With the rapid proliferation of 5G technology and the exponential growth of IoT devices, federated learning is emerging as a typical paradigm in 5G IoT scenarios. However, traditional federated learning still faces numerous challenges in 5G IoT scenarios, including resource constraints on edge devices, strong data distribution heterogeneity, and stringent privacy protection requirements. To address these challenges, this paper proposes a lightweight federated learning privacy protection framework (FedDHKD) based on dynamic hierarchical knowledge distillation. The FedDHKD framework divides the model into a client-side feature extractor and a server-side classifier, and achieves efficient knowledge transfer and model compression through a dynamic knowledge distillation mechanism, thereby reducing communication overhead. Additionally, an optimization strategy based on model-agnostic meta-learning is introduced to enhance adaptability to heterogeneous data distributions and accelerate convergence. Furthermore, by adding Gaussian noise that satisfies differential privacy constraints to the low-dimensional features to be uploaded, lightweight and effective privacy protection is achieved. Finally, we evaluated the performance of the FedDHKD framework against baseline approaches across various datasets. Experimental results demonstrate that FedDHKD reduces communication overhead to approximately one-seventh of FedAvg while maintaining competitive model accuracy. This approach provides an effective solution for 5G IoT edge scenarios, achieving a balanced trade-off between performance, efficiency, and privacy.

As a key intelligent component of core networks, NWDAF (Network Data Analytics Function) provides network intelligence capabilities while facing increasingly data security challenges. Current research on NWDAF data security primarily adopts federated learning framework, which trains models locally to avoid privacy leakage risks. However, existing NWDAF federated learning studies mostly rely on idealized assumptions, failing to adequately address two critical issues in real-world network deployments: 1) uneven data distribution across different regions, and 2) differentiated optimization requirements for high priority security regions. To solve these problems, we propose a region dual-factor aware federated learning framework for NWDAF (NWDAF-FedRDA), specifically designed to handle regional data imbalance and security priority differences in core networks. The framework comprises three core components: 1) Model parameter distribution: enabling allocation of global model parameters to regional nodes; 2) Local training: performing regional data preprocessing and model training; 3) Region dual-factor aware aggregation: computing regional weights through awareness factors and executing global model aggregation. Experimental evaluations across four network scenarios demonstrate the framework’s performance in anomaly detection tasks. Results show that compared to baseline methods, our framework exhibits significant advantages in uneven data distribution environments while effectively enhancing model performance for high-priority security regions.

Environment perception is the premise for intelligent vehicles to drive safely and stably. Despite the rapid development of road detection technology based on visual images, it is still challenging to robustly identify road areas in visual images due to the influence of illumination changes and noise. In order to solve this problem, we introduce a new optimized lidar and camera sensor fusion method for road environment sensing of intelligent vehicles. In road boundary detection based on laser data, a median point filtering method of ordered pole cloud is proposed. A method of boundary search, boundary seed point growth and obstacle clustering is proposed to identify road boundary. In the lane line classification based on visual image, a lane line search classification method is proposed, which can effectively classify lane lines and extract single lane lines. On the basis of the optimization of sensors, several constraint conditions are proposed based on the fusion of the two data, and the location of missing lane lines is predicted by using the road information identified by lidar and image, and the lane lines are identified again. Finally, a large number of experiments are carried out on kitti-Road benchmark data set, and a test platform is built to verify the results of the identification method proposed in this paper in rainy day, cloudy day, night and other special scenarios. Experimental results show that this method is superior to existing methods.

Abstract In network function virtualization, resource allocation is one of the key techniques to ensure the QoS of service requests in face of the uncertain traffic demand and traffic fluctuation of user services. The previous related works usually assume that the traffic demand is a deterministic value and then reallocate substrate resources to deal with the demand uncertainty and traffic fluctuation during operation. In response to performance degradation caused by demand uncertainty and traffic fluctuation, the paper models the service function chain orchestration under demand uncertainty as a robust optimization problem, where the parameter Γ is introduced to control the conservativeness of the solution. On this basis, the strong duality theory is used to transform the original problem into a mixed‐integer linear programming, and then devise an exact Robust Service Provisioning (RSP) algorithm. The simulation evaluation demonstrates that the proposed algorithm could achieve different levels of robustness and make a trade‐off between robustness and cost. The impact of Γ value on the realized robustness and price of robustness is also analysed. Thus, the algorithm proposed could get an effective service function chain orchestration scheme under uncertain traffic demands and provide a reference of the total cost.