In recent years, unmanned aerial vehicles (UAVs) have become a key role in wireless communication networks due to their flexibility and dynamic adaptability. However, the openness of UAV-based communications leads to security and privacy concerns in wireless transmissions. This paper investigates a framework of UAV covert communications which introduces flexible reconfigurable intelligent surfaces (F-RIS) in UAV networks. Unlike traditional RIS, F-RIS provides advanced deployment flexibility by conforming to curved surfaces and dynamically reconfiguring its electromagnetic properties to enhance the covert communication performance. We establish an electromagnetic model for F-RIS and further develop a fitted model that describes the relationship between F-RIS reflection amplitude, reflection phase, and incident angle. To maximize the covert transmission rate among UAVs while meeting the covert constraint and public transmission constraint, we introduce a strategy of jointly optimizing UAV trajectories, F-RIS reflection vectors, F-RIS incident angles, and non-orthogonal multiple access (NOMA) power allocation. Considering this is a complicated non-convex optimization problem, we propose a deep reinforcement learning (DRL) algorithm-based optimization solution. Simulation results demonstrate that our proposed framework and optimization method significantly outperform traditional benchmarks, and highlight the advantages of F-RIS in enhancing covert communication performance within UAV networks.

Unmanned aerial vehicles (UAVs) equipped with visible light communication (VLC) systems are envisioned to simultaneously provide secure data transmission and nighttime illumination. However, when buildings obstruct the optical links, both connectivity and lighting are disrupted, which may severely compromise system reliability and safety. This paper investigates an artificial noise-based physical layer security (PLS) scheme for a VLC-enabled UAV communication system in a multiuser environment with potential eavesdroppers, while explicitly incorporating awareness of shadowed area caused by blockage and enabling the UAV to autonomously adjust its trajectory to proactively avoid such shadow coverage to the ground users. We formulate a joint optimization problem of user association, power allocation, and UAV trajectory design to maximize the average secrecy rate of the system, while taking into account illumination requirements, shadowing effects, and UAV mobility. To tackle this mixed-integer and non-convex optimization problem, we decompose it into three subproblems and transform them into tractable convex forms. Furthermore, we also develop an iterative algorithm by leveraging successive convex approximation techniques under a block coordinate descent framework to efficiently obtain a suboptimal solution. Simulation results demonstrate that the proposed scheme can achieve fast convergence and improve the average secrecy rate at least by 51.1% compared with conventional schemes. Moreover, the algorithm still exhibits robustness and efficacy in exploiting the spatial-temporal trade-offs under severe eavesdropping threats and shadowing with diverse user geometries, highlighting its practicality for secure nighttime urban VLC-UAV communication.

As a critical component of sixth-generation (6G) wireless networks, ultra-reliable and low-latency communication (URLLC) is expected to support real-time and reliable information exchange in low-altitude environments. However, achieving URLLC often incurs significant resource overhead, including increased bandwidth consumption, higher transmit power, and denser access point (AP) deployment, which pose significant challenges to both spectral efficiency (SE) and energy efficiency (EE). Besides, existing iterative optimization algorithms are computationally intensive and struggle to meet the latency requirements of URLLC. To address these challenges, we propose a hybrid aerial-terrestrial cell-free massive MIMO (CF-mMIMO) network to support diverse services, along with a channel prediction network and a deep mixture of experts (MoE) network for uplink optimization. First, we design a channel prediction network (CP-Net) to mitigate channel aging caused by high-mobility user equipment (UE). CP-Net employs three Transformer-based sub-networks for aged channel state information (CSI) prediction, while a channel quality-aware loss function is introduced to improve the prediction accuracy of weak links. Based on the predicted CSI, we develop a deep MoE network (MoE-Net) for power allocation comprising three expert models targeting different objectives. Then, we introduce a weighted gating network (WT-Net) to learn an efficient adaptive combination of expert outputs. The proposed framework better captures heterogeneous UE requirements and improves communication performance under URLLC constraints. Numerical results demonstrate the effectiveness of the proposed method.

