networks.txt

Ten years after TCP’s development, theoretical analyses showed that TCP’s
congestion-control algorithm serves as a distributed asynchronous-optimization
algorithm that results in several important aspects of user and network performance
being simultaneously optimized [Kelly 1998]. A rich theory of congestion control
has since been developed [Srikant 2004].

Using this formula, we can see that in order to achieve a throughput of 10 Gbps,
today’s TCP congestion-control algorithm can only tolerate a segment loss probabil-
ity of 2 · 10–10 (or equivalently, one loss event for every 5,000,000,000 segments)—
a very low rate. This observation has led a number of researchers to investigate new
versions of TCP that are specifically designed for such high-speed environments;
see [Jin 2004; RFC 3649; Kelly 2003; Ha 2008] for discussions of these efforts.

An area of
research today is thus the development of congestion-control mechanisms for the
Internet that prevent UDP traffic from bringing the Internet’s throughput to a grind-
ing halt [Floyd 1999; Floyd 2000; Kohler 2006].

see [Molinero-Fernandez 2002] for an interesting comparison of the complexity 
of circuit- versus packet-switched networks

http://web.cecs.pdx.edu/~jrb/ui/