ABSTRACT In federated learning (FL)‐assisted Internet of Things (IoT) systems, FL trains models using datasets on various client devices without sending the datasets to a centralized server. This approach enhances the accuracy and reliability of models while preserving the privacy of client devices. However, FL implementations face challenges, such as single point of server failure and lack of incentives. To address the server failure issue, a backup server can be added. Meanwhile, each FL client has varying data quality and motivations to participate, leading to differences in the quality of local models uploaded to the server. To motivate clients to contribute more, we designed a novel incentive mechanism based on the Stackelberg game. This mechanism allocates rewards based on the quality of the models each client uploads, rather than the amount of data trained. We separately modelled the utilities of the server and the clients, allowing the server to rationally allocate rewards based on each client's contribution to model training. After analysing the utilities, we transform the game into two optimization problems and develop an algorithm whose per‐round complexity scales linearly with the number of clients under fixed numerical tolerances. The obtained equilibrium matches exhaustive search within numerical precision while significantly reducing computation.

In resource constrained satellite-terrestrial integrated networks (STINs), satellite downlinks supporting earth stations often have to share the same band with terrestrial networks. Under this scenario, achieving secure and timely communication in STINs could be challenging due to the presence of co-channel interference, imperfect CSI, and potential eavesdroppers. Existing security techniques in STINs e.g. robust secure beamforming (BF) often overlook another key performance indicator of STINs, i.e. communication timeliness in terms of Age of Information (AoI). To overcome this issue, this paper proposes a new joint AoI and security-oriented optimization in enhancing the performance of STINs. Specifically, two schemes are developed to achieve low latency and secure BF, including a single-slot scheme and a multi-slot scheme. Specifically, we first establish a continuous-time AoI evolution model and derive a closed-form secrecy margin for the wiretap channel, which enables a unified characterization of information freshness and transmission security. Building on this, we incorporate imperfect channel state information (CSI) to formulate a single-slot joint optimization problem that explicitly targets both AoI-aware freshness and physical-layer security. The objective is to minimize the total transmit power, while meeting the required secrecy-margin constraints, quality of service (QoS) constraints, eavesdropping probability constraints, and pertransmitter power budget constraints. To handle this nonconvex problem, we first apply Bernstein inequalities to convert the probabilistic constraints into deterministic forms. Subsequently, an iterative difference-of-convex programming algorithm is proposed to derive the BF vectors. Furthermore, to capture multi-slot temporal dynamics, we extend the design to a multi-slot framework that considers the impact of random data arrivals on system performance and establishes queue stability conditions based on the data queue. We apply the Lyapunov optimization technique to transform the multi-slot stochastic problem into a per-slot penalized power minimization problem, after which each slot can be solved in the same manner as the single-slot design. Finally, experimental results show that the proposed single-slot scheme satisfies both security and timeliness requirements while significantly reducing system power consumption, whereas the multi-slot optimization retains these performance advantages and further enables a favorable trade-off between power consumption and queue stability.

This paper considers an integrated sensing and communication (ISAC) system, where two dual-functional base stations (BSs) serve their users and detect multiple targets. To improve detection accuracy while meeting communication quality of service, this paper proposes a two-phase cooperative target detection algorithm that relies on Capon-based adaptive beamforming and maximum likelihood estimation (MLE)-based hypothesis testing. Specifically, based on Capon’s detection results, the two BSs first scan targets with an omnidirectional beam and then track targets with a directional beam. Subsequently, multiple hypotheses regarding the locations of targets are established based on the detection results of the Capon method, and the MLE is employed for hypothesis testing to filter out ghost targets. Finally, simulation results show that the proposed algorithm achieves more precise angles-of-arrival estimation of multiple targets than conventional single-BS sensing, and enables high-precision localization by eliminating ghost targets.

