Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Attention Networks for Time Series Regression and Application to Congestion Control

Abstract : This paper studies a new attention-based recurrent architecture, lighter and less computationally expensive than a global attention network. This type of architecture achieves better performance than commonly used recurrent networks for time series regression. An application to congestion control is considered, where the history of round trip times (RTT) evolution history is used to monitor congestion control. The performance of the proposed new congestion control strategy is evaluated with both synthetic and real traces, showing that it can be efficiently used to estimate the congestion state of a network.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-03668711
Contributeur : Emmanuel Lochin Connectez-vous pour contacter le contributeur
Soumis le : lundi 16 mai 2022 - 08:37:00
Dernière modification le : lundi 4 juillet 2022 - 09:29:47

Fichier

Attention_IFIP.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-03668711, version 1

Collections

Citation

Victor Perrier, Emmanuel Lochin, Jean-yves Tourneret, Patrick Gélard. Attention Networks for Time Series Regression and Application to Congestion Control. The 4th International Workshop on Network Intelligence in conjunction with IFIP Networking, Jun 2022, Catania, Italy. ⟨hal-03668711⟩

Partager

Métriques

Consultations de la notice

21

Téléchargements de fichiers

5