The Evolution of Internet Congestion

34 Pages Posted: 6 Feb 2012

See all articles by Steven Bauer

Steven Bauer

Massachusetts Institute of Technology (MIT) - Laboratory for Computer Science (LCS)

David D. Clark

MIT CSAIL

William Lehr

Massachusetts Institute of Technology (MIT) - Computer Science and Artificial Intelligence Laboratory (CSAIL)

Date Written: August 15, 2009

Abstract

This paper discusses the evolution of the congestion controls that govern all Internet traffic. In particular we chronicle and discuss the implications of the fact that the most significant "congestion signals" are increasingly coming from network operators, not the TCP stack. Providers now nudge users into different traffic patterns using a variety of new technical and non-technical means. These 'network based congestion management' techniques include volume-based limits and active traffic management of best effort traffic. The goal and effect of these techniques differs from the historically coveted flow-rate fairness of TCP, provoking some in the technical and policy community to question the appropriateness of such deviations, and feeding debates over network management and network neutrality. To appropriately evaluate emerging trends in congestion control, it is useful to understand how congestion control has evolved in the Internet, both with respect to its intellectual history within the technical community and with respect to the changing traffic/industry environment in which the Internet operates. This is important because a sophisticated and nuanced view of congestion and its management is necessary for good public policy in this space. We conclude the paper with a discussion of the policy implications and questions raised by the continual evolution of congestion.

Suggested Citation

Bauer, Steven and Clark, David D. and Lehr, William, The Evolution of Internet Congestion (August 15, 2009). TPRC 2009. Available at SSRN: https://ssrn.com/abstract=1999830

Steven Bauer (Contact Author)

Massachusetts Institute of Technology (MIT) - Laboratory for Computer Science (LCS) ( email )

United States

David D. Clark

MIT CSAIL ( email )

Stata Center
Cambridge, MA 02142
United States
617-253-6003 (Phone)

William Lehr

Massachusetts Institute of Technology (MIT) - Computer Science and Artificial Intelligence Laboratory (CSAIL) ( email )

Stata Center
Cambridge, MA 02142
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
210
rank
137,895
Abstract Views
1,011
PlumX Metrics