Laser-based Simultaneous Localization and Mapping (SLAM) is fundamental to autonomous navigation systems. However, conventional frameworks such as Lightweight and Ground-Optimized LiDAR Odometry and Mapping (LeGO-LOAM) face challenges in geometric segmentation robustness, feature extraction accuracy, and loop closure reliability, especially in complex and dynamic environments. To overcome these limitations, this paper proposes LeGO-LOAM-RAS, a semantic-aware, graph-based LiDAR SLAM framework that integrates RandLA-Net for multi-class semantic segmentation, a depth-guided AFE strategy, and a semantic-contextual loop closure mechanism. In the proposed system, RandLA-Net replaces traditional geometry-based segmentation with a deep learning approach, enabling fine-grained scene understanding and the effective discrimination of objects such as roads, vehicles, and buildings. This enhances both local contextual awareness and global structural representation. The AFE module dynamically adjusts neighborhood configurations and angular resolutions based on depth cues, employing depth-error-based noise suppression and curvature refinement to improve the reliability of planar and edge features. For loop closure, a semantic-contextual descriptor is constructed by fusing geometric features with semantic histograms in a polar grid representation, introducing joint geometric-semantic constraints. This design improves loop closure robustness by mitigating ambiguity in perceptually similar environments and suppressing the impact of dynamic elements. Extensive evaluations on publicly available benchmark datasets validate the effectiveness of LeGO-LOAM-RAS, demonstrating substantial improvements in localization accuracy and overall system robustness compared to state-of-the-art methods.

In recent years, semantic segmentation of large-scale point clouds has garnered significant attention due to its critical role in 3D scene understanding. However, the inherent complexity and uneven distribution of large-scale point clouds, coupled with substantial inter-class similarity, significantly hinder the discriminative power of existing segmentation approaches. RandLA-Net has shown strong capabilities in directly inferring semantic information. Building upon this foundation, we proposed three redesigned modules to improve the accuracy of point cloud segmentation: a Local Contextual Feature (LCF) module, a Global Contextual Feature (GCF) module and, a Contextual Feature Enhancement (CFE) module. The LCF module preserves the local spatial encoding unit and introduces an improved dual attention mechanism that independently computes geometric and feature-based attention scores. This facilitates more effective local feature aggregation and overcomes the segmentation artifacts caused by the difficulty in distinguishing similar classes. To complement local representations, the GCF module is integrated to capture scene-level semantics across all 3D points by using the spatial position volume ratio, thereby addressing feature extraction from both local and global perspectives. The CFE module is designed as a plug-and-play component, which enhances feature representations by integrating richer contextual cues from both explicit 3D geometry and implicit feature spaces, along with global bilinear interactions. Comprehensive experiments on the S3DIS (indoor) and Semantic3D (outdoor) datasets show that our method attains Overall Accuracy (OA) scores of 89.8% and 95.3%, and mean Intersection over Union (mIoU) scores of 73.3% and 78.0%, respectively, outperforming existing methods and providing new perspectives for large-scale point cloud semantic segmentation across diverse environments.

Multi-unmanned aerial vehicle (UAV) assisted mobile edge computing enables aerial platforms to collaboratively provide computing services for delay-sensitive applications. In such systems, information freshness must be preserved while multiple UAVs simultaneously perform trajectory control, task offloading, and resource scheduling under practical energy, computation, and quality-of-service constraints. The Age of Information (AoI) metric inherently couples these decisions over long time horizons, making the design of effective coordination policies difficult for conventional optimization techniques and reinforcement learning methods. In this work, we develop a constraint-aware multi-agent decision transformer framework, referred to as Prompt-CMADT, to address AoI optimization in multi-UAV MEC networks. By casting multi-UAV coordination as a sequential decision modeling problem, the proposed framework captures long-term temporal dependencies among heterogeneous agents while explicitly accounting for system-level constraints. Moreover, a constraint-aware prompt mechanism is designed to steer policy generation toward feasible solutions, and an opponent action prediction module is introduced to alleviate inter-UAV resource contention. Numerical results demonstrate that Prompt-CMADT consistently reduces the average AoI and overall energy consumption, while improving resource utilization, when compared with representative baseline schemes.

Federated Learning (FL) confronts challenges such as resource constraints and unbalanced data distribution in the Space-Air-Ground Integrated Network (SAGIN). This paper proposes a Hierarchical Split Federated Learning (HSFL) framework considering satellite handoff and derives its upper bound of loss function affected by model splitting and data distribution. To minimize the weighted sum of training loss and latency, we formulate a joint optimization problem that integrates device association, model split layer selection, and resource allocation. We decompose the original problem into several subproblems, where an iterative optimization algorithm incorporating closed-form solutions and brute-force split point search is proposed. Simulation results demonstrate that the proposed algorithm can balance training efficiency and model accuracy for FL in SAGIN.

