This paper investigates the physical layer security of non-orthogonal multiple access (NOMA) in large-scale networks with invoking stochastic geometry. Both single-antenna and multiple-antenna aided transmission scenarios are considered, where the base station (BS) communicates with randomly distributed NOMA users. In the single-antenna scenario, we adopt a protected zone around the BS to establish an eavesdropper-exclusion area with the aid of careful channel ordering of the NOMA users. In the multiple-antenna scenario, artificial noise is generated at the BS for further improving the security of a beamforming-aided system. In order to characterize the secrecy performance, we derive new exact expressions of the security outage probability for both single-antenna and multiple-antenna aided scenarios. For the single-antenna scenario, we perform secrecy diversity order analysis of the selected user pair. The analytical results derived demonstrate that the secrecy diversity order is determined by the specific user having the worse channel condition among the selected user pair. For the multiple-antenna scenario, we derive the asymptotic secrecy outage probability, when the number of transmit antennas tends to infinity. Monte Carlo simulations are provided for verifying the analytical results derived and to show that: 1) the security performance of the NOMA networks can be improved by invoking the protected zone and by generating artificial noise at the BS and 2) the asymptotic secrecy outage probability is close to the exact secrecy outage probability.

The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices. To overcome this challenge, in this paper, we advocate the integration of edge computing paradigm and parallel split learning (PSL), allowing multiple edge devices to offload substantial training workloads to an edge server via layer-wise model split. By observing that existing PSL schemes incur excessive training latency and a large volume of data transmissions, we propose an innovative PSL framework, namely, efficient parallel split learning (EPSL), to accelerate model training. To be specific, EPSL parallelizes client-side model training and reduces the dimension of activations' gradients for backpropagation (BP) via last-layer gradient aggregation , leading to a significant reduction in server-side training and communication latency. Moreover, by considering the heterogeneous channel conditions and computing capabilities at edge devices, we jointly optimize subchannel allocation, power control, and cut layer selection to minimize the per-round latency. Simulation results show that the proposed EPSL framework significantly decreases the training latency needed to achieve a target accuracy compared with the state-of-the-art benchmarks, and the tailored resource management and layer split strategy can considerably reduce latency than the counterpart without optimization.

Sparse representation can efficiently model signals in different applications to facilitate processing. In this article, we will discuss various applications of sparse representation in wireless communications, with a focus on the most recent compressive sensing (CS)-enabled approaches. With the help of the sparsity property, CS is able to enhance the spectrum efficiency (SE) and energy efficiency (EE) of fifth-generation (5G) and Internet of Things (IoT) networks.

A super-resolution imaging technique based on the vortex electromagnetic (EM) wave, which carries orbital angular momentum (OAM), is reported in this paper. The proof-of-concept experiment for the EM vortex imaging is conducted. An imaging processing method based on the real-world OAM radar data is proposed to obtain the target profile. Experimental results validate the effectiveness of the proposed imaging method and demonstrate that the vortex EM wave can be exploited to image targets with high-resolution beyond the limit of the array aperture. This breakthrough on the Rayleigh limit paves the way for innovative techniques in radar imaging and remote sensing.

In this article, we investigate an unmanned aerial vehicle (UAV)-assisted Internet of Things (IoT) system in a sophisticated 3-D environment, where the UAV’s trajectory is optimized to efficiently collect data from multiple IoT ground nodes. Unlike existing approaches focusing only on a simplified 2-D scenario and the availability of perfect channel state information (CSI), this article considers a practical 3-D urban environment with imperfect CSI, where the UAV’s trajectory is designed to minimize data collection completion time subject to practical throughput and flight movement constraints. Specifically, inspired by the state-of-the-art deep reinforcement learning approaches, we leverage the twin-delayed deep deterministic policy gradient (TD3) to design the UAV’s trajectory and we present a TD3-based trajectory design for completion time minimization (TD3-TDCTM) algorithm. In particular, we set an additional information, i.e., the merged pheromone, to represent the state information of the UAV and environment as a reference of reward which facilitates the algorithm design. By taking the service statuses of the IoT nodes, the UAV’s position, and the merged pheromone as input, the proposed algorithm can continuously and adaptively learn how to adjust the UAV’s movement strategy. By interacting with the external environment in the corresponding Markov decision process, the proposed algorithm can achieve a near-optimal navigation strategy. Our simulation results show the superiority of the proposed TD3-TDCTM algorithm over three conventional nonlearning-based baseline methods.

In this paper, we investigate resource allocation with edge computing in Internet of Things (IoT) networks via machine learning approaches. Edge computing is playing promising role in IoT networks by providing computing capabilities close to users. However, the massive number of users in IoT networks requires sufficient spectrum resource to transmit their computation tasks to a edge server, while IoT users were developed to have more powerful computation ability recently, which makes it possible for them to execute some tasks locally. Then the design of computation task offloading policies for such IoT edge computing systems remains challenging. In this paper, centralized user clustering is explored to group the IoT users into different clusters according to users’ priorities. The cluster with the highest priority is assigned to offload computation tasks and executed at the edge server, while the lowest priority cluster executes computation tasks locally. For the other clusters, the design of distributed task offloading policies for IoT users is modelled by a Markov decision process, where each IoT user is considered as an agent which makes a series of decisions on task offloading by minimizing the system cost based on the environment dynamics. To deal with the curse of high dimensionality, we use deep Q network to learn the optimal policy in which deep neural network is used to approximate the Q-function in Q-learning. Simulations show that users are grouped into clusters with optimal number of clusters. Moreover, our proposed computation offloading algorithm outperforms the other baseline schemes under same system costs.