References of "El Khayat, Ibtissam"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailEnhancement of TCP over wired/wireless networks with packet loss classifiers inferred by supervised learning
El Khayat, Ibtissam; Geurts, Pierre ULg; Leduc, Guy ULg

in Wireless Networks (2010), 16(2), 273-290

TCP is suboptimal in heterogeneous wired/wireless networks because it reacts in the same way to losses due to congestion and losses due to link errors. In this paper, we propose to improve TCP performance ... [more ▼]

TCP is suboptimal in heterogeneous wired/wireless networks because it reacts in the same way to losses due to congestion and losses due to link errors. In this paper, we propose to improve TCP performance in wired/wireless networks by endowing it with a classifier that can distinguish packet loss causes. In contrast to other proposals we do not change TCP’s congestion control nor TCP’s error recovery. A packet loss whose cause is classified as link error will simply be ignored by TCP’s congestion control and recovered as usual, while a packet loss classified as congestion loss will trigger both mechanisms as usual. To build our classification algorithm, a database of pre-classified losses is gathered by simulating a large set of random network conditions, and classification models are automatically built from this database by using supervised learning methods. Several learning algorithms are compared for this task. Our simulations of different scenarios show that adding such a classifier to TCP can improve the throughput of TCP substantially in wired/wireless networks without compromizing TCP-friendliness in both wired and wireless environments. [less ▲]

Detailed reference viewed: 101 (13 ULg)
Full Text
Peer Reviewed
See detailMachine-learnt versus analytical models of TCP throughput
El Khayat, Ibtissam; Geurts, Pierre ULg; Leduc, Guy ULg

in Computer Networks (2007), 51(10), 2631-2644

We first study the accuracy of two well-known analytical models of the average throughput of long-term TCP flows, namely the so-called SQRT and PFTK models, and show that these models are far from being ... [more ▼]

We first study the accuracy of two well-known analytical models of the average throughput of long-term TCP flows, namely the so-called SQRT and PFTK models, and show that these models are far from being accurate in general. Our simulations, based on a large set of long-term TCP sessions, show that 70% of their predictions exceed the boundaries of TCP-Friendliness, thus questioning their use in the design of new TCP-Friendly transport protocols. We then investigate the reasons of this inaccuracy, and show that it is largely due to the lack of discrimination between the two packet loss detection methods used by TCP, namely by triple duplicate acknowledgements or by timeout: expirations. We then apply various machine learning techniques to infer new models of the average TCP throughput. We show that they are more accurate than the SQRT and PFTK models, even without the above discrimination, and are further improved when we allow the machine-learnt models to distinguish the two loss detection techniques. Although our models are not analytical formulas, they can be plugged in transport protocols to make them TCP-Friendly. Our results also suggest that analytical models of the TCP throughput should certainly benefit from the incorporation of the timeout loss rate. (C) 2006 Elsevier B.V. All rights reserved. [less ▲]

Detailed reference viewed: 35 (3 ULg)
Full Text
Peer Reviewed
See detailOn the accuracy of analytical models of TCP throughput
El Khayat, Ibtissam; Geurts, Pierre ULg; Leduc, Guy ULg

in Lecture Notes in Computer Science (2006, May), 3976

Based on a large set of TCP sessions we first study the accuracy of two well-known analytical models (SQRT and PFTK) of the TCP average rate. This study shows that these models are far from being accurate ... [more ▼]

Based on a large set of TCP sessions we first study the accuracy of two well-known analytical models (SQRT and PFTK) of the TCP average rate. This study shows that these models are far from being accurate on average. Actually, our simulations show that 70% of their predictions exceed the boundaries of TCP-Friendliness, thus questioning their use in the design of new TCP-Friendly transport protocols. Our study also shows that the inaccuracy of the PFTK model is largely due to its inability to make the distinction between the two packet loss detection methods used by TCP: triple duplicate acknowledgments or timeout expirations. We then use supervised learning techniques to infer models of the TCP rate. These models show important accuracy improvements when they take into account the two types of losses. This suggests that analytical model of TCP throughput should certainly benefit from the incorporation of the timeout loss rate. [less ▲]

Detailed reference viewed: 29 (1 ULg)
Full Text
Peer Reviewed
See detailImproving TCP in wireless networks with an adaptive machine-learnt classifier of packet loss causes
El Khayat, Ibtissam; Geurts, Pierre ULg; Leduc, Guy ULg

in Lecture Notes in Computer Science (2005, May), 3462

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 ... [more ▼]

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. [less ▲]

Detailed reference viewed: 30 (5 ULg)
Full Text
Peer Reviewed
See detailA Machine Learning Approach to Improve Congestion Control over Wireless Computer Networks
Geurts, Pierre ULg; El Khayat, Ibtissam; Leduc, Guy ULg

(2004, November)

In this paper, we present the application of machine learning techniques to the improvement of the congestion control of TCP in wired/wireless networks. TCP is suboptimal in hybrid wired/wireless networks ... [more ▼]

In this paper, we present the application of machine learning techniques to the improvement of the congestion control of TCP in wired/wireless networks. TCP is suboptimal in hybrid wired/wireless networks because it reacts in the same way to losses due to congestion and losses due to link errors. We thus propose to use machine learning techniques to build automatically a loss classifier from a database obtained by simulations of random network topologies. Several machine learning algorithms are compared for this task and the best method for this application turns out to be decision tree boosting. It outperforms ad hoc classifiers proposed in the networking literature. [less ▲]

