Reinforcement-Learning-based Network Design and Control with Stepwise Reward Variation and Link-Adjacency Embedding

Kenji Cruzado; Ryuta Shiraki; Yojiro Mori; Takafumi Tanaka; Katsuaki Higashimori; Fumikazu Inuzuka; Takuya Ohara; Hiroshi Hasegawa

European Conference on Optical Communication (ECOC) 2022
Technical Digest Series (Optica Publishing Group, 2022),
paper We2B.3

Reinforcement-Learning-based Network Design and Control with Stepwise Reward Variation and Link-Adjacency Embedding

Kenji Cruzado, Ryuta Shiraki, Yojiro Mori, Takafumi Tanaka, Katsuaki Higashimori, Fumikazu Inuzuka, Takuya Ohara, and Hiroshi Hasegawa

European Conference and Exhibition on Optical Communication 2022

Basel Switzerland
18–22 September 2022
ISBN: 978-1-957171-15-9

From the session
Control Plane and Automation (We2B)

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
K. Cruzado, R. Shiraki, Y. Mori, T. Tanaka, K. Higashimori, F. Inuzuka, T. Ohara, and H. Hasegawa, "Reinforcement-Learning-based Network Design and Control with Stepwise Reward Variation and Link-Adjacency Embedding," in European Conference on Optical Communication (ECOC) 2022, J. Leuthold, C. Harder, B. Offrein, and H. Limberger, eds., Technical Digest Series (Optica Publishing Group, 2022), paper We2B.3.

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Save article

Abstract

We propose a reinforcement-learning-based network design and control algorithm that introduces reward variation dependent on maximum link utilization and link-adjacency embedding as input parameters. Up to 65%/20% capacity enhancement relative to first-fit and link-congestion-aware methods is verified.

PDF Article

More Like This

Reinforcement-Learning-based Multilayer Path Planning Framework that Designs Grooming, Route, Spectrum, and Operational Mode

Takafumi Tanaka and Katsuaki Higashimori
We5.59 European Conference and Exhibition on Optical Communication (ECOC) 2022

Deep Reinforcement Learning-based Spectrum Assignment with Multi-metric Reward Function and Assignable Boundary Slot Mask

Masayuki Shimoda and Takafumi Tanaka
M4B.3 Optoelectronics and Communications Conference (OECC) 2021

Evaluation of Deep Reinforcement Learning for Restoration in Optical Networks

C. Hernández-Chulde, R. Casellas, R. Martínez, R. Vilalta, and R. Muñoz
Th2A.19 Optical Fiber Communication Conference (OFC) 2022

Previous Article Next Article