Survey on machine learning for traffic-driven service provisioning in optical networks

T Panayiotou, M Michalopoulou… - … Surveys & Tutorials, 2023 - ieeexplore.ieee.org
The unprecedented growth of the global Internet traffic, coupled with the large spatio-
temporal fluctuations that create, to some extent, predictable tidal traffic conditions, are …

On deep reinforcement learning for static routing and wavelength assignment

N Di Cicco, EF Mercan, O Karandin… - IEEE Journal of …, 2022 - ieeexplore.ieee.org
Deep Reinforcement Learning (DRL) is rising as a promising tool for solving optimization
problems in optical networks. Though studies employing DRL for solving static optimization …

An overview of ML-based applications for next generation optical networks

R Gao, L Liu, X Liu, H Lun, L Yi, W Hu… - Science China Information …, 2020 - Springer
Over the past few decades, the demand for the capacity and reliability of optical networks
has continued to grow. In the meantime, optical networks with larger knowledge scales have …

Deep reinforcement learning for comprehensive route optimization in elastic optical networks using generative strategies.

PN Renjith, G Sujatha, M Vinoth… - Optical & Quantum …, 2023 - search.ebscohost.com
The latest advances in Deeper Reinforcement Learning (DRL) have completely changed
how decision-making and automatic control issues are solved. The study community …

Resource allocation in multicore elastic optical networks: a deep reinforcement learning approach

J Pinto-Ríos, F Calderón, A Leiva, G Hermosilla… - …, 2023 - Wiley Online Library
A deep reinforcement learning (DRL) approach is applied, for the first time, to solve the
routing, modulation, spectrum, and core allocation (RMSCA) problem in dynamic multicore …

Deep reinforcement learning-based RMSA policy distillation for elastic optical networks

B Tang, YC Huang, Y Xue, W Zhou - Mathematics, 2022 - mdpi.com
The reinforcement learning-based routing, modulation, and spectrum assignment has been
regarded as an emerging paradigm for resource allocation in the elastic optical networks …

Routing and spectrum assignment employing long short-term memory technique for elastic optical networks

L Cheng, Y Qiu - Optical Switching and Networking, 2022 - Elsevier
With the prevalence of some high bandwidth-demanding applications, such as cloud
computing, traditional wavelength-division-multiplexing passive optical networks have …

Multi-agent and cooperative deep reinforcement learning for scalable network automation in multi-domain SD-EONs

B Li, R Zhang, X Tian, Z Zhu - IEEE Transactions on Network …, 2021 - ieeexplore.ieee.org
The service provisioning in multi-domain software-defined elastic optical networks (SD-
EONs) is an interesting but difficult problem to tackle, because the basic problem of lightpath …

Traffic-based adaptive bandwidth adjustment for flexible OTN connectivity in optical networks

Q Hu, W Wang, L Hu, Y Li, Y Zhao, J Zhang - Optics Express, 2023 - opg.optica.org
In conventional optical transport networks, the service form is the fixed bandwidth
connectivity, which is not flexible for carrying bursting traffic. To support the time-varying …

OpticGAI: Generative AI-aided Deep Reinforcement Learning for Optical Networks Optimization

S Li, X Lin, Y Liu, G Li, J Li - Proceedings of the 1st SIGCOMM Workshop …, 2024 - dl.acm.org
Deep Reinforcement Learning (DRL) is regarded as a promising tool for optical network
optimization. However, the flexibility and efficiency of current DRL-based solutions for optical …