Reinforcement Learning for Power Management in Low-margin Optical Networks
Paper in proceeding, 2024
We explore the Q-learning and Proximal Policy Optimization (PPO) algorithms for solving the Routing, Wavelength, and Power Allocation (RWPA) problem. The results indicate that reinforcement learning can significantly optimize launch power in low-margin optical networks, with Q-learning achieving better results than PPO, delivering improvement in GSNR of over 175 % and over 48 % in small and large networks, respectively.
q-learning
power management
optical networks
Author
Sze Ka Tse
Northeastern University
Xiaoyang Zhao
Northeastern University
Anita Chan
Northeastern University
Di Tang
Northeastern University
Aanchan Mohan
Northeastern University
Carlos Natalino Da Silva
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Michal Aibin
British Columbia Institute of Technology
Northeastern University
International Conference on Transparent Optical Networks
21627339 (ISSN)
9798350377309 (ISBN)
24th International Conference on Transparent Optical Networks, ICTON 2024
Bari, Italy,
Bari, Italy,
Subject Categories (SSIF 2011)
Telecommunications
DOI
10.1109/ICTON62926.2024.10647982