New publication: SERENE-Prox – Proximal Federated Reinforcement Learning for Energy-Efficient Clustering in NR-V2X Vehicular Networks
Published in Electrical & Electronic Engineering, Mathematical & Computational Engineering Applications, and Mechanical Engineering
Our paper, "SERENE-Prox: Proximal Federated Reinforcement Learning for Energy-Efficient Clustering in NR-V2X Vehicular Networks," addresses the challenge of energy-efficient clustering in next-generation vehicular networks based on 5G NR-V2X technology.
The proposed SERENE-Prox framework leverages Proximal Federated Reinforcement Learning to support distributed and energy-efficient clustering decisions in vehicular environments, while benefiting from federated learning to enable collaborative intelligence.
This work contributes to ongoing research on intelligent, scalable, and energy-efficient solutions for connected and autonomous vehicular networks.
The article is available here:
https://authors.elsevier.com/
Many thanks to my co-authors, Dr. Wassim Jerbi and Dr. Mohamed H. Maâloul, for their valuable contributions and collaboration.
#NRV2X #VehicularNetworks #FederatedLearning #ReinforcementLearning #EnergyEfficiency