As satellite communications play an increasingly important role in future wireless networks, the issue of limited link budget in satellite systems has attracted significant attention in current research. Although semantic communications emerge as a promising solution to address these constraints, it introduces the challenge of increased computational resource consumption in wireless communications. To address these challenges, we propose a multi-layer hybrid bit and generative semantic communication framework which can adapt to the dynamic satellite communication networks. Furthermore, to balance the semantic communication efficiency and performance in satellite-to-ground transmissions, we introduce a novel semantic communication efficiency metric (SEM) that evaluates the trade-offs among latency, computational consumption, and semantic reconstruction quality in the proposed framework. Moreover, we utilize a novel deep reinforcement learning (DRL) algorithm group relative policy optimization (GRPO) to optimize the resource allocation in the proposed network. Simulation results demonstrate the flexibility of our proposed transmission framework and the effectiveness of the proposed metric SEM, illustrate the relationships among various semantic communication metrics.

Tracking micro-unmanned aerial vehicles (micro-UAVs) in low signal-to-noise ratio (SNR) environments poses significant challenges due to their weak radar cross-section (RCS) and the inherent limitations of traditional Detect-Before-Track (DBT) radar algorithms. This paper proposes a novel Track-Before-Detect (TBD) approach based on a Markov Chain Monte Carlo-Enhanced Particle Filter (MCMC-EPF), leveraging 4D Frequency Modulated Continuous Wave (FMCW) MIMO radar. By directly processing unthresholded multi-frame 4D-FFT radar data, the method achieves joint detection and tracking, effectively preserving weak target information that is typically lost in DBT methods. Experimental results on real radar data demonstrate that the proposed algorithm achieves robust and accurate UAV tracking, maintaining a root-mean-square error (RMSE) within 1 meter and an average relative tracking error below 2.5% under low SNR conditions. These results highlight the method’s potential for reliable UAV surveillance in challenging operational environments.

This article established a novel multi-input multioutput (MIMO) communication network, in the presence of full-duplex (FD) transmitters and receivers with the assistance of dual-side intelligent omni surface (IOS). Compared with the traditional IOS, the dual-side IOS allows signals from both sides to reflect and refract simultaneously, which further exploits the potential of metasurfaces to avoid frequency dependence, and size, weight, and power (SWaP) limitations. By considering both the downlink and uplink transmissions, we aim to maximize the weighted sum rate, subject to the transmit power constraints of the transmitter, the users and the dual-side reflecting and refracting phase shifts constraints. However, the formulated sum rate maximization problem is not convex, hence we exploit the weighted minimum mean square error (WMMSE) approach, and tackle the original problem iteratively by solving two subproblems. For the beamforming matrices optimization of the downlink and uplink, we resort to the Lagrangian dual method combined with a bisection search to obtain the results. Furthermore, we resort to the quadratically constrained quadratic programming (QCQP) method to optimize the reflecting and refracting phase shifts of both sides of the IOS. Simulation results validate the efficacy of the proposed algorithm and demonstrate the superiority of the dual-side IOS.

In this paper, we introduce a novel framework consisting of hybrid bit-level and generative semantic communications for efficient downlink image transmission within space-air-ground integrated networks (SAGINs). The proposed model comprises multiple low Earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and ground users. Considering the limitations in signal coverage and receiver antennas that make the direct communication between satellites and ground users unfeasible in many scenarios, thus UAVs serve as relays and forward images from satellites to the ground users. Our hybrid communication framework effectively combines bit-level transmission with several semantic-level image generation modes, optimizing bandwidth usage to meet stringent satellite link budget constraints and ensure communication reliability and low latency under low signal-to-noise ratio (SNR) conditions. To reduce the transmission delay while ensuring reconstruction quality for the ground user, we propose a novel metric to measure delay and reconstruction quality in the proposed system, and employ a deep reinforcement learning (DRL)-based strategy to optimize resource allocation in the proposed network. Simulation results demonstrate the superiority of the proposed framework in terms of communication resource conservation, reduced latency, and maintaining high image quality, significantly outperforming traditional solutions. Therefore, the proposed framework can ensure the real-time image transmission requirements in SAGINs, even under dynamic network conditions and user demand.

