Comparing TCP Congestion Control Algorithms Based on Passively Collected Packet Traces

Recently, traffic in the Internet increases largely according to the improvement of network capacity. However, it is sometimes pointed out that a small number of giant users exhaust large part of network bandwidth. In order to resolve such problems, a practical way is to suppress large traffic flows which do not conform to Transmission Control Protocol (TCP) congestion control algorithms. For this purpose, the network operators need to infer congestion control algorithms of individual TCP flows using passively monitored packet traces in the middle of networks. On the other hand, a lot of TCP congestion control mechanisms have been introduced recently. Although there are several proposals on inferring them, no schemes are proposed which can analyze recently introduced TCP congestion control algorithms based on the passive approach. This paper proposes a new passive scheme to compare most of recently proposed congestion control algorithms. It estimates the congestion window size (cwnd) at a TCP sender at round-trip time intervals, and specifies the cwnd growth as a function of the estimated value of cwnd and the cwnd decrease parameter at individual congestion events. This paper shows the results of applying our scheme to eight congestion control algorithms and shows that they can be identified from passively monitored traces. KeywordsTCP congestion control; passive monitoring; congestion window.