This paper investigates covert communications in an uncrewed aerial vehicle (UAV) assisted cellular system in the presence of a ground eavesdropper(Eav). To enhance the secrecy performance of a secure user (SU) while guaranteeing the quality-of-service (QoS) requirements of common users, a dual-UAV cooperative non-orthogonal multiple access (NOMA) framework with a two-slot transmission scheme, referred to as Spatio-Temporal-Energy Domain Cooperative NOMA (STEDC-NOMA), is proposed. In the considered architecture, an aerial base station (UAV-BS) and an aerial relay (UAV-Relay) collaboratively serve ground users, where the transmission is divided into two time slots and different common users are paired with the SU in each slot for NOMA superposition. By jointly exploiting temporal-domain two-slot cooperation, spatio-domain dual-UAV diversity, and energy-domain NOMA superposition, additional degrees of freedom are introduced for covert communication with fairer access. Based on this framework, a joint optimization problem of user pairing and resource allocation is formulated to maximize the overall secrecy capacity of the SU under the QoS constraints of common users. To support the proposed scheduling strategy, closed-form power allocation solutions are derived for the two slot respectively. Numerical results demonstrate that, compared with the previous benchmark schemes, the proposed STEDC-NOMA significantly improves the secrecy performance while satisfying the QoS demands and enhancing the access fairness of all users.

As a key paradigm in sixth-generation (6G) systems for enabling physical–virtual mapping and intelligent network management, Digital Twin (DT) networks demand high-precision, low-latency modeling and continuous updates of wireless environments. However, in dynamic urban scenarios, channel conditions are highly non-stationary, and traditional sensing schemes suffer from limitations in coverage, information timeliness, and scheduling efficiency. To address these challenges, this paper proposes an Integrated Communication-Computing-Intelligence-Controlling (ICCIC) network based on layered unmanned aerial vehicles (UAVs). The system comprises mobile edge servers (ESs) with trajectory control and scheduling capabilities, and statically deployed working UAVs responsible for wireless channel measurements. The collected data is offloaded to ESs for edge computing and local model construction, which supports subsequent DT channel modeling. A multi-objective optimization problem is formulated to jointly schedule UAV trajectories and data offloading, with Age of Information (AoI) and service delay as performance metrics. The optimization is subject to constraints including maximum task execution time and service fairness. To capture multi-type interactions among UAVs during sensing and coordination, we build a multi-relational heterogeneous graph and encode it with a graph neural network (GNN) to obtain structured system states. On this basis, we adopt a QMIX-based multi-agent reinforcement learning (MARL) framework under centralized training and decentralized execution (CTDE) is developed to learn cooperative scheduling policies. Simulation results demonstrate that the proposed method achieves superior performance in sensing timeliness, scheduling responsiveness, and policy convergence, providing robust support for efficient and reliable DT channel modeling.

The convergence of communication, sensing, and computing capabilities is a key trend in future 6th generation mobile (6 G) networks. Integrating unmanned aerial vehicles (UAVs) with federated learning can further enhance network performance in these areas while reducing resource overhead and protecting data privacy. However, due to limited spectrum resources and data heterogeneity, lack of client scheduling not only increases bandwidth pressure but also degrades training performance. Moreover, incentive allocation in federated learning directly influences whether UAVs accept client selection and participate in collaborative learning tasks. In order to solve the above problems, this paper designs an incentive assignment scheme for UAV clients in federated intelligent inspection based on communication-sensing-computing integration. This scheme comprehensively considers two dimensional metrics, client data quality and contribution value, for UAV incentive allocation and selection, hence abbreviated as the Multi Dimensional Scheme (MDS). MDS accounts for the communication, sensing, and computational energy consumption of UAVs, establishing a federated learning candidate pool through contract theory. Subsequently, UAVs that contribute more to model training are selected from the candidate pool via Bayesian optimization. Experiments conducted on multiple datasets show that, compared to existing methods, MDS effectively improves the accuracy of model training while reducing incentive costs.

Multivariate time series (MTS) forecasting is crucial in the finance, energy and transportation sectors. Although current models deliver high prediction accuracy, their complexity and extensive computational demands hinder practical deployment. To address these limitations, this paper introduces a lightweight multiscale spatio-temporal convolutional network (LW-MSTCNN) that leverages deep separable convolution (DSCNN) to build an efficient multiscale pyramid model to decrease model complexity and computational costs. Additionally, a multiscale attention (MA) mechanism is incorporated to selectively emphasize important features across different spatial and temporal scales, improving feature extraction and overall performance. This combined approach enhances the model’s ability to process high-dimensional data efficiently while capturing critical multiscale patterns, addressing key challenges in spatio-temporal data processing. Experimental results on four datasets demonstrate that the proposed model significantly reduces the usage of computational resources, with the parameter count reduced by 4 to 5 times, while maintaining comparable prediction accuracy. Additionally, extensive generalization experiments show that the model exhibits strong robustness. This highlights the effectiveness and practicality of the model in multivariate time series (MTS) forecasting.

