PHFedDA: Personalized Hierarchical Federated Learning Framework Based on Heterogeneous Data Aggregation in Vehicular Networks

In the Internet of Vehicles (IoV) environment, data among vehicles exhibits Non-Independent Identical Distribution (Non-IID) characteristics due to the diversity of vehicle types, on-board hardware, and user preferences. In addition, when users request location-based services (LBS), they face the risk of privacy leakage and have higher Quality of Service (QoS) requirements. Therefore, personalized location privacy protection has become an urgent issue. Most existing research focuses on protecting overall privacy but lacks personalized strategies to address varying user needs and struggles with handling Non-IID data. To address these challenges, this paper proposes a personalized hierarchical federated learning framework (PHFedDA) based on heterogeneous data aggregation. First, we apply a personalized location privacy budget allocation scheme (PLPB) to vehicle trajectories, and a quality assessment model is proposed for evaluating the accuracy of vehicle trajectory aggregation, through which an effective balance between aggregation accuracy and privacy protection is achieved. Then, we design a personalized hierarchical federated learning algorithm to effectively deal with the Non-IID data problem caused by the differences in vehicle end-user preferences. Finally, through simulation experiments, our PHFedDA framework achieves an 8.74% improvement in aggregation accuracy over the best-performing baseline scheme DSLP. Additionally, the model accuracy improves by 7.52% compared to the top-performing baseline scheme SCAFFOLD. Compared to other baseline schemes mentioned in this paper, PHFedDA demonstrates significant advantages in security and handling data heterogeneity.