Lianghui Ding

To enhance the anti-interference capability of uncrewed aerial vehicle (UAV) networks, many UAV nodes are now equipped with directional antennas. However, their narrow beamwidth significantly increases the latency of neighbor discovery. In conventional neighbor discovery protocols, each node scans independently, leading to redundant discoveries as adjacent nodes repeatedly scan the same regions. To optimize this process, we propose Co-ND, a collaborative neighbor discovery protocol that enables a discovering node to offload part of its scanning workload to neighboring collaborators. This protocol not only accelerates the discovery process but also preserves discovery completeness. To analyze the performance of Co-ND, we first model neighbor discovery as a state-transition process and derive a recursive expression for the delay. Then, by applying the additive-drift principle, we calculate the upper and lower bounds and a closed-form approximation for the delay, theoretically proving its advantages in delay reduction. Finally, we conduct extensive simulations under various settings. The results show that Co-ND significantly outperforms existing schemes in neighbor discovery latency, especially in narrow-beam scenarios.

Cooperative spectrum sensing (CSS) enables secondary users (SUs) to jointly detect primary user (PU) activity for efficient spectrum access. Federated learning (FL) has emerged as a promising solution for CSS due to its capabilities in distributed feature extraction and privacy preservation. However, conventional FL usually suffers from performance degradation under heterogeneous sensing conditions and leads to high communication overhead. This paper proposes a prior-assisted personalized FL (PFL) framework for CSS in multi-PU, multi-resource-block orthogonal frequency division multiplexing (OFDM) scenarios. We design a hybrid architecture consisting of SU-specific shallow models for local feature extraction and a shared deep model for global fusion. Additionally, we propose two inference schemes with quantized message passing, namely, probability aggregation and feature aggregation, and analyze their computational complexity and communication overhead. We formulate the PFL as a multi-class classification problem, in which the parameters of the shallow and deep models are coupled. To address parameter coupling in model training, we first approximate the original problem. Then, we derive a dual decomposition-based training algorithm that decomposes the global problem into parallel subproblems, yielding faster convergence and reduced communication overhead. Finally, we propose a pilot-assisted feature embedding method to enhance CSS performance and a reference-assisted training method to accelerate the learning process. Simulation results demonstrate that the proposed approaches accelerate convergence and boost detection accuracy by 5.9% – 70.6%, reduce communication overhead during inference by 10% – 70%, and maintain desirable inference speed in large-scale systems.

Unmanned aerial vehicle (UAV) swarms encounter the challenge of high overhead due to both network management and formation control requirements. In this paper, we propose a Bio-inspired Integrated Networking and Control (BINC) scheme, enabling efficient formation management for swarms comprising thousands of UAVs. The scheme forms a two-layer hierarchical structure, where network clusters and formations share the same groups so that cross-cluster control is eliminated. For networking, we design a fused routing message together with control information to reduce overhead, and limit clusters' size to local two-hop topologies for fast command transmission. For controlling, we develop a hybrid bio-inspired control approach, including a pigeon-like leader-follower algorithm within formations under the consideration of cluster topology maintenance, and a starling-like algorithm among formations that helps to improve the ability of obstacle avoidance. We establish a simulation platform for UAV swarms with over 1000 nodes, and experimental results show that the proposed BINC scheme can achieve highly maneuverable swarm formation marching with significant reduction on communication overhead.

Millimeter-wave (MMW) radar, as a widely used sensor, is increasingly employed in intelligent driving systems. Particularly in challenging driving conditions, such as adverse weather or varying light levels, radar often outperforms other sensors like camera and LiDAR. However, due to the relatively low resolution of radar sensors and its original complex data being difficult to process, deep learning approaches have been less explored in radar target detection compared to camera and LiDAR. Furthermore, we observe that existing methods in the literature often suffer from slow processing speeds and relatively low precision, which poses significant challenges for meeting the detection accuracy and real-time performance requirements of autonomous driving systems. To address these challenges, this paper proposes a lightweight radar target detection network designed to efficiently detect targets from FFT-processed radar frequency data in Range-Doppler spectrum format. The proposed model draws inspiration from YOLOv7-tiny and is further optimized to accommodate the specific characteristics of radar data. A novel, lightweight feature extraction backbone and a multi-scale feature enhancement network are introduced, significantly improving detection accuracy while reducing computational complexity. Additionally, to fully exploit radar data, various data augmentation strategies are explored, and a more efficient augmentation method is developed. Extensive experimental evaluations demonstrate that our model achieves superior detection accuracy and faster inference speed compared to state-of-the-art methods on the RADDet and CARRADA datasets.

