TCP-GT

A new approach to congestion control based on goodput and throughput

Hyungsoo Jung, Shin Gyu Kim, Heon Young Yeom, Sooyong Kang*

*Corresponding author for this work

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A plethora of transmission control protocol (TCP) congestion control algorithms have been devoted to achieving the ultimate goal of high link utilization and fair bandwidth sharing in high bandwidth-delay product (HBDP) networks. We present a new insight into the TCP congestion control problem; in particular an end-to-end delay-based approach for an HBDP network. Our main focus is to design an end-to-end mechanism that can achieve the goal without the assistance of any network feedback. Without a router's aid in notifying the network load factor of a bottleneck link, we utilize goodput and throughput values in order to estimate the load factor. The obtained load factor affects the congestion window adjustment. The new protocol, which is called TCP-goodput and throughput (GT), adopts the carefully designed inversely-proportional increase multiplicative decrease window control policy. Our protocol is stable and efficient regardless of the link capacity, the number of flows, and the round-trip delay. Simulation results show that TCP-GT achieves high utilization, good fairness, small standing queue size, and no packet loss in an HBDP environment.

Original languageEnglish
Pages (from-to)499-509
Number of pages11
JournalJournal of Communications and Networks
Volume12
Issue number5
Publication statusPublished - Oct 2010
Externally publishedYes

Keywords

  • Congestion control
  • High bandwidth-delay product networks (HBDP)
  • Protocol design

Fingerprint Dive into the research topics of 'TCP-GT: A new approach to congestion control based on goodput and throughput'. Together they form a unique fingerprint.

  • Cite this