PhD defense Isaia Andrenacci: Leveraging machine learning for efficient and secure optical networking
Wednesday 06 May, 2026, at 09:30 (Paris time) at Télécom Paris
Télécom Paris, 19 place Marguerite Perey F-91120 Palaiseau [getting there], amphi 5 and in videoconferencing
Jury
- Massimo Tornatore – Professor, Politecnico di Milano – Reviewer
- Christelle Aupetit-Berthelemot – Professor, ENSIL-ENSCI – Reviewer
- Ghaya Rekaya-Ben Othman – Professor, Télécom Paris – Examiner
- Vincent Choqueuse – Associate Professor, ENIB – Examiner
- Claire Goursaud – Associate Professor, INSA Lyon – Examiner
- Walid Hachem – Research Director, CNRS, Université Gustave Eiffel – Examiner
- Élie Awwad – Associate Professor, Télécom Paris – Co-supervisor
- Ekhiñe Irurozki – Associate Professor, Télécom Paris – Co-supervisor
- Petros Ramantanis – Research Engineer, Nokia Bell Labs – Co-supervisor
- Stéphan Clémençon – Professor, Télécom Paris – PhD supervisor
Abstract
Future optical networks must cope with rapidly increasing traffic demands while operating close to fundamental capacity limits, making efficient resource utilization increasingly critical. Massive monitoring and telemetry have emerged as promising solutions for more autonomous and adaptive network operation. In this PhD, I investigate machine learning–based techniques leveraging receiver-side measurements and optical network parameters to improve the efficiency, reliability, and security of point-to-point optical links.
Learn more
I propose models to accurately predict nonlinear interference, as well as closed-loop controllers to optimize launch power in the presence of polarization-dependent loss. I also introduce low-cost monitoring techniques to localize impairments and identify dominant noise sources. Finally, I propose a method to quantify fiber macro-bending events, enabling future discrimination between maintenance operations and physical-layer attacks. This work demonstrates that machine learning combined with pervasive monitoring can pave the way toward intelligent, autonomous, and secure optical networks.