet is been analysed.

The
ways of classification and the comparison of the algorithms along with the
hello packet has achieved high results of accuracy.

accuracy
is shown below. The file transfer is made easier. The use of the Hello packet
is been analysed. The ways of classification and the comparison of the
algorithms along with the hello packet has achieved high results of accuracy

 

 

Classifiers

Accuracy

Time T in
seconds

C45

78.9189

0

Bayes
Net

68.1081

0.1

SVM

74.0541

0.3

Naïve
Bayes

71.8919

0.1

 

The
efficiency of these four algorithms are analysed and the results are being
compared and listed  below in the form of
graph.

                  VII.CONCLUSION                                                                                         
In this paper, we discuss Network traffic
classification techniques and discuss How new researchers or new network
operators will apply the network traffic classification technique using machine
learning algorithm to classify unknown applications and manage performance of
network. And then we perform comparative analysis of four machine learning
classifiers. Firstly, we demonstrated Network Traffic Classification Techniques
(Port Based, Pay Load Based and Machine Learning Based technique) and their
limitation. The Hello Packet concept has been implemented which is used for
easier data transfer which adds additional advantage to the existing system.
The Classification is done in a better way and achieves better accuracy.

                   REFERENCE TABLE                                                              

                     REFERENCES

1. Hamza Awad Hamza Ibrahim, Omer Radhi AqeelAl
Zuobi, Marwan A. Al-Namari,Gaafer MohamedAli, Ali Ahmed Alfaki Abdalla, Internet
Traffic Classification using Machine Language Approach: Datasets validation
issues IEEE 2016.

2.
Muhammad Shafiq, Xiangzhan Yu, Asif Ali Laghari , Lu Yao, Nabin Kumar Karn,
Foudil Abdessmia, Network Traffic Classification techniques and comparative
analysis using Machine Learning algorithms IEEE 2016.

3.
Walter deDonato, Antonio Pescape, Alberto Dainotti, Traffic Identification
Engine: An Open Platform for Traffic Classification IEEE 2014.

4.
P.Raj Kumar , P.Prasanna,Traffic Classification By Using :TIE(Traffic
Classification Engine, International Journal of Engineering and Computer
Science(IJECS) 2015.

5.
Mohammad Reza Parsaei, Mohammad Javad Sobouti, Seyed Raouf Khayami, Reza
Javidan, Network Traffic Classification using Machine Learning Techniques over
Software Defined Networks International Journal of Advanced Computer Science
and Applications (IJRSCA)2017.

6.
HE HaiTao, LUO XiaoNan, MA Fei Teng, CHE ChunHui & WANG JianMin,Network Traffic
Classication based on Ensemble Learning and co-training,Springer 2009.

7.
Michael Finsterbusch, Chris Ritcher Eduardo Rocha,Jean-Alexander Muller,Klaus
Hanssgen, A Survey of Payload-Based Traffic Classification Approaches. IEEE
2013.

8.  A. Moore and K. Papaginnaki,Toward the
accurate identification of network applications in PAM 2005.

9.
A. Dainotti, W. De Donato, A. Pescape, and P. Salvo Rossi, “Classification of
network traffic via packet-level hidden markov models. IEEE Global
Telecommunications Conference, 2008.

10.
Ms. Zeba Atique Shaik,Prof.Dr.D.G. Harkut, An Overview of Network Traffic
Classification Methods International Journal on Recent and Innovation Trends in
Computing and Communication(IJRITCC)2015.

Post Author: admin

x

Hi!
I'm Erica!

Would you like to get a custom essay? How about receiving a customized one?

Check it out