Abstract
ULg Research Unit in Networking RUN
Abstract


Improving TCP in wireless networks with an adaptive machine-learnt classifier of packet loss causes

I. El Khayat2 , P. Geurts1 and G. Leduc2

1 Stochastic Methods research unit, EECS department, University of Liège, Belgium
2 Research unit in Networking, EECS department, University of Liège, Belgium

(2005)

Abstract

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.

Keywords

Machine Learning, TCP, Wireless

[ Home | People | Research Topics | Projects | Publications | IFIP WG 6.1 | Events and Conferences | CSS | How to Reach Us ]

Editor: - G. Leduc -
Webmaster: - C. Soldani -
Still running IPv4 at: 54.146.50.80... RUN | Montefiore | ULg
© 2000-2015.