Integrated sensing and communication (ISAC) is an essential technique for overcoming spectrum congestion. However, the performance of traditional ISAC systems with fixed-position-antennas (FPA) is limited due to insufficient spatial degree of freedom (DoF) exploration. Recently, fluid antenna (FA) with reconfigurable antenna position is developed to enhance the sensing and communication performance by reshaping the channel. This paper investigates an FA-enhanced ISAC system where a base station is equipped with multiple FAs to communicate with multiple single-antenna users and with FPAs to sense a point target. In this paper, we consider both perfect and imperfect channel state information (CSI) of the communication channel and sensing channel. In two cases, we focus on the maximization of the sensing signal-to-noise (SNR) by optimizing the positions of FAs and the dual-functional beamforming under the constraints of the FA moving region, the minimum FA distance and the minimum signal-to-interference-plus-noise (SINR) per user. Specifically, for the ideal case of perfect CSI, an iterative alternating optimization (AO) algorithm is proposed to tackle the formulated problem where the dual-functional beamforming and the FA positions are obtained via semidefinite relaxation (SDR) and successive convex approximation (SCA) techniques. Then, for the imperfect CSI case, we propose an AO-based iterative algorithm where $\mathcal {S}-$Procedure and SCA are applied to obtain the dual-functional beamforming and the FA positions. Furthermore, we analytically and numerically prove the convergence of the proposed algorithms. Numerical results demonstrate the notable gains and effectiveness of the proposed algorithms over baseline schemes.

In this paper, we investigate federated learning (FL) efficiency improvement in practical edge computing systems, where edge workers have non-independent and identically distributed (non-IID) local data, as well as dynamic and heterogeneous computing and communication capabilities. We consider a general FL algorithm with configurable parameters, including the number of local iterations, mini-batch sizes, step sizes, aggregation weights, and quantization parameters, and provide a rigorous convergence analysis. We formulate a joint optimization problem for FL worker selection and algorithm parameter configuration to minimize the final test loss subject to time and energy constraints. The resulting problem is a complicated stochastic sequential decision-making problem with an implicit objective function and unknown transition probabilities. To address these challenges, we propose knowledge/model-driven single-agent and multi-agent deep reinforcement learning (DRL) frameworks. We transform the primal problem into a Markov decision process (MDP) for the single-agent DRL framework and a decentralized partially-observable Markov decision process (Dec-POMDP) for the multi-agent DRL framework. We develop efficient single-agent and multi-agent asynchronous advantage actor-critic (A3C) approaches to solve the MDP and Dec-POMDP, respectively. In both frameworks, we design a knowledge-based reward to facilitate effective DRL and propose a model-based stochastic policy to tackle the mixed discrete-continuous actions and large action spaces. To reduce the computational complexities of policy learning and execution, we introduce a segmented actor-critic architecture for the single-agent DRL and a distributed actor-critic architecture for the multi-agent DRL. Numerical results demonstrate the effectiveness and advantages of the proposed frameworks in enhancing FL efficiency.

The costs of channel estimation, reflection adjustment, and computation have severe impacts on intelligent reflection surface (IRS)-aided physical layer security (PLS) wireless communication systems in practice but are usually overlooked for simplicity in most existing works. This paper considers a multi-antenna base station serving a single-antenna legitimate user with the assistance of a multi-element IRS under the surveillance of a single-antenna eavesdropper. Firstly, we introduce a partial instantaneous CSI and statistical CSI (PICSI-SCSI)-adaptive beamforming and SCSI-adaptive reflection design. Secondly, we maximize the achievable ergodic secrecy rate (ESR) with respect to the PICSI-SCSI-adaptive beamforming and SCSI-adaptive reflection design, resulting in a two-timescale stochastic non-convex problem. Thirdly, we present two stochastic iterative algorithms to reach stationary and approximate stationary points. Moreover, we show that the two proposed designs achieve lower computational complexities and adjustment costs for reflection than the existing PICSI-SCSI-adaptive beamforming and reflection design. Lastly, we numerically demonstrate the two proposed designs’ notable gains over baselines. To our knowledge, this is the first work providing an optimization-based PICSI-SCSI-adaptive beamforming and SCSI-adaptive reflection design in an IRS-aided PLS wireless communication system, achieving promising secure performance at the minimum adjustment cost for reflection.