POST-DOCTORAL POSITION

Il y a 7 jours

GifsurYvette, Île-de-France L2S - Laboratoire des signaux et systèmes Temps plein

Position Overview

Post‑doctoral position on resource allocation in the vehicular slice for remote car driving (Project title: Resource allocation in the vehicular slice for remote car driving). The project focuses on developing mechanisms for network slice resource provisioning under stringent rate and latency constraints for mobile users in tele‑operation or remote car driving scenarios.

Objectives

• Propose joint resource reservation mechanisms that cover both core network (CN) and radio access network (RAN) resources. • Incorporate user‑equipment trajectory information and uncertainty to facilitate joint provisioning. • Apply mixed‑integer linear programming (MILP) and deep reinforcement learning techniques to optimize the reservation problem. • Evaluate the proposed solutions on a real 5G platform.

Project Steps

  • Bibliographic study on Cloud RAN, Open RAN, NFV/SDN, 5G slicing, V2X slicing, and 5G resource allocation.
  • Develop radio‑resource provisioning models for perfectly known trajectories; extend to known trajectory uncertainty and multiple remotely controlled cars sharing resources.
  • Implement resource reservation in the BBU pool and DU, ensuring coverage and handover constraints.
  • Integrate allocation mechanisms for both radio, access, and core network resources along the trajectory.
  • Collaborate with the PEPR Future Networks (PC5) team, particularly the NAI project.

Expected Results

  • Optimization models (MILP) capturing all relevant parameters and constraints.
  • Allocation algorithms tailored for known and uncertain trajectory scenarios.
  • Resource reservation modules within the Open Radio Access Network (ORAN) framework.
  • Performance evaluation and validation on a 5G testbed.

Prerequisites

  • Ph.D. in telecommunication engineering, computer science, or related field.
  • Strong background in networking protocols, routing, beamforming antennas, simulation/emulation.
  • Proficiency in AI techniques, performance evaluation, and programming in C/C++/Python.
  • Experience with deep learning and reinforcement learning highly appreciated.

Application Process

  • Letter of motivation detailing suitability for the position.
  • Detailed curriculum vitae.
  • List of publications, if any.
  • Name and contact email of one or two referees.

Financial Aid & Duration

The project is funded by the national PEPR Future Networks program under France 2030, led by CEA, CNRS and IMT. The position lasts 18 months.

Laboratory and Supervisors

Laboratoire des Signaux et Systèmes (L2S), UMR 8506 (University Paris‑Saclay, CNRS, CentraleSupélec). Team Multinet. Supervisor(s):

#J-18808-Ljbffr