In a vehicular ad-hoc network (VANET), vehicles can communicate with each other to exchange critical infor-mation. However, communications among vehicles may suffer from unstable transmission paths or high messaging overhead owing to the high mobility of vehicles. Vehicle clustering is an effective approach for VANET management. This paper presents a distributed clustering algorithm based on federated deep reinforcement learning. The proposed algorithm can improve the stability of vehicle-to-vehicle connections in a rapidly changing environment. The results show that our algorithm can improve the stability of clustering by reducing the number of role and cluster changes for vehicles.
Stable Clustering in VANET Using Federated Deep Reinforcement Learning
23.07.2023
856739 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Optimizing Environment-aware VANET Clustering using Machine Learning
Springer Verlag | 2023
|V2V2I VANET Data Offloading Path Using Reinforcement Learning
Springer Verlag | 2025
|Vehicles Control: Collision Avoidance using Federated Deep Reinforcement Learning
ArXiv | 2023
|