Reinforcement learning for compensating power excursions in amplified WDM systems - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Lightwave Technology Année : 2021

Reinforcement learning for compensating power excursions in amplified WDM systems

Résumé

Wavelength-dependent power excursions in gaincontrolled erbium doped fiber amplifiers (EDFA) is a challenging issue in optical networks. We investigate a launch channel power control method using reinforcement learning (RL) to mitigate the power excursions of EDFA systems. A machine learning engine is developed, trained and evaluated with four different policygradient RL algorithms that are compared according to two main criteria: achieved power excursion reduction and learning time. Different scenarios are considered with 12-, 24-, 40-active channels at fixed wavelengths and with variable number of active channels (between 12 and 64) assigned randomly at different wavelengths during RL process. We show 62% power excursion reduction in the 40-channel scenario and 28% in the variable scenario, which demonstrates the promising role of online RL approach for controlling power excursion in EDFA systems.

Dates et versions

hal-04304793 , version 1 (28-11-2023)

Identifiants

Citer

Maria José Freire Hermelo, Dipankar Sengupta, Antoine Lavignotte, Christine Tremblay, Catherine Lepers. Reinforcement learning for compensating power excursions in amplified WDM systems. Journal of Lightwave Technology, 2021, 39 (21), pp.6805 - 6813. ⟨10.1109/jlt.2021.3107774⟩. ⟨hal-04304793⟩
13 Consultations
1 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More