PhD defense of Guillaume Terrier (December 07th, 2026)

Guillaume Terrier will defend his doctoral thesis, entitled Artificial Intelligence and Resource Allocation in Wireless Networks, on Monday, December 7th, 2026 at 9:30 at IRISA, room Métivier (C024).

This thesis was made in the framework of the ANR SAFE.

Wireless networks must handle an increasing number of user devices, a growing diversity of services, all while operating with limited radio resources subject to channel fluctuations. Radio resource scheduling plays a pivotal role in balancing spectral efficiency, Quality of Service (QoS) and energy consumption.

This thesis first examines the mechanisms influencing scheduler performance and their impact on performance evaluations. It then proposes new solutions designed to reduce user energy consumption while remaining compatible with existing schedulers. The second part of the thesis introduces Artificial Intelligence as a tool for exploring scheduling policies. The approach progresses from a proof-of-concept based on selecting explicit policies to the exploration of a broader solution space that integrates multiple objectives.

This work culminates in AISE (Artificial Intelligence for Scheduler Exploration), which explores explicit and analyzable scheduling policies, and MS-AISE, which leverages these policies to adapt the scheduler to system conditions and QoS constraints. The research thus aims to reconcile the adaptation of scheduling policies to network conditions with requirements for performance, safety, and interpretability.

ADOPNET
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.