This paper presents a general framework for probabilistic relay selection (RS) in asymmetric buffer-aided cooperative relaying systems, which caters to scenarios with both perfect and imperfect channel state information (CSI) during the RS process. The framework extends and generalizes many existing buffer-aided RS schemes. In particular, we introduce an auxiliary stochastic process which assigns varying selection probabilities to different links, considering the dynamic wireless channel and buffer states. Subsequently, we leverage the obtained outage probability and average packet delay (APD) to formulate outage optimization problems while adhering to APD. To address the intricate high-dimensional optimization problems, we employ a deep learning (DL) approach, which involves designing probability mass functions for the auxiliary stochastic process and developing an effective loss function to update the neural network. Simulation results unequivocally demonstrate the superior performance of the proposed DL-based probabilistic RS scheme compared to benchmark schemes, particularly in scenarios involving imperfect CSI.

The space-air-ground integrated network (SAGIN) has become a crucial research direction in future wireless communications due to its ubiquitous coverage, rapid and flexible deployment, and multi-layer cooperation capabilities. However, integrating hierarchical federated learning (HFL) with edge computing and SAGINs remains a complex open issue to be resolved. This paper proposes a novel framework for applying HFL in SAGINs, utilizing aerial platforms and low Earth orbit (LEO) satellites as edge servers and cloud servers, respectively, to provide multi-layer aggregation capabilities for HFL. The proposed system also considers the presence of inter-satellite links (ISLs), enabling satellites to exchange federated learning models with each other. Furthermore, we consider multiple different computational tasks that need to be completed within a limited satellite service time. To maximize the convergence performance of all tasks while ensuring fairness, we propose the use of the distributional soft-actor-critic (DSAC) algorithm to optimize resource allocation in the SAGIN and aggregation weights in HFL. Moreover, we address the efficiency issue of hybrid action spaces in deep reinforcement learning (DRL) through a decoupling and recoupling approach, and design a new dynamic adjusting reward function to ensure fairness among multiple tasks in federated learning. Simulation results demonstrate the superiority of our proposed algorithm, consistently outperforming baseline approaches and offering a promising solution for addressing highly complex optimization problems in SAGINs.

In recent years, the amalgamation of satellite communications and aerial platforms into space-air-ground integrated network (SAGINs) has emerged as an indispensable area of research for future communications due to the global coverage capacity of low Earth orbit (LEO) satellites and the flexible Deployment of aerial platforms. This paper presents a deep reinforcement learning (DRL)-based approach for the joint optimization of offloading and resource allocation in hybrid cloud and multi-access edge computing (MEC) scenarios within SAGINs. The proposed system considers the presence of multiple satellites, clouds and unmanned aerial vehicles (UAVs). The multiple tasks from ground users are modeled as directed acyclic graphs (DAGs). With the goal of reducing energy consumption and latency in MEC, we propose a novel multi-agent algorithm based on DRL that optimizes both the offloading strategy and the allocation of resources in the MEC infrastructure within SAGIN. A hybrid action algorithm is utilized to address the challenge of hybrid continuous and discrete action space in the proposed problems, and a decision-assisted DRL method is adopted to reduce the impact of unavailable actions in the training process of DRL. Through extensive simulations, the results demonstrate the efficacy of the proposed learning-based scheme, the proposed approach consistently outperforms benchmark schemes, highlighting its superior performance and potential for practical applications.

This paper investigates a deep learning-based algorithm to optimize the unmanned aerial vehicle (UAV) trajectory and reconfigurable intelligent surface (RIS) reflection coefficients in UAV-RIS-aided cell-free (CF) hybrid non-orthogonal multiple-access (NOMA)/orthogonal multiple-access (OMA) networks. The practical RIS reflection model and user grouping optimization are considered in the proposed network. A double cascade correlation network (DCCN) is proposed to optimize the RIS reflection coefficients, and based on the results from DCCN, an inverse-variance deep reinforcement learning (IV-DRL) algorithm is introduced to address the UAV trajectory optimization problem. Simulation results show that the proposed algorithms significantly improve the performance in UAV-RIS-assisted CF networks.

