With the widespread use of mobile devices and the rapid growth of big data, the application of federated learning in decentralized data environments has attracted increasing attention. 5G and 6G mobile communication systems take the large-scale Internet of things as one of the core scenarios, which can be employed to realize the real-time data transmissions of massive terminals in federated learning. Multiple access technology is the key to achieve massive connectivity in 6G massive IoT. Resource hopping multiple access achieves efficient access by assigning different resource hopping patterns to different users. In this paper, a federated learning scheme combining RHMA and differential privacy is proposed, which divides the communication channel into multiple subchannels and allocates hopping patterns according to data characteristics and computational resources. Therein, differential privacy mechanism effectively protects the privacy of user data by adding noise to the model training process of federated learning. Experimental results show that the proposed scheme not only improves the training speed of the federated learning model, but also improves the robustness and security of the system while ensuring user privacy. © 2025 IEEE.

In this paper, massive access in millimeter wave (mmWave) cell-free massive multiple-input multiple-output (CF-mMIMO) system is investigated. We propose a model-based deep learning algorithm to solve the joint active detection and channel estimation (JADCE) problem in grant-free random access. By exploiting structured sparsity and cluster sparsity, we unfold the vector approximate message propagation (VAMP) algorithm with Bernoulli Gaussian mixed distribution into a network and introduce a parameter estimation module to adapt different active ratios and noise variance based on the expectation maximization (EM) algorithm. The proposed network benefits from the param-eter learning ability of deep learning and the low computation complexity of the model-based method. Simulation results show that the proposed network achieves better detection performance and faster convergence rate than the considered state-of-the-art algorithms. © 2024 IEEE.

In this paper, we investigate coverage enhancement, base station (BS) association, and BS handover management schemes for cellular-connected unmanned aerial vehicles (UAVs) equipped with beamforming capabilities. Specifically, we consider the following characteristics of cellular-connected UAVs: 1) They can receive signals from more BSs than ground terminals, but they also experience greater interference. 2) They often reside at locations with in zero or low power directions of BSs, resulting in unstable reference signal received power (RSRP). These characteristics lead to issues such as poor coverage for cellular-connected UAVs and frequent BS handovers. We have therefore in this paper established a multi-antenna cellular-connected UAV system, where the UAV can perform beamforming based on predefined beamforming vectors. Subsequently, we considered two communications scenarios: UAV being associated with a single BS and multiple BSs cooperating to serve the UAV. In each scenario, we proposed corresponding BS association, UAV beamforming and handover strategies to enhance the UAV's coverage probability in cellular networks and to some extent reduce the number of handovers for the UAV. Finally, we validated the effectiveness of the proposed methods in both scenarios through simulations. © 2024 IEEE.

This paper considers the uplink cell-free massive multiple-input multiple-output (CF mMIMO) ultra reliable and low-latency communications (URLLC) system. Different from the original CF mMIMO, we consider a user-centric (UC) architecture, where each device is served by a cluster of access points (APs) in the system. Therefore, it requires less signaling overhead and computations for signal detection. However, the APs cluster for each device is formed solely based on the received power of the reference signal at APs in the most related works, which can't guarantee fairness among devices. For this, we propose a UC clustering algorithm to overcome the limitation. Firstly, we derive the lower bound of ergodic rates for CF mMIMO URLLC systems with local partial zero-forcing (PZF) performed at APs and large-scale fading decoding (LSFD) performed at the central processing unit (CPU). Then, we utilize a genetic algorithm to solve the max-min rate optimization problem of UC clustering. Simulation results demonstrate its effectiveness in ensuring fairness in CF mMIMO URLLC systems. © 2024 IEEE.

Unmanned Aerial Vehicles (UAVs), with their high levels of flexibility and maneuverability, can greatly enhance the capabilities of Mobile Edge Computing (MEC) by acting as edge computing servers. In practice, however, it is often challenging to jointly optimize the flying trajectories of UAVs and the offloading decisions of tasks, due to the fast and randomly changing of physical environments. In this work, we investigate an UAV-enable MEC network with the assistance of Digital Twin (DT), where a DT layer is introduced to simulate the Physical Entity (PE) layer, generate different strategies, and evaluate their performances. Specifically, we formulate a joint flying trajectories, task offloading, and resource allocation problem on the DT layer, aiming at minimizing both task delay and energy consumption, under the maximum tolerated delay and resource constraints. To solve the problem in an online distributed manner and implement the derived strategies on the real PE layer, we propose a hierarchical learning approach, which consists of a Deep Reinforcement Learning (DRL) module and a Constrained Optimization (CO) module. First, the DRL module determines the UAVs' flying trajectories. Then, the CO module determines the MDs' task offloading decisions and the associated resource allocations, given the UAV s' flying decisions. Finally, the outputs of both modules are combined together to train the DRL module by using the Deep Deterministic Policy Gradient (DDPG) method. Experiment results show that our proposed DT-assisted scheme outperforms existing benchmark schemes in terms of both task delay and energy cost. © 2024 IEEE.

