Modeling network traffic as images Conference Paper

abstract

• This paper presents a network measurement approach to represent samples of network packet header data as frames or images. With such a formulation, a series of samples can be seen as a sequence of frames or video. This enables techniques from image processing and video compression to be applied to the analysis of packet header data to reveal interesting properties of traffic. We show that traffic images can reveal sudden changes in traffic behavior or anomalies. Using a combination of visual modeling and trace-driven simulation, we evaluate how the design factors impact the representation of dynamic network traffic. In particular, we study the impact of sampling rate and retained DCT coefficients on the network traffic data representation. 2005 IEEE.

name of conference

• IEEE International Conference on Communications, 2005. ICC 2005. 2005

authors

• Reddy, Narasimha

published proceedings

• ICC 2005: IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, VOLS 1-5

author list (cited authors)

• Kim, S. S., & Reddy, A.

citation count

• 6

complete list of authors

• Kim, SS||Reddy, ALN

publication date

• January 2005

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• 2013 National Conference on Communications, NCC 2013  Journal

keywords

• Image Difference Analysis
• Network Anomaly Detection
• Network Security
• Network Traffic
• Network Traffic Modeling And Characterization
• Time-varying Imagery
• Video Analysis

Digital Object Identifier (DOI)

• 10.1109/icc.2005.1494341

International Standard Book Number (ISBN) 10

• 0-7803-8938-7

start page

• 168

end page

• 172

volume

• 1

URL

• http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=9996