Space-air-ground integrated vehicular networks (SAGVN) play a crucial role in the 6G system, offering global coverage and ultra-wide-area broadband access. Meanwhile, advancements in artificial intelligence (AI) have led to a significant increase in model inference demands, which come with stringent latency requirements. In this paper, considering the intelligent services in SAGVN, we explore the co-inference problem and improve the inference efficiency by performing model splitting, vehicle association, and resource allocation. This problem is solved iteratively by decomposing it into multiple sub-problems. In particular, the model splitting problem is addressed by systematically searching for the optimal split points. Besides, the joint vehicle association and resource allocation problem are reformulated into a monotone submodular function without satellites, and then a low-complexity submodular optimization algorithm is proposed. To further utilize the computing power of the satellite, we further introduce a resource reallocation algorithm based on the existing optimization results. These two subproblems can iterate alternately until the optimization goal converges. Simulation results show that the proposed algorithm can achieve better latency performance in several inference tasks.

This paper proposes a radio map reconstruction method based on the Neural Architecture Search Enhanced Deep Regularization Model. Traditional radio map reconstruction algorithms face many challenges, such as extremely sparse measurement data and complex wireless signal environments. To solve the problem of unstable output, an external regularizer is introduced to provide additional regularization input in the prediction process to assist the neural network in capturing the explicit prior information from the sparse measurements and performing restoration. Moreover, to ensure the efficiency of capturing implicit prior information, neural architecture search is adopted to optimize the structure of the completion network, further enhancing the robustness of the neural network and the accuracy of reconstruction. The experimental results show that our proposed method is more accurate and stable than the traditional completion methods, especially in the circumstance of a low sampling rate, and can better adapt to the situation of interrupting the probability distribution in unknown regions without a dataset.

Space-Air-ground integrated vehicular network (SAGVN) can provide substantial advantages for the Internet of Vehicles (IoV) with broad coverage and long-distance communications. However, efficient task offloading in SAGVN is difficult due to the dynamic and multi-dimensional characteristics of IoV. In this paper, we address a task offloading problem in SAGVN, where unmanned aerial vehicles (UAVs) and low Earth orbit (LEO) satellites collaborate to offer mobile edge computing (MEC) services to vehicles. Our goal is to jointly design service placement and task offloading strategies for each UAV to minimize overall system latency, subject to mobility, coverage, energy, and bandwidth constraints. The problem can be reformulated as a multi-agent Markov decision process (MAMDP), where each vehicle and UAV can act as an agent, and the actions taken by agents correspond to the optimal UAV trajectory, subchannel selection, task partition ratio, and offloading destination. Then, we decompose the problem into three sub-problems of service placement, task offloading, and subchannel selection. Given the extensive observation and action space, an iterative best response multi-agent proximal policy optimization (IBR-MAPPO) algorithm is proposed. Finally, simulation results show that our approach converges rapidly and achieves lower execution delay than baseline algorithms.

Symbiotic backscatter communication radio (SBCR) systems enable spectrum-efficient communication by allowing backscatter devices (BDs) to modulate and reflect primary transmitter (PT) signals. However, prior studies often assume circularly symmetric complex Gaussian (CSCG) signals for BDs, which is impractical for low-complexity BDs. This paper addresses this gap by investigating SBCR systems where the BD adopts one of two popular modulation schemes in wireless communications, i.e., binary phase-shift keying (BPSK) and quadrature phase-shift keying (QPSK) modulation schemes. We derive the PT’s rates for these modulation schemes, highlighting the critical role of BD’s modulation phase in enhancing the PT’s rate. We then formulate two optimization problems to maximize the PT’s rate by optimizing the BD’s reflection phases for BPSK and QPSK, respectively, and derive closed-form expressions for the optimal phases. Simulations validate our theoretical analysis, and reveal that BPSK modulation achieves a higher PT’s rate than that of QPSK.

Federated Learning (FL) is a promising paradigm for privacy-preserving collaborative intelligence in Internet of Vehicles (IoV) systems. In this work, vehicles are used to cooperatively train neural network models for the object recognition task. However, the inherent data heterogeneity across vehicles severely compromises the effectiveness of conventional FL frameworks that employ a unified global model. To address this challenge, we propose PFedOR - a confidence-aware personalized FL framework for vehicular object recognition. Specifically, we introduce a confidence quantification mechanism that uses public datasets on the server side to estimate class-specific confidence levels and data distribution patterns. Then, a