Home > Archive > 2011 > Volume 1 Number 3 (Aug. 2011) >
IJMLC 2011 Vol.1(3): 236-241 ISSN: 2010-3700
DOI: 10.7763/IJMLC.2011.V1.35

Type-2 Fuzzy Logic Control Model for Traffic Shaping Using Backpressure over High Speed Networks

Somchai Lekcharoen

Abstract—Current, network has become a significant part of network and data communications. The crisis problem is that cannot properly shape incoming connection. A traffic shaper assists monitors the amount of egress traffic, and makes smooth the burst traffic rate. It wants the guarantee performance, lower delaying packet, and raises the serviceable bandwidth by packets that meet up certain criteria. As the major of networks has a limited amount of bandwidth. Network traffics are always to become so busy. It is leads to choking points. However, one way to solve this problem, we use type-2 fuzzy backpressure to control traffic shaping. In deed, the telecommunication network traffic always becomes fluctuation. Especially, various types of burst/silence traffic are being generated. A type-2 fuzzy control is suitable for uncertain traffic, especially in alternative burst and silence. The backpressure mechanism can control traffic and increases conforming frames. In this paper wants to evaluate and compare the performance of the three mechanisms in traffic shaping: type-2 fuzzy using backpressure (T2F), Fuzzy control (T1F) and conventional traffic shaping mechanism on Leaky Bucket (LB). Simulation results showed that the type-2 fuzzy using backpressure mechanism could help to improve the performance in traffic shaping much better than conventional traffic shaping one while various types of burst/silence traffic are being generated.

Index Terms—type-2 fuzzy control, traffic shaping, congestion control

Somchai Lekcharoen is with the Faculty of Information Technology, Rangsit University (e-mail: s_lekcharoen@yahoo.com).

[PDF]

Cite: Somchai Lekcharoen, "Type-2 Fuzzy Logic Control Model for Traffic Shaping Using Backpressure over High Speed Networks," International Journal of Machine Learning and Computing vol. 1, no. 3, pp. 236-241, 2011.

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net


Article Metrics in Dimensions