This paper investigates a learning-based approach autonomously and jointly optimizing the trajectory of unmanned aerial vehicle (UAV), phase shifts of reconfigurable intelligent surfaces (RIS), and aggregation weights for federated learning (FL) in wireless communications, forming an autonomous RIS-assisted UAV-enabled network. The proposed network considers practical RIS reflection models and FL transmission errors in wireless communications. To optimize the RIS phase shifts, a double cascade correlation network (DCCN) is introduced. Additionally, the deep deterministic policy gradient (DDPG) algorithm is employed to address the optimization problem of UAV trajectory and FL aggregation weights based on the results obtained from DCCN. Simulation results demonstrate the substantial improvement in FL performance within the autonomous RIS-assisted UAV-enabled network setting achieved by the proposed algorithms compared to the benchmarks.

This paper proposes a secure transmission in reconfigurable intelligent surfaces (RIS) aided non-terrestrial cooperative networks (NTCN), where the practical phase-dependent model is considered in which the RIS reflection amplitudes change with the corresponding discrete phase shifts. Moreover, we employ a full-duplex transmission scheme at the relay nodes to reduce the long-range signal loss and improve the security between the satellite and the relay node. To solve the complex nonconvex optimization problem of the joint RIS reflection coefficient and relay selection optimization, we propose the deep cascade correlation learning (DCCL) algorithm to enhance optimization efficiency. Simulation results show that the proposed DCCL-based method significantly improves the secrecy capacity compared to the random relay selection and RIS coefficient methods.

In this paper, we study the simultaneous wireless information and power transfer (SWIPT) cooperative system, where one source forwards information to one destination with the assistance of multiple relays. Each relay is equipped with a finite data butter and a finite energy butter storing the harvested energy by radio-frequency (RF). An optimization problem is formulated for throughput maximization of the SWIPT cooperative system, taking into consideration the strict delay constraint, dynamic channel conditions, time-varying discrete data butter states and time-varying continuous energy butter states. A discrete-time Markov decision process (MDP) is adopted to model the relay selection process referring to data butter states and energy butter states. Two deep Q-network (DQN)based methods named invalid action penalty (IAP) and invalid action mask (IAM) are proposed. The simulation results show that the proposed IAM method can achieve better convergence and throughput performance than the IAP method.

This article proposes a novel machine-learning-based routing optimization for the multiple reconfigurable intelligent surfaces (M-RIS)-assisted multihop cooperative networks, in which a practical phase model for reconfigurable intelligent surface (RIS) with the amplitude variation based on the corresponding discrete phase shift is considered. We aim to maximize the end-to-end data rate in the proposed network by jointly optimizing the data transmission path, the passive beamforming design of RIS, and transmit power allocation. To tackle this complicated nonconvex problem, we divide it into two subtasks: 1) the passive beamforming design of the RIS and 2) joint routing and power allocation optimization. First, for the passive beamforming design of RIS, we develop a distributed learning algorithm that employs a cascade forward backpropagation network in each relay node to solve the RIS coefficients optimization problem by directly using the optimization target to train the cascade networks. This solution can avoid the curse of dimensionality of traditional reinforcement learning algorithms in the RIS optimization problem. Then, based on the result of RIS optimization, we introduce the proximal policy optimization (PPO) algorithm with the clipping method to find solutions for joint optimization of routing and power allocation via achieving the long-term benefit in the Markov decision process (MDP). Simulation results show that the proposed learning-based scheme can learn from the environment to improve its policy stability and efficiency in the iterative training process for optimizing routing and RIS and significantly outperform the benchmark schemes.

This article investigates the reinforcement learning for the relay selection in the delay-constrained buffer-aided networks. The buffer-aided relay selection significantly improves the outage performance but often at the price of higher latency. On the other hand, modern communication systems such as the Internet of Things often have strict requirement on latency. It is thus necessary to find relay selection policies to achieve good throughput performance in the buffer-aided relay network while stratifying the delay constraint. With the buffers employed at the relays and delay constraints imposed on the data transmission, obtaining the best relay selection becomes a complicated high-dimensional problem, making it hard for the reinforcement learning to converge. In this article, we propose the novel decision-assisted deep reinforcement learning to improve the convergence. This is achieved by exploring the a priori information from the buffer-aided relay system. The proposed approaches can achieve high throughput subject to delay constraints. Extensive simulation results are provided to verify the proposed algorithms.

