In TCP, congestion control as well as error recovery are implemented by a s
liding window. The dynamics of TCP specifically, a mismatch between the TCP
window and the bandwidth-delay product of the network can sometimes cause
the network switches or routers to accumulate large queues, resulting in bu
ffer overflows, reduced throughput, unfairness and underutilization. It is
generally accepted that there is a limit to how much control can be accompl
ished from the congestion control mechanisms in the end systems. Some mecha
nisms are needed in the intermediate network elements to complement the end
point congestion avoidance mechanisms. We describe in this paper, a new TCP
rate control scheme based on a simple recursive algorithm. The idea behind
the algorithm is to match the offered network load to the available resour
ces by modifying at an intermediate network element, the receiver's adverti
sed window in TCP acknowledgments returning to the source. We show through
simulations that the scheme can efficiently control TCP traffic to limit qu
eue buildups and buffer requirements at the network nodes, resulting in sig
nificant improvements in delay, packet loss rates, fairness in the distribu
tion of the maximum achievable window size, and link utilization. (C) 2001
Elsevier Science B.V. All rights reserved.