Congestion avoidance and control
SIGCOMM '88 Symposium proceedings on Communications architectures and protocols
Promoting the use of end-to-end congestion control in the Internet
IEEE/ACM Transactions on Networking (TON)
Experimental investigations into TCP performance over wireless multihop networks
Proceedings of the 2005 ACM SIGCOMM workshop on Experimental approaches to wireless network design and analysis
Design, implementation and evaluation of a QoS-aware transport protocol
Computer Communications
A Study on the Benefit of TCP Packet Prioritisation
PDP '09 Proceedings of the 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing
VoIP cross-layer load control for hybrid satellite-WiMAX networks
IEEE Wireless Communications
| Hi-index | 0.00 |
TFRC protocol has not been designed to enable reliability. Indeed, the birth of TFRC results from the need of a congestion controlled and realtime transport protocol in order to carry multimedia traffic. Historically, and following the anarchical deployment of congestion control mechanisms implemented on top of UDP protocol, the IETF decided to standardize such protocol in order to provide to multimedia applications developers a framework for their applications. In this paper, we propose to design a reliable rate-based transport protocol based on TFRC. This design is motivated by finding an alternative to TCP where its oscillating behaviour is known to be counterproductive over certain networks such as VANET. However, we found interesting results partly inherited from the smooth behaviour of TFRC in the context of wired networks. In particular, we show that TFRC can realize shorter data transfer compare to TCP over a complex and realistic topology. We firstly detail and fully benchmark our protocol in order to verify that our resulting prototype inherits from the good properties of TFRC in terms of TCP-friendliness. As a second contribution, we also propose a ns-2 implementation for testing purpose to the networking community. Following these preliminary tests, we drive a set of non-exhaustive experiments to illustrate some interesting behaviour of this protocol in the context of wired networks.