This paper investigates asynchronous reinforcement learning algorithms for joint buffer-aided relay selection and power allocation in the non-orthogonal-multiple-access (NOMA) relay network. With the hybrid NOMA/OMA transmission, we investigate joint relay selection and power allocation to maximize the throughput with the delay constraint. To solve this complicated high-dimensional optimization problem, we propose two asynchronous reinforcement learning-based schemes: the asynchronous deep Q-Learning network (ADQN)-based scheme and the asynchronous advantage actor-critic (A3C)-based scheme, respectively. The A3C-based scheme achieves better performance and robustness when the action space is large, while the ADQN-based scheme converges faster with a small action space. Moreover, a-prior information is exploited to improve the convergence of the proposed schemes. The simulation results show that the proposed asynchronous learning-based schemes can learn from the environment and achieve good convergence.

This paper proposes a multi-agent deep reinforcement learning-based buffer-aided relay selection scheme for an intelligent reflecting surface (IRS)-assisted secure cooperative network in the presence of an eavesdropper. We consider a practical phase model where both phase shift and reflection amplitude are discrete variables to vary the reflection coefficients of the IRS. Furthermore, we introduce the buffer-aided relay to enhance the secrecy performance, but the use of the buffer leads to the cost of delay. Thus, we aim to maximize either the average secrecy rate with a delay constraint or the throughput with both delay and secrecy constraints, by jointly optimizing the buffer-aided relay selection and the IRS reflection coefficients. To obtain the solution of these two optimization problems, we divide each of the problems into two sub-tasks and then develop a distributed multi-agent reinforcement learning scheme for the two cooperative sub-tasks, each relay node represents an agent in the distributed learning. We apply the distributed reinforcement learning scheme to optimize the IRS reflection coefficients, and then utilize an agent on the source to learn the optimal relay selection based on the optimal IRS reflection coefficients in each iteration. Simulation results show that the proposed learning-based scheme uses an iterative approach to learn from the environment for approximating an optimal solution via the exploration of multiple agents, which outperforms the benchmark schemes.

In this paper, we investigate a Deep Reinforcement Learning based delay-constrained relay selection for secure buffer aided Cognitive Relay Networks (CRNs). We model the relay selection problem in secure butter-aided CRNs as a Markov Decision Process (MDP) problem, and introduce Deep Q-Learning to solve this MDP problem. In the proposed scheme, delay constraint is considered when the packets arriving at the receiver in CRNs. Moreover, we consider the security of data transmissions in butter-aided CRNs with an eavesdropper which can intercept the signals from the source and relays. Furthermore, we introduce ε-greedy strategy to balance the exploitation and exploration. The result shows compared with Max-Ratio scheme, the proposed scheme enhances the throughput with both delay and security constrained significantly in secure CRNs.

Generally speaking, digital libraries have multiple granularities of semantic units: book, chapter, page, paragraph and word. However, there are two limitations of current eBook retrieval systems: (1) the granularity of retrievable units is either too big or too small, scales such as chapters, paragraphs are ignored; (2) the retrieval results should be grouped by facets to facilitate user's browsing and exploration. To overcome these limitations, we propose a multi-granularity multi-facet eBook retrieval approach.

Keyphrases play a key role in text indexing, summarization and categorization. However, most of the existing keyphrase extraction approaches require human-labeled training sets. In this paper, we propose an automatic keyphrase extraction algorithm, which can be used in both supervised and unsupervised tasks. This algorithm treats each document as a semantic network. Structural dynamics of the network are used to extract keyphrases (key nodes) unsupervised. Experiments demonstrate the proposed algorithm averagely improves 50% in effectiveness and 30% in efficiency in unsupervised tasks and performs comparatively with supervised extractors. Moreover, by applying this algorithm to supervised tasks, we develop a classifier with an overall accuracy up to 80%.