Post-Doctoral position : « Machine Learning-Based Resource Management in LEO Satellite Networks. »

Machine Learning-Based Resource Management in LEO Satellite Networks.

Date limite de candidature : 20/03/24
Date de début : 01/06/2024
Date de fin : 01/06/2025

Pôle : Télécoms et réseaux
Type de poste : Post-Doc ou ATER
Contact : Alexis ARAVANIS (

la fiche

Postdoctoral Position: Machine Learning-Based Resource Management in LEO Satellite Networks.
Duration: 12 months Gross Salary: approximately 3200 € monthly Host institution: L2S, CNRS, CentraleSupélec, University of Paris-Saclay Advisor: Alexis I. Aravanis, {email:}
Description: As the demand for global connectivity continues to surge, LEO satellite networks present a promising solution for providing ubiquitous and high-speed internet access to remote and underserved regions. However, the optimization of the routing strategies and of the resource allocation in these dynamic and rapidly evolving networks as well as the seamless integration of LEO satellite networks into 5G terrestrial networks pose significant challenges.
The present position aims to develop innovative routing and resource management solutions to optimize connectivity, performance, and resource utilization in dynamic LEO satellite environments, employing Machine Learning-based resource management techniques.
Profile: PhD in Telecommunications engineering, or Machine learning
The successful candidate will join a dynamic research team and contribute to advancing the state-of-the-art in routing and resource management for 5G Non-Terrestrial Networks (NTN), with a specific focus on Machine Learning-based resource allocation. Key responsibilities include:

Investigate routing strategies, to maximize service accommodation and optimize resource allocation under variable network topologies and 5G service requirements.

Design intelligent resource management strategies to optimize throughput and mitigate interference in dynamic LEO satellite networks.

Explore multi-connectivity between terrestrial and non-terrestrial networks to enhance user experience and network resilience.

Employ machine learning-based resource allocation, using ML algorithms to adaptively route traffic and optimize network efficiency and performance based on historical data, real-time metrics, and predictive modeling.

Optimize connectivity via satellites, ground stations and/or high-altitude platforms (HAP) to maximize resource utilization, considering different transmission environments and channel conditions.

Design routing strategies that ensure the security of the satellite networks against terrestrial and non-terrestrial eavesdroppers.
Applicants should contact Alexis I. Aravanis providing a CV and a cover letter in PDF format.