Graph Convolutional Reinforcement Learning for Load Balancing and Smart Queuing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Graph Convolutional Reinforcement Learning for Load Balancing and Smart Queuing

Hassan Fawaz
Omar Houidi
  • Fonction : Auteur
  • PersonId : 1042003
Julien Lesca
  • Fonction : Auteur
Pham Tran Anh Quang
  • Fonction : Auteur
Jérémie Leguay
  • Fonction : Auteur
Paolo Medagliani
  • Fonction : Auteur

Résumé

In this paper, we propose a graph convolutional deep reinforcement learning framework for both smart load balancing and queuing agents in a collaborative environment. We aim to balance traffic loads on different paths, and then control how packets belonging to different flow classes are dequeued at network nodes. Our objective is twofold: first to improve general network performance in terms of throughput and end-to-end delay, and second, to ensure meeting stringent service level agreements for a set of classified network flows. Our proposals use attention mechanisms to extract relevant features from local observations and neighborhood policies to limit the overhead of inter-agent communications. We assess our algorithms in a Mininet testbed and show that they outperform classic approaches to load balancing and smart queuing in terms of throughput and end-to-end delay.
Fichier principal
Vignette du fichier
Graph_Convolutional_Reinforcement_Learning_for_Load_Balancing_and_Smart_Queuing_IEEE.pdf (1.1 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04389446 , version 1 (11-01-2024)

Identifiants

Citer

Hassan Fawaz, Omar Houidi, Djamal Zeghlache, Julien Lesca, Pham Tran Anh Quang, et al.. Graph Convolutional Reinforcement Learning for Load Balancing and Smart Queuing. 2023 IFIP Networking Conference (IFIP Networking), Jun 2023, Barcelona, France. pp.1-9, ⟨10.23919/IFIPNetworking57963.2023.10186430⟩. ⟨hal-04389446⟩
8 Consultations
18 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More