The growing demand for intelligent mobile applications has made the deployment and operation of Deep Neural Networks (DNNs) on mobile Edge Devices (EDs) increasingly essential. However, the limited computational resources of EDs often result in significant energy consumption and compromised inference quality. To address these challenges, we propose a Partitioned Collaborative Inference (PCI) system that reduces on-device model inference costs by distributing the inference process across multiple EDs and MEC servers. To dynamically model the relationships between computing nodes, inference tasks, and resources, we employ Graph Neural Networks to construct the current state representation of the system. Furthermore, we develop a Cross-Entropy Method (CEM) based Evolutionary Reinforcement Learning algorithm, which leverages negative temporal difference (TD) error as a population fitness metric to generate elite individuals. The elite produces high-quality samples to improve learning efficiency, thereby obtaining optimal partitioned collaborative inference decisions and resource allocation in highly dynamic and complex search spaces. Extensive simulations demonstrate that the proposed approach significantly outperforms existing methods and benchmark schemes, achieving a 57. 5% increase in the inference task completion rate and a 65.7% reduction in system costs.

The Internet of Vehicles (IoV) enhances data availability by equipping a plethora of sensors, driving the automotive industry towards data-driven Predictive Maintenance (PreM) models. However, traditional centralized PreM solutions, requiring complete access to training data, raise concerns about data privacy. PreM in the automotive domain is more challenging than in many other fields, partly due to the varying distribution nature of data samples and the limited network connectivity time caused by vehicle mobility. To address these challenges, we propose the PreM-FedIoV framework, extending single-agent Double Deep Q-Network (DDQN) to Multi-Agent Double Deep Q-Network (MADDQN). In each round, each vehicle client uploads a data packet to the server based on the current contention window, containing its local model, local test Mean Absolute Error (MAE), and a timestamp. The server initially performs federated aggregation on the received local models. The MADDQN module then dynamically adjusts the contention window of each vehicle for the next round based on the local test MAE and communication statistical state, aiming to optimize communication costs and predictive performance. Additionally, we utilize NS-3 to create IoV simulations and deploy the PreM-FedIoV framework within NS3-gym. We choose Federated Averaging (FedAvg) and FedAdam following the IEEE 802.11p standard as baselines. The experiments demonstrate significant improvements in our framework compared to state-of-the-art algorithms. On the C-MAPSS dataset, we achieve reductions of up to 10.2% in MAE, 26.31% in average communication clock time per round, and 65.6% in the number of participating clients per round. For the Random Battery Usage dataset, with up to 4.55%, 24.44%, and 36.58% improvements in the respective metrics.

Traditional traffic classification methods struggle to identify emerging network traffic due to the need for model retraining, which hampers the real-time response of deployed edge devices. Furthermore, emerging network traffic samples are often scarce, traditional methods often treat a session as a single image, thereby overlooking essential structural features. These factors can result in poor generalization ability of the trained model. To overcome these challenges, we propose ConViTML (Convolutional Vision Transformer-based Meta-Learning), a real-time end-to-end network traffic classification framework that employs meta-learning to avoid model retraining. We propose a novel feature extraction network, Convolutional Visual Transformer (ConViT), merging Convolutional Neural Network (CNN) and Visual Transformer (ViT). ConViT can directly extract low-dimensional discriminative features containing basic and structural features of the session, which is vital for improving detection accuracy and accelerating convergence in a data-scarce environment. Furthermore, we employ a Packet-based Relation Network (PRN) to analyze the matching degree of support samples and query samples. Therefore, accurate classification in novel traffic identification tasks can be achieved with just a few labeled samples, eliminating extensive data collection and labeling operations. Finally, we replace various feature extractors and compare our approach with the classic meta-learning framework Relation Network (RelationNet). Extensive experimental results demonstrate that ConViTML outperforms others with various performance indicators.

The advent of Industry 4.0 has resulted in a significant increase in data availability, leading to the development and deployment of data-driven models for predicting the Remaining Useful Life (RUL) of machines. However, traditional centralized Predictive Maintenance (PreM) solutions that require complete access for training data give raise to concerns regarding data privacy. To address this challenge, Federated Learning (FL) has emerged as a promising and practical approach to enhance task performance while preserving data privacy within network nodes. Nevertheless, the presence of Non-Independent and Identically Distributed (Non-IID) data samples across devices can present challenges in terms of the convergence and speed of FL. Additionally, the heterogeneity of devices can lead to issues such as local model discarding and high communication costs, which are important considerations in FL. To address these challenges, this paper proposes Fedrated Predictive Maintenance (FedPreM), a novel federated reinforcement learning-based PreM scheme. FedPreM selectively involves a subset of devices in each communication round and employs an improved Perturbed Gradient Descent (PGD) optimizer to achieve flexible workload distribution among participating devices. By conducting experiments on a widely used turbofan dataset, our results demonstrate the effectiveness of FedPreM in reducing the number of communication rounds and minimizing prediction errors in distributed Industry 4.0 scenarios.

The Internet of Things (IoT) has become an important enabler for vehicular network applications, primarily the Internet of Vehicles (IoV). With the increase in the use of IoV, there is a potential increase in vulnerabilities to attacks and faults on vehicular networks. These misbehaviors or anomalies can vary from wrongly broadcasted data to more intense attacks like Denial of Service (DoS). It has become necessary to protect these vehicular networks through anomaly or misbehavior detection mechanisms. Deep learning models can be used for anomaly detection, considering the large volume of vehicular data available to train them. However, this gives rise to a need for privacy and security against data theft or information leaks of vehicular data. Hence, privacy preserving approaches like federated learning can be leveraged for anomaly detection. In this paper, we develop three federated learning (FL) schemes based on the federated averaging (FedAvg), FedAvg with Adam optimizer (FedAvg-Adam) and FedProx algorithms to acquire deep learning models in a distributed manner to perform anomaly detection in the IoV setting. The federated learning tasks run on local nodes deployed at the network edge, and models are combined on a global server deployed on the cloud. Our evaluation results using a publicly available IoV-relevant dataset show that these schemes were able to learn accurate models which permit effective anomaly detection in vehicular networks under different data distributions and network architectures.