Abstract

The congestion control provided by Transmission Control Protocol (TCP) plays a key role in ensuring network stability and increased Quality of Service (QoS). However, in the face of the increasing number of high-speed networks such as Multi-protocol Label Switching with band-width width reservation, conventional congestion control algorithms limit the network resource utilization efficiency since they overreact to packet loss. This paper proposes a new TCP congestion control scheme that improves the goodput by using reserved bandwidth to set the slow start threshold and the congestion window after a timeout or three duplicate acknowledgments. The advantage of this algorithm is that the TCP sender recovers faster after packet loss, especially when the connections have large round trip times; it avoids Reno's overreaction to loss.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call