Description du sujet de thèse

The domain of wireless cell communications is observing a technological revolution with the rise of 5th generation mobile networks. In addition of providing increased communication capacities and guaranteed differentiated services, 5G also provides high flexibility for deploying the new services required by users, or for allowing a facilitated management for network operators (NetOps). This flexibility relies on the softwarization principle of networks, i.e. the use of software modules easily deployable and manageable remotely, and that do not require to act on hardware devices for changing their configuration or add new services. 5G then takes advantage of the virtualization of networks and the SDN (Software Defined network) paradigm. Software radio techniques (SDR) are also part of the techniques selected these last years for the development of the new functionalities promised by 5G.

Given this paradigm change, the design and validation of the 5G modules, and of the global 5G network, is a significant scientific challenge. Few tools for that purpose exist nowadays. Thus, this thesis aims at working on the design of a 5G digital twin. This digital twin aims at designing a global statistical and behavioural model of 5G including each 5G protocol layer, each of its virtualized functions, and also considering non-functional properties as energy consumption, computational load or electromagnetic radiations.

For this purpose, LAAS deployed a 5G experimental platform leveraging Open Air Interface for experimenting all communication scenarios required for establishing the behaviour and performances of a 5G network, and that will allow the digital twin design. This will be made autonomously using artificial intelligence techniques.

Contexte de travail

Research in computer networks

Le poste se situe dans un secteur relevant de la protection du potentiel scientifique et technique (PPST), et nécessite donc, conformément à la réglementation, que votre arrivée soit autorisée par l'autorité compétente du MESR.

Contraintes et risques

None