In the last decade, network data communication has experienced a rapid growth, which has led to explosive congestion in heterogeneous networks. Moreover, the emerging industrial applications such as automatic driving put forward higher requirements on both networks and devices. On the contrary, running computation-intensive industrial applications locally is constrained by the limited resources of devices. Correspondingly, fog computing has recently emerged to reduce the congestion of content-centric networks. It has proven to be a good way in industry and traffic for reducing network delay and processing time. In addition, device to device (D2D) offloading is viewed as a promising paradigm to transmit network data in mobile environment, especially for auto-driving vehicles. In this paper, jointly taking both the network traffic and computation workload of industrial traffic into consideration, we explore a fundamental tradeoff between energy consumption and service delay when provisioning mobile services in vehicular networks. In particular, when the available resource in mobile vehicles becomes a bottleneck, we propose a novel model to depict the users' willingness of contributing their resources to the public. We then formulate a cost-minimization problem by exploiting the framework of Markov decision progress (MDP) and propose the dynamic reinforcement learning scheduling algorithm and the deep dynamic scheduling algorithm to solve the offloading decision problem. By adopting different mobile trajectory traces, we conduct extensive simulations to evaluate the performance of the proposed algorithms. The results show that our proposed algorithms outperform other benchmark schemes in the mobile edge networks.

In the era of information, the green services of content-centric IoT are expected to offer users the better satisfaction of Quality of Experience (QoE) than that in a conventional IoT. Nevertheless, the network traffic and new demands from IoT users increase along with the promising of the content-centric computing system. Therefore, the satisfaction of QoE will become the major challenge in the content-centric computing system for IoT users. In this article, to enhance the satisfaction of QoE, we propose QoE models to evaluate the qualities of the IoT concerning both network and users. The value of QoE does not only refer to the network cost, but also the Mean Opinion Score (MOS) of users. Therefore, our models could capture the influence factors from network cost and services for IoT users based on IoT conditions. Specially, we mainly focus on the issues of cache allocation and transmission rate. Under this content-centric IoT, aiming to allocate the cache capacity among content-centric computing nodes and handle the transmission rates under a constrained total network cost and MOS for the whole IoT, we devote our efforts to the following two aspects. First, we formulate the QoE as a green resource allocation problem under the different transmission rate to acquire the best QoE. Then, in the basis of the node centrality, we will propose a suboptimal dynamic approach, which is suitable for IoT with content delivery frequently. Furthermore, we present a green resource allocation algorithm based on Deep Reinforcement Learning (DRL) to improve accuracy of QoE adaptively. Simulation results reveal that our proposals could achieve high QoE performance for content-centric IoT.

Federated learning has attracted much research attention due to its privacy protection in distributed machine learning. However, existing work of federated learning mainly focuses on Convolutional Neural Network (CNN), which cannot efficiently handle graph data that are popular in many applications. Graph Convolutional Network (GCN) has been proposed as one of the most promising techniques for graph learning, but its federated setting has been seldom explored. In this article, we propose FedGraph for federated graph learning among multiple computing clients, each of which holds a subgraph. FedGraph provides strong graph learning capability across clients by addressing two unique challenges. First, traditional GCN training needs feature data sharing among clients, leading to risk of privacy leakage. FedGraph solves this issue using a novel cross-client convolution operation. The second challenge is high GCN training overhead incurred by large graph size. We propose an intelligent graph sampling algorithm based on deep reinforcement learning, which can automatically converge to the optimal sampling policies that balance training speed and accuracy. We implement FedGraph based on PyTorch and deploy it on a testbed for performance evaluation. The experimental results of four popular datasets demonstrate that FedGraph significantly outperforms existing work by enabling faster convergence to higher accuracy.

This paper studies the secure transmission rate issue between sensors and the remote controller to defend the jamming and eavesdropping attacks in green cyber–physical transportation systems. In this system, the traffic sensor transmits the transportation state information to the remote controller via wireless networks. Due to the broadcast characteristics of the wireless communication, the systems are vulnerable to the eavesdropping and jamming attacks. In this paper, we study how to maximize the secure transmission rate between sensors and the controller in the presence of a malicious eavesdropper and a jammer. Specifically, the malicious jammer is smart and can choose the optimal power strategy to maximize the side effect with the knowledge of sensor's transmission power. For the purpose of achieving the maximum utility, the optimal strategy is determined via adjusting the sensor's transmission power according to the control feedback conditions. We consider the single-antenna model and the multiantenna model to formulate this problem as an optimization problem based on a Stackelberg game. We then prove the existence of the Stackelberg equilibrium via the interaction between the sensor and the jammer. Moreover, we present two algorithms to obtain the optimal transmission strategy, i.e., a stochastic algorithm with feedback and renewed intelligent simulated annealing. Finally, extensive simulations and trace experimental results are presented to verify our theoretical analysis.

To create a context-aware environment, human locations and movement paths must be considered. In this paper, we propose an algorithm that tracks human movement paths using only binary sensed data obtained by infrared (IR) sensors attached to the ceiling of a room. Our algorithm can estimate multiple human movement paths without a priori knowledge of the number of humans in the room. By repeating predictions and estimations of human positions and links from the previous human positions to the estimated ones at each time period, human movement paths can be estimated. Simulation-based evaluation results show that our algorithm can dynamically trace human movement paths.

Data traffic in cellular networks has dramatically surged in recent years due to the booming growth of various mobile applications. It is hence crucial to increase network capacity to accommodate new applications and services. In this article, we propose a promising concept of cooperative device-to-device communication to improve resource utilization in cellular networks. Based on a novel fine-grained resource allocation scheme, we study the problem of maximizing the minimum rate among multiple wireless links by jointly considering relay assignment, transmission scheduling, and channel allocation. Simulation results show that our proposed solutions can significantly increase resource utilization in cellular networks.