A Caltech Library Service

Understanding TCP Vegas: A Duality Model

Low, Steven H. and Peterson, Larry L. and Wang, Limin (2002) Understanding TCP Vegas: A Duality Model. Journal of the ACM, 49 (2). pp. 207-235. ISSN 0004-5411. doi:10.1145/506147.506152.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We view congestion control as a distributed primal--dual algorithm carried out by sources and links over a network to solve a global optimization problem. We describe a multilink multisource model of the TCP Vegas congestion control mechanism. The model provides a fundamental understanding of delay, fairness and loss properties of TCP Vegas. It implies that Vegas stabilizes around a weighted proportionally fair allocation of network capacity when there is sufficient buffering in the network. It clarifies the mechanism through which persistent congestion may arise and its consequences, and suggests how we might use REM active queue management to prevent it. We present simulation results that validate our conclusions.

Item Type:Article
Related URLs:
URLURL TypeDescription
Low, Steven H.0000-0001-6476-3048
Additional Information:© 2002 ACM, Inc. Received February 2001; Revised January 2002; Accepted January 2002. Partial and preliminary results have appeared in LOW, S. H., PETERSON, L., AND WANG, L. 2001. Understanding Vegas: A duality model. In Proceedings of ACM SIGMETRICS (June). ACM, New York. S. H. Low acknowledges the support of the Australian Research Council through Grant A49930405, National Science Foundation (NSF) through Grant ANI-0113425, and the Caltech Lee Center for Advanced Networking. L. L. Peterson acknowledges the support of NSF through Grant ANI-9906704 and DARPA through contract F30602-00-2-0561. We are grateful to Sanjeewa Athuraliya, Nick Maxemchuk, and the anonymous reviewers for their helpful comments.
Funding AgencyGrant Number
Australian Research CouncilA49930405
Caltech Lee Center for Advanced NetworkingUNSPECIFIED
Defense Advanced Research Projects Agency (DARPA)F30602-00-2-0561
Subject Keywords:Algorithms; Performance; Theory; Persistent congestion; REM; TCP congestion control; TCP Vegas
Issue or Number:2
Record Number:CaltechAUTHORS:20111101-161123893
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:27567
Deposited By: Jason Perez
Deposited On:02 Nov 2011 17:25
Last Modified:09 Nov 2021 16:49

Repository Staff Only: item control page