Modeling TCP Reno performance: a simple model and its empirical validation
IEEE/ACM Transactions on Networking (TON)
Equation-based congestion control for unicast applications
Proceedings of the conference on Applications, Technologies, Architectures, and Protocols for Computer Communication
A decision-theoretic generalization of on-line learning and an application to boosting
EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
Efficiency/Friendliness Tradeoffs in TCP Westwood
ISCC '02 Proceedings of the Seventh International Symposium on Computers and Communications (ISCC'02)
Distinguishing Congestion Losses from Wireless Transmission Losses: A Negative Result
IC3N '98 Proceedings of the International Conference on Computer Communications and Networks
BRITE: A Flexible Generator of Internet Topologies
BRITE: A Flexible Generator of Internet Topologies
I-TCP: indirect TCP for mobile hosts
ICDCS '95 Proceedings of the 15th International Conference on Distributed Computing Systems
Modeling wireless links for transport protocols
ACM SIGCOMM Computer Communication Review
A Machine Learning Approach to Improve Congestion Control over Wireless Computer Networks
ICDM '04 Proceedings of the Fourth IEEE International Conference on Data Mining
A report on recent developments in TCP congestion control
IEEE Communications Magazine
TCP Veno: TCP enhancement for transmission over wireless access networks
IEEE Journal on Selected Areas in Communications
Machine-learnt versus analytical models of TCP throughput
Computer Networks: The International Journal of Computer and Telecommunications Networking
On the accuracy of analytical models of TCP throughput
NETWORKING'06 Proceedings of the 5th international IFIP-TC6 conference on Networking Technologies, Services, and Protocols; Performance of Computer and Communication Networks; Mobile and Wireless Communications Systems
| Hi-index | 0.00 |
TCP understands all packet losses as buffer overflows and reacts to such congestions by reducing its rate. In hybrid wired/wireless networks where a non negligible number of packet losses are due to link errors, TCP is unable to sustain a reasonable rate. In this paper, we propose to extend TCP Newreno with a packet loss classifier built by a supervised learning algorithm called 'decision tree boosting'. The learning set of the classifier is a database of 25,000 packet loss events in a thousand of random topologies. Since a limited percentage of wrong classifications of congestions as link errors is allowed to preserve TCP-Friendliness, our protocol computes this constraint dynamically and tunes a parameter of the classifier accordingly to maximise the TCP rate. Our classifier outperforms the Veno and Westwood classifiers by achieving a higher rate in wireless networks while remaining TCP-Friendly.