Project Description:
Over the past few years, telecommunications networks have migrated towards concepts of virtualisation and programmability, which has recently also affected the optical layer [1]. This has provided the opportunity to build more intelligent control of optical networks, for example to predict quality of transmission and thus improve overall network utilisation, as transmission channels can be setup to match the expected optical signal to noise ratio.
A key milestone is the development of digital twins, that are able to represent the network behaviour and thus test algorithms and configurations in a safe environment, before launching them into production.
Goal:
The goal of this project is to design ML algorithms, including transfer learning paradigms, to represent the behaviour of optical devices. The student will have access to data and experimental setups from the OpenIreland testbed located in TCD .
[1] JOCN Special Issue on Open Optical Networks. Journal of Optical Communications and Networking ( Volume: 12, Issue: 6, June 2020)