New Data Mining Techniques for Macroflows Delimitation in Congestion Control Management

published in Proceedings of the KEPT 2009 – Knowledge Engineering Principles and Techniques, Studia Universitatis Babeş-Bolyai, Special Issue 2009, Volume II, pp. 288-291, July 2009.

Cite as

Full paper

New Data Mining Techniques for Macroflows Delimitation in Congestion Control Management

Authors

Darius Bufnea
Department of Computer Science, Faculty of Mathematics and Computer Science,
Babeş-Bolyai University of Cluj-Napoca

Abstract

State of the art approaches in Internet congestion control suggest the collaboration between streams in a so called macroflow, instead of the current approach, where streams compete with each other for scarce bandwidth. However, the macroflows granularity follows a simple approach, a macroflow being constructed on host pair bases. This paper presents new data mining techniques for grouping flows into macroflows based on their similar behavior over time.

Key words

congestion control, macroflow

BibTeX bib file

bufnea-2009.bib

References

  1. J. Han and M. Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers, 2001.
  2. D. V. Bufnea, A. Campan and A. S. Darabant, Fine-Grained Macroflow Granularity in Congestion Control Management, Studia Universitatis, Vol. L(1), pp. 79-88, 2005.
  3. A. Campan and D. V. Bufnea, Delimitation of Macroflows in Congestion Control Management Using Data Mining Techniques, 4th ROEDUNET International Conference, Education/Training and Information/Communication Technologies – ROEDUNET ’05, Romania, pp. 225-234, 2005.
  4. D. V. Bufnea, A New Method for Macroflows Delimitation from a Receiver’s Perspective, Proceedings of the IEEE 2nd International Conference on Computers, Communications & Control (ICCCC 2008), Felix Spa, Romania, Vol. III (2008), pp. 201-205.

Darius Bufnea