Loughborough University
Browse
PAM 07.pdf (480.39 kB)

A live system for wavelet compression of high speed computer network measurements

Download (480.39 kB)
online resource
posted on 2007-10-17, 10:52 authored by Kostas KyriakopoulosKostas Kyriakopoulos, David Parish
Monitoring high-speed networks for a long period of time produces a high volume of data, making the storage of this information practically inefficient. To this end, there is a need to derive an efficient method of data analysis and reduction in order to archive and store the enormous amount of monitored traffic. Satisfying this need is useful not only for administrators but also for researchers who run their experiments on the monitored network. The researchers would like to know how their experiments affect the network's behavior in terms of utilization, delay, packet loss, data rate etc. In this paper a method of compressing computer network measurements while preserving the quality in interesting signal characteristics is presented. Eight different mother wavelets are compared against each other in order to examine which one offers the best results in terms of quality in the reconstructed signal. The proposed wavelet compression algorithm is compared against the lossless compression tool bzip2 in terms of compression ratio (C.R.). Finally, practical results are presented by compressing sampled traffic recorded from a live network.

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Citation

KYRIAKOPOULOS, K.G. and PARISH, D.J., 2007. A live system for wavelet compression of high speed computer network measurements. IN: Passive and Active Network Measurement : Proceedings of the 8th International Conference on Passive and Active Measurements 2007 (PAM 2007), Louvain-la-neuve, Belgium, 4-6 April. Lecture Notes in Computer Science, 4427. Berlin : Springer-Verlag, pp. 241-244

Publisher

© Springer-Verlag

Publication date

2007

Notes

This is a conference paper. The original version is available at www.springerlink.com

ISBN

9783540716167

Language

  • en

Usage metrics

    Loughborough Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC