Abstract
We propose a reinforcement-learning-based multilayer path planning framework that designs grooming and optical path parameters. Simulation results show that the proposed method can improve blocking probability by 20 % compared to conventional heuristic methods.
© 2022 The Author(s)
PDF ArticleMore Like This
Takafumi Tanaka
Tu2D.6 Optical Fiber Communication Conference (OFC) 2023
Huy Tran Quang, Omar Houidi, Javier Errea-Moreno, Dominique Verchere, and Djamal Zeghlache
Mo4B.3 European Conference and Exhibition on Optical Communication (ECOC) 2022
Abdennour Ben Terki, Joao Pedro, Antonio Eira, Antonio Napoli, and Nicola Sambo
Tu5.63 European Conference and Exhibition on Optical Communication (ECOC) 2022