Multi-band Environments for Optical Reinforcement Learning Gym for Resource Allocation in Elastic Optical Networks

Patricia Morales, Patricia Franco, Astrid Lozada, Nicolas Jara, Felipe Calderon, Juan Pinto-Rios, Ariel Leiva

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The use of additional fiber bands for optical communications-known as Multi-band or Band-division multiplexing (BDM)-allows to increase the traffic served in transparent optical networks. In recent years, many proposals have emerged as a solution for resource allocation in such multi-band architectures. This work presents a novel approach based on reinforcement learning (RL) techniques to accommodate multi-band elastic optical network resources. Two new environments were implemented and added to the Optical-RL-Gym toolkit considering four scenarios with different band availability. Six agents were tested in four real network topologies, contrasting their episode rewards on a large number of training steps. Results show Trust Region Policy Optimization (TRPO) as the best performing agent, with consistent output across all the scenarios and network topologies considered. In addition, we illustrate the blocking probability behavior in relation to the traffic load, and band usage distribution, allowing further discussions.

Original languageEnglish
Title of host publication25th International Conference on Optical Network Design and Modelling, ONDM 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9783903176331
DOIs
StatePublished - 28 Jun 2021
Externally publishedYes
Event25th International Conference on Optical Network Design and Modelling, ONDM 2021 - Gothenburg, Sweden
Duration: 28 Jun 20211 Jul 2021

Publication series

Name25th International Conference on Optical Network Design and Modelling, ONDM 2021

Conference

Conference25th International Conference on Optical Network Design and Modelling, ONDM 2021
Country/TerritorySweden
CityGothenburg
Period28/06/211/07/21

Keywords

  • multi-band optical networks
  • reinforcement learning
  • resource allocation

Fingerprint

Dive into the research topics of 'Multi-band Environments for Optical Reinforcement Learning Gym for Resource Allocation in Elastic Optical Networks'. Together they form a unique fingerprint.

Cite this