MAGC-RSA: multi-agent graph convolutional reinforcement learning for distributed routing and spectrum assignment in elastic optical networks - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

MAGC-RSA: multi-agent graph convolutional reinforcement learning for distributed routing and spectrum assignment in elastic optical networks

Résumé

This paper proposes MAGC-RSA, a Multi-Agent Graph Convolutional Reinforcement Learning approach, to solve the Routing and Spectrum Assignment (RSA) problem in a distributed manner. A blocking probability reduction of 80% can be achieved compared to the Shortest Path First-Fit approach.
Fichier non déposé

Dates et versions

hal-03973109 , version 1 (03-02-2023)

Identifiants

  • HAL Id : hal-03973109 , version 1

Citer

Huy Tran Quang, Omar Houidi, Javier Errea-Moreno, Dominique Verchère, Djamal Zeghlache. MAGC-RSA: multi-agent graph convolutional reinforcement learning for distributed routing and spectrum assignment in elastic optical networks. 2022 European Conference on Optical Communication (ECOC), Sep 2022, Basel, Switzerland. pp.Mo4B.3. ⟨hal-03973109⟩
35 Consultations
0 Téléchargements

Partager

More