Detailed reference viewed: 46 (3 ULg)
Full Text
Peer Reviewed
See detailSmoothing the TCP rate by learning the delay versus window size dependency
El Khayat, Ibtissam; Leduc, Guy ULg

in Lecture Notes in Computer Science (2003), 2899

We propose TCP-L, an improved version of TCP, equipped with a learning algorithm whose purpose is to avoid probing for additional bandwidth when the network conditions are known to be unfavourable. TCP-L ... [more ▼]

We propose TCP-L, an improved version of TCP, equipped with a learning algorithm whose purpose is to avoid probing for additional bandwidth when the network conditions are known to be unfavourable. TCP-L learns the relationship between its current (average) one-trip delay and its current window size when congestion occurs, leading to packet loss. After the learning phase, TCP-L will only probe for bandwidth by increasing its window if, under the current network conditions (measured by the one-trip delay), this inflated window has not previously created congestion. Simulations show that after the learning phase, TCP-L reaches a much more stable throughput, while remaining TCP-friendly, which makes it usable for a larger class of applications, including some multimedia applications that will benefit from that stability. TCP-L is a simple backward compatible extension of TCP which can thus be deployed progressively. We show that there is a benefit for the Internet to deploy TCP-L, because the overall traffic becomes smoother when the proportion of TCP-L flows increases. Finally, our learning component can also be easily embedded in other unicast or multicast transport protocols. [less ▲]

Detailed reference viewed: 32 (4 ULg)
Full Text
Peer Reviewed
See detailA Stable and Flexible TCP-friendly congestion control protocol for layered multicast transmission
El Khayat, Ibtissam; Leduc, Guy ULg

in Lecture Notes in Computer Science (2001, September 04), 2158

We propose an improvement of our RLS (Receiver-driven Layered multicast with Synchronization points) protocol, called CIFL for “Coding-Independent Fair Layered mulaticast”, along two axes. In CIFL, each ... [more ▼]

We propose an improvement of our RLS (Receiver-driven Layered multicast with Synchronization points) protocol, called CIFL for “Coding-Independent Fair Layered mulaticast”, along two axes. In CIFL, each receiver of a layered multicast transmission will try and find the adequate number of layers to subscribe to, so that the associated throughput is fair towards TCP and stable in steady-state. The first improvement is that CIFL is not specific to any coding scheme. It can work as well with an exponentially distributed set of layers (where the throughput of each layer i equals the sum of the throughputs of all layers below i), or with layers of equal throughputs, or any other scheme. The second improvement is the excellent stability of the protocol which avoids useless join attempts by learning from its unsuccessful previous attempts in the same (or better) network conditions. Moreover, the protocol tries and reaches its ideal TCP-friendly as soon as possible by computing its target throughput in a clever way when an incipient congestion is confirmed. [less ▲]

Detailed reference viewed: 18 (1 ULg)
Full Text
See detailContrôle de congestion pour la transmission multipoint en couches
El Khayat, Ibtissam; Leduc, Guy ULg

Conference (2000, November 06)

Le contrôle de congestion en transmission multipoints est rendu difficile par l'hétérogénéité des récepteurs. En effet, pour la transmission vidéo par exemple, il serait peu raisonnable que l'émetteur ... [more ▼]

Le contrôle de congestion en transmission multipoints est rendu difficile par l'hétérogénéité des récepteurs. En effet, pour la transmission vidéo par exemple, il serait peu raisonnable que l'émetteur adapte son débit en fonction du récepteur le moins performant ou de celui qui subit temporairement la congestion la plus sévère. Pour contourner ce problème, l'émetteur peut émettre un flux structuré en couches, de telle sorte que la couche de base donne une qualité minimale et que les couches suivantes améliorent successivement cette qualité. L'algorithme de contrôle de congestion proposé est basé sur ce schéma. Il permet à chaque récepteur de sélectionner dynamiquement un sous-ensemble adéquat de couches en répondant aux objectifs suivants. Premièrement, l'algorithme doit être équitable vis-à-vis de TCP; ce qui signifie que les débits du flux multicouches reçu et celui d'un flux TCP placé dans les mêmes conditions doivent être plus ou moins les mêmes. Deuxièmement, les récepteurs doivent être suffisamment coordonnés pour qu'une congestion résultant de l'ajout d'une couche par l'un d'eux ne puisse être interprétée par un autre récepteur comme une congestion résultant de ses propres décisions ou d'un trafic perturbateur. Enfin, lorsque deux sessions multicouches empruntent un même goulet, nous souhaitons que les récepteurs obtiennent le même débit, ce qui signifiera en général des nombres de couches différents si les débits des couches sont distincts. [less ▲]

Detailed reference viewed: 37 (0 ULg)
Peer Reviewed
See detailCongestion Control for Layered Multicast Transmission
El Khayat, Ibtissam; Leduc, Guy ULg

in Networking and Information Systems Journal (2000), 3(3-4), 559-573

Heterogeneity of receivers makes it hard to control congestion for multicast transmission. Using hierarchical layering of the information is one of the most elegant and efficient approach to tackle this ... [more ▼]

Heterogeneity of receivers makes it hard to control congestion for multicast transmission. Using hierarchical layering of the information is one of the most elegant and efficient approach to tackle this problem. The proposed algorithm is based on this principle and has three objectives: to fulfill intra-session fairness, i.e. between different receivers of the same session; to be fair towards TCP; to fulfill inter-session fairness, i.e. same throughputs (and not number of layers) to concurrent sessions. [less ▲]

Detailed reference viewed: 23 (0 ULg)