8th International Conference on Machine Learning for Networking (MLN'2025)
Keynote: Nour El-Houda Yellas, Associate Professor at Télécom SudParis, France
Title: Closed Loop Automation System for B5G and 6G networks
Abstract
In this talk, I present a work on closed-loop automation system that leverages AI to automatically mitigate anomalous states in the connect-compute software infrastructure. This work describes the key components of the automation system, including: an anomaly detection module based on federated learning; AI function scheduling to meet detection performance targets while mitigating federated learning stragglers; and a data-pipeline design that supports high accuracy, real-time preprocessing, and timely data delivery.
Biography
Nour-El-Houda Yellas is an Associate Professor at Télécom SudParis since December 2024. She obtained the Ph.D. degree in Computer Science from Cnam, Paris in 2023. She was a postdoctoral researcher at Orange Innovation from January 2024 to November 2024 and served as a teaching assistant at Sorbonne University from September 2022 to January 2024. Her research focuses primarily on the automation and optimization of Beyond 5G mobile network orchestration within multi-access edge computing (MEC) infrastructures, leveraging data analytics techniques.