In order to satisfy the increasingly massive connection in mMTC system, multiple access technology is a key enabler in the future 6G mMTC. Recently, an emerging multiple access scheme named resource hopping based multiple access (RHMA) has been proposed to achieve reliable user identification and data detection in grant-free random access for mMTC. However, the collision resolution of RHMA is still limited for the future 6G mMTC requirements. Therefore, an improved design is proposed in this paper to enhance the collision resolution capability of RHMA. Specifically, successive interference cancellation (SIC) is combined with user identification and segment decoding at the receiver of RHMA. Also, the user identification of RHMA is improved to eliminate the false alarm user caused by collision and blind channel estimation is considered to recover the signal on the colliding segments. The simulation results show that the improved design is able to achieve a higher collision resolution capability of RHMA. © 2024 IEEE.

With the vision of global coverage for the sixth generation (6G) wireless communication systems, the low Earth orbit (LEO) satellite systems have drawn considerable attention. In this paper, A LEO satellite-to-ground channel model for urban scenarios is proposed based on ray-tracing. The channel model is divided into the atmospheric part and near-ground part, and the effects of ionospheric scintillation, rainfall, and multipath are studied. The model analyzes the multipath effect in the near-ground with the image method, assuming that the incident rays come from a circular plane transmitter over the ground. Channel characteristics such as delay power spectral density (PSD) and received power of signals are derived. The simulation results show that the received power increases with the satellite elevation angle increasing in urban scenarios. © 2024 18th European Conference on Antennas and Propagation, EuCAP 2024. All Rights Reserved.

The strict block error rate (BLER) requirement under the time-varying nature of wireless channels in Ultra-reliable low-latency communication (URLLC) systems pose sig-nificant challenges for link adaptation (LA). To tackle these challenges, we propose a novel LA method that adaptively selects the modulation and coding scheme (MCS) without requiring perfect channel knowledge which is unrealistic to obtain in URLLC. The goal is to maximize the coding rate while ensuring strict BLER constraints in URLLC systems. To achieve this, we utilize the Deep Q-Network (DQN) algorithm to select the MCS dynamically. Furthermore, we enhance the MCS selection process by using the Outer Loop Link Adaptation algorithm for transmission reliability improvement. Given the nature of URLLC, the samples of ACK and NACK are highly imbalanced, which can cause issues in the training process. To address it, we propose a novel training mechanism that improves the performance of DQN model and convergence speed during the training stage. Through extensive simulations, we demonstrate that our proposed algorithm outperforms existing methods regarding coding rate and imposing strict BLER constraints. © 2024 IEEE.

Virtual Reality (VR) applications have attracted great attention from both industry and academia in recent years. With an increasing demand for these applications, there is high pressure on resource and performance optimization using software-defined networking. In this paper, we consider one type of QoE models in the literature; and then use the Monte Carlo Tree Search and develop an SDN-based routing scheme to guarantee users' QoE for VR applications. Our routing scheme is tested using computer simulation in a 5x5 square grid network. Simulation results indicate that our routing scheme consistently outperforms the shortest path first (SPF) algorithm in terms of the QoE scores. © 2024 IEEE.

In this paper, we introduce rate-splitting multiple access (RSMA) into the network-assisted full-duplex (NAFD) MIMO system for downlink transmission. Based on this framework, we investigate the resource allocation problem of ultrareliable and low-latency communication (URLLC). Our objective is to maximize the total system throughput by jointly optimizing downlink beamforming, common rate allocation and uplink user power control. This problem is intractable due to its non-convex nature, thus we employ a low-complexity algorithm to obtain a suboptimal solution. Simulation results demonstrate that the proposed algorithm converges rapidly and significantly improves the system throughput. © 2024 IEEE.