Throughput prediction in wireless networks using statistical learning - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Throughput prediction in wireless networks using statistical learning

Résumé

The focus of this work is on the estimation of throughput in wireless networks, more specificaly on IEEE 802.11. Our proposal is based on active measurements and statistical learning tools. We present a methodology where the system is trained during short periods with application flows and probe packets bursts. We learn the relation between throughput obtained by the application and the state of the network, which is inferred from the interarrival times of the probe packets bursts. As a result we obtain a continuous non intrusive methodology that allows to determine the maximum throughput of a wireless connection only knowing some characteristics of the network. We use Support Vector Machines (SVM) for regression and we show results obtained by simulations.
Fichier principal
Vignette du fichier
lawdn2010_submission_2.pdf (117.93 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00531743 , version 1 (03-11-2010)

Identifiants

  • HAL Id : inria-00531743 , version 1

Citer

Claudina Rattaro, Pablo Belzarena. Throughput prediction in wireless networks using statistical learning. LAWDN - Latin-American Workshop on Dynamic Networks, INTECIN - Facultad de Ingeniería (U.B.A.) - I.T.B.A., Nov 2010, Buenos Aires, Argentina. 4 p. ⟨inria-00531743⟩

Collections

LAWDN-2010
163 Consultations
337 Téléchargements

Partager

Gmail Facebook X LinkedIn More