An Efficient Clustering Scheme to Exploit Hierarchical Data in Network Traffic Analysis

An Efficient Clustering Scheme to Exploit Hierarchical Data in Network Traffic Analysis

Abstract:

There is significant interest in the data mining and network management communities about the need to improve existing techniques for clustering multivariate network traffic flow records so that we can quickly infer underlying traffic patterns. In this paper, we investigate the use of clustering techniques to identify interesting traffic patterns from network traffic data in an efficient manner. We develop a framework to deal with mixed type attributes including numerical, categorical, and hierarchical attributes for a one-pass hierarchical clustering algorithm. We demonstrate the improved accuracy and efficiency of our approach in comparison to previous work on clustering network traffic.

Modules:
1 Cluster Formation in Echidna
2 Radius Calculations
3 Determining Parameters
4 Testing

Man power of project: one
Problem Domain:
Investigation of the use of clustering techniques to identify interesting traffic patterns from network traffic data in an efficient manner.
Existing System:-

• No efficient clustering scheme used in generating reports about the network traffic.

• There is no proper key distribution technique was used.


Proposed System:-
• Clustering scheme called Echidna for generating summary reports of significant traffic flows in network traces.
• The key contributions of our scheme are the introduction of a new distance measure for hierarchically structured attributes such as IP addresses and a set of heuristics to summarize and compress reports of significant traffic clusters from a hierarchical clustering algorithm.

Hardware requirements:
Windows XP,2000
Hard disk:40GB
Processor Pentium4,1.33MHZ
RAM 512MB
LAN

Software requirements:
JDK1.6.0
Java run time environment