Hierarchical Federated Transfer Learning in Digital Twin-Based Vehicular Networks

Hierarchical Multi-Task Federated Learning in VANETs

Vehicular Ad hoc Networks (VANETs) increasingly rely on federated learning (FL) to enable collaborative intelligence without sharing raw sensory data. However, most existing vehicular FL frameworks assume that all vehicles train a single global model for a common task, which limits their applicability in practical vehicular environments where vehicles may perform heterogeneous learning tasks under non-independent and identically distributed (non-IID) data, intermittent connectivity, and high mobility. To address these challenges, this paper proposes an AutoEncoder-based Reliability-Optimized Hierarchical Multi-Task Federated Learning (AERO-HMTFL) framework for dynamic multi-hop clustered VANETs. The proposed framework introduces a tri-weighted clustering metric that jointly considers vehicular mobility, shared-model similarity, and task affinity to produce mobility-stable, semantically aligned clusters. Each vehicle employs a split-model architecture comprising a shared autoencoder-based representation module and multiple task-specific heads, with only the shared autoencoder parameters exchanged while the task heads remain local. To improve robustness, cluster heads perform reliability-aware aggregation based on historical validation performance and participation frequency, while the Evolved Packet Core (EPC) conducts global shared-autoencoder fusion across clusters. Extensive simulations demonstrate that, compared with the multi-task federated learning benchmarks, AERO-HMTFL achieves up to 13% higher sustained EPC-level accuracy, exhibits more stable learning dynamics, and reduces EPC-level packet transmissions by approximately 87-97%. Under short-range connectivity, it also requires approximately 13-29% fewer communication rounds to converge.

Lightweight Aggregation Protocols for Green Federated Learning in Vehicle-to-Cloud Systems

Leveraging deep learning for advanced routing optimization in urban vehicular networks

The increasing advances in smart mobility and connected systems have intensified interest in transforming urban mobility, with Vehicular Ad-hoc Networks (VANETs) technologies emerging as a key enabler for safer and more efficient cities. However, VANETs face significant routing challenges due to high vehicle mobility, dynamic network topologies, and privacy constraints. This paper proposes a Deep Learning-based Routing Optimization (DLRO) framework that integrates an attention-based DL model with Federated Learning (FL) for efficient and privacy-preserving route prediction in urban vehicular networks. The framework adopts a client–server architecture where local training is performed on each vehicle, and only model parameters are shared with the server. We evaluate DLRO using the SUMO simulator with a dataset containing vehicle trajectories across urban scenarios. Compared to baseline non-cooperative routing method, DLRO achieves up to 47.1–75% reduction in distance traveled. The Average Displacement Error (ADE) and Final Displacement Error (FDE) consistently decrease across training epochs, confirming the model’s predictive accuracy. These findings confirm that the integration of DL with FL provides an effective approach for privacy-preserving route optimization in urban vehicular networks.

Distributed Decision-making System for Intelligent Connected Vehicles Based on Federated Learning

Current distributed decision-making for intelligent connected vehicles is constrained by model heterogeneity, high communication overhead, and data privacy concerns, which impede efficient multi-vehicle collaboration in wireless vehicular communication environments. As reliable information exchange and low-latency signal transmission become increasingly important in intelligent transportation systems and electromagnetic communication networks, this paper proposes a distributed decision-making framework integrating Federated Distillation (FD) and Graph Attention Networks (GAT). A local GAT dynamically constructs vehicle adjacency graphs for neighboring perception, while FD replaces conventional parameter sharing with soft-label exchange, significantly reducing communication burden, enabling knowledge transfer across heterogeneous devices, and alleviating computational bottlenecks on resource-limited nodes. Evaluated in the most challenging scenario characterized by maximum vehicle density, dynamic communication delays, packet loss, severe data Non-IIDness, and complex multi-intersection interactions, the proposed method demonstrates superior collaborative performance. The average decision latency is maintained at 91 ms, which is 43 ms lower than that of the traditional FedAvg approach, while the number of uncoordinated behavior triggers is reduced by 50% to only three. These results verify that the proposed framework achieves efficient and privacy-preserving collaborative decision-making while providing a scalable solution for distributed intelligence in wireless vehicular networks and communication-intensive electromagnetic environments.

A hierarchical federated learning framework with FedNova, game-theoretic matching, and QKD-assisted privacy for the internet of vehicles

The Internet of Vehicles (IoV) supports essential intelligent transportation applications but encounters challenges in federated learning (FL) due to non-independent and identically distributed (non-IID) data, vehicle mobility, resource heterogeneity, and strict privacy requirements in latency-sensitive scenarios such as misbehavior detection and accident response. Traditional FL methods, such as random client selection and standard FedAvg, often experience slow convergence and reduced performance under non-IID conditions. We introduce a hierarchical federated learning framework for software-defined vehicular fog computing. The framework incorporates FedNova (a normalized-averaging aggregation method for heterogeneous federated optimization) to produce normalized model updates under data heterogeneity, a Reward-Based Payoff Strategy (RBPS) for incentive-aware client selection, and game-theoretic vehicle-aggregator matching based on the college admissions problem. Privacy is strengthened through quantum key distribution (QKD)-assisted secure key establishment and classical gradient masking, with quantum circuit simulation used to assess future enhancements. The three-layer architecture includes vehicles, Roadside Unit (RSU)/ Base Station (BS)-level aggregators, and a Software-Defined Network Controller (SDNC) global aggregator. The framework uses both monetary and service-based incentives, such as toll exemptions, to encourage vehicle participation. Hybrid simulations using OMNeT++, Veins, SUMO, and the VeReMi misbehavior detection dataset show that the proposed approach achieves 94.8% classification accuracy [95% Confidence Interval (CI): 92.7–97.0 over 10 runs], converges in 120 rounds (33% faster than FedAvg), and reduces average latency by 29% (320 ms compared to 450 ms for FedAvg), with statistically significant improvements (p < 0.05). These gains enable faster model adaptation to evolving attacks (5–10 min shorter training cycles) and support real-time safety applications where delays above 400 ms can compromise road safety. Ablation studies confirm the complementary roles of FedNova, RBPS, and matching. Although quantum operations are currently simulated classically, the design remains compatible with future quantum hardware.

A Simulation-Driven Trust-Aware Federated Learning Framework for Robust Intelligent IoT Networks

The experimental results demonstrate that the proposed Trust-FedAvg framework substantially improves robustness over conventional FedAvg and remains competitive with established robust aggregation strategies, particularly under directional model-manipulation attacks and intermittent-connectivity conditions.