Achieving Loss Discrimination with Congestion Avoidance in a Rate-based Protocol

Gaonkar, Shravan; Kravets, Robin; Magalhaes, Luiz

Permalink

https://hdl.handle.net/2142/10824 Copy

Description

Title

Achieving Loss Discrimination with Congestion Avoidance in a Rate-based Protocol

Author(s)

• Gaonkar, Shravan
• Kravets, Robin
• Magalhaes, Luiz

Issue Date

2004-05

Keyword(s)

• Computer Networks
• Wireless Networks

Abstract

The stability of the Internet depends on the presence of well-behaved flows. While TCP forms the majority of the traffic over the Internet, the Internet user community is also dedicated to supporting mobile devices over wireless networks. However, TCP is not well suited to support applications over lossy wireless networks. Ideally, these applications require a protocol that adapts to network conditions with the ability to discriminate congestion-based and transmission-based losses. In this paper, we present a rate-based transport protocol that is designed to support communication for mobile nodes using infrastructure-based wireless networks. We propose an end-to-end approach to loss discrimination based on network state estimation at the receiver. Discrimination is achieved by correlating short-term history of packet inter-arrival times with the loss. We also integrate a congestion avoidance algorithm to react to pending network congestion. Simulations of our protocol prototype show that rate-based protocols can provide better correlation to network conditions than ACK-clocked protocols. We provide extensive evaluation through simulation demonstrating that our protocol is well-behaved over a wide range of scenarios.

Type of Resource

text

Permalink

http://hdl.handle.net/2142/10824

Copyright and License Information

You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the University of Illinois at Urbana-Champaign Computer Science Department under terms that include this permission. All other rights are reserved by the author(s).

Owning Collections