A fair TCP-based congestion avoidance approach for one-to-many private networks

Tarik Taleb, Hiroki Nishiyama, Abbas Jamalipour, Nei Kato, Yoshiaki Nemoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Over the past few years, a number of private networks have emerged. In these private networks, a server provides its subscribed clients with Internet services, forming a one-to-many network topology. Given the fact that users are located at different distances from the server, usage of the Transmission Control Protocol (TCP) for communication results ' in drastically unfair bandwidth allocations among the users. In this regard, this paper addresses the fairness and efficiency issues of TCP in such one-to-many IP (Internet Protocol) networks. The efficiency of TCP is controlled by matching the aggregate traffic rate of all TCP connections to the sum of the link capacity and total buffer size. On the other hand, its unfairness issue is mitigated by allocating bandwidth among individual flows in relative proportion with their RTTs. Simulation results elucidate that the proposed method makes better utilization of the network resources, reduces the number of packet drops, and provides a fair service to users.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Communications, ICC 2006
Pages1921-1926
Number of pages6
DOIs
Publication statusPublished - 2006 Dec 1
Event2006 IEEE International Conference on Communications, ICC 2006 - Istanbul, Turkey
Duration: 2006 Jul 112006 Jul 15

Publication series

NameIEEE International Conference on Communications
Volume4
ISSN (Print)0536-1486

Other

Other2006 IEEE International Conference on Communications, ICC 2006
Country/TerritoryTurkey
CityIstanbul
Period06/7/1106/7/15

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A fair TCP-based congestion avoidance approach for one-to-many private networks'. Together they form a unique fingerprint.

Cite this