Unmanned aerial vehicle (UAV) assisted emergency communication is an important technique for future B5G/6G scenario. The UAV is usually considered as a mobile relay to forward information from the macro base station (MBS) to the users in emergency area. In this paper, the MBS power allocation, the UAV service zone selection, and the user scheduling are jointly investigated to enhance the sum spectrum efficiency. We formulate the MBS power allocation and UAV service zone selection problem as an Markov Decision Process (MDP) in the delay ignored system (DIS) and propose a deep reinforcement learning (DRL) algorithm based on Q-learning and Convolutional Neural Networks (CNN). Then the proposed DRL-based scheme is extended in time delay system (TDS) to estimate the current optimal action with the outdated channel information. We also formulate the user scheduling as a 0-1 optimization problem and solve it by dividing into sub-problems. Simulation results demonstrate that the proposed DRL-based resource scheduling scheme can effectively improve the spectrum efficiency compared with the existing schemes.

As a key enabler of emerging 6G applications, mobile edge computing (MEC) improves the system performance by coordinating the computation resources between the mobile devices and edge. However, the energy consumption and carbon emission are boosted as the device number increases. This paper constructs a hierarchical network-assisted task offloading architecture for Green Internet of Things (IoT). Then the authors propose an energy-efficient scheduling based on traffic mapping with energy slack-space proportional pre-allocation algorithm (ESTMP) in the heterogeneous edge computing system to minimize the schedule length under certain energy constraints. The proposed algorithm is suitable for delay-sensitive mobile applications such as Augmented Reality (AR)/Virtual Reality (VR)/Mixed Reality (MR), which process massive multi-modal data. Simulation results demonstrate the significant advantages of the algorithm in terms of the schedule length of arriving parallel tasks, resource utilization and energy consumption.

This letter proposes a joint interference suppression scheme in heterogeneous networks (HetNets) with dense small cells (SCs) and users. Different from the majority of existing studies, we adopt the co-tier intra-cell interference alignment (IA), while the co-tier inter-cell and cross-tier interference is suppressed by centralized power control in the macro base station (MBS). Specifically, the power control problem is modeled as a Markov Decision Process (MDP) with the aim of maximizing the sum spectrum efficiency. Considering the exponential growth of the output layer neurons faced by general deep reinforcement learning (DRL) algorithms, we propose a deep deterministic policy gradient (DDPG)-based algorithm to solve the problem. Simulation results demonstrate that the proposed algorithm is able to achieve better performance and wider application scope comparing with existing algorithms.

The rapid development of smart healthcare and the increasing number of wearable devices in consumer electronics can facilitate health monitoring services with lower latency and less energy consumption, and provide more reliable computation and communication for medical cares. In this paper, we consider the next generation (next-gen) wearable consumer electronics architecture and introduce D2D communication in a trustworthy health monitoring system that utilizes collaborative computing among different wearables to reduce the execution cost of health monitoring tasks and improve the efficiency of medical services, which can monitor several health indicators of the human body in real-time. We further construct a device-collaborative offloading framework for health monitoring (DCO-HM) to reduce energy consumption and computational latency. A directed acyclic graph (DAG)-based offloading algorithm, in which wearables can execute medical tasks locally or perform device-collaborative computation, is proposed. We also consider the priority of task execution and the CPU frequency of wearables to achieve distributed smart monitoring. The simulation results show that the proposed device-collaborative computing scheme significantly improves the computational efficiency of smart health monitoring system with a trustworthy manner.

The vertical industry member and the Internet of Things (IoT) business are spurring heated discussions on the evolution of future mobile communication. The emerging non-terrestrial network (NTN) plays increasingly important role in addressing service and coverage demand boom, whilst they still envisage technical and performance bottlenecks. Besides, traditional communication paradigm is constrained by Shannon theorem and fails to exploit the semantic features. In this article, we review the classic 6G NTN IoT networks and semantic communication in terms of structure, challenges, and applications. Then we observe that the superiority of semantic communication in low signal-to-noise ratio (SNR) regime is complementary to 6G NTN. We further propose an adaptive semantic-empowered 6G NTN IoT structure supporting communication paradigm switching. Finally, the open issues are discussed.

The power amplifier (PA) behavior models based on deep neural networks (DNNs) have been widely used. However, it is challenging to balance the network depth, the number of neurons, and the combination of input terms. Accordingly, how to obtain a suitable DNN model becomes a problem. This letter proposes a method to acquire the corresponding optimal DNN structure balancing multiple aspects for a PA by decoupling the relationship of the three factors mentioned above. The algorithm first chooses the optimal input combinations, and then utilizes the inputs to select the DNN structure with excellent capability to fit nonlinear functions and fewer coefficients. Experimental results verify that the DNN model acquired by the algorithm proposed can maintain superior performance with low complexity.