Clustered Predictive Quality of Service for Connected Vehicles Using Federated Learning

To enable the development of multi-functional cellular networks that aim to satisfy increasing expectations of connectivity and trustworthiness, it is crucial to provide reliable quality of service (QoS) guarantees for end users. With predictive QoS (pQoS), cellular networks become proactive to meet QoS requirements for a wide variety of new use cases, including advanced driver assistance applications. This work introduces a novel predictive framework to improve the availability and performance of pQoS in cellular networks, especially for advanced road transport applications. We show that by dividing the road into geographical segments, clustering segments with similar data, and assigning each cluster a predictive model, the adversary effects of the propagation environment and interference on QoS become manageable. To this end, each predictive cluster model is trained locally on vehicles within the cluster boundaries by data driven Federated Learning, resulting in personalized predictive models for each cluster. Our numerical results show that the clustered predictive model outperforms the more common predictive approach proposed by previous works that train a single global predictive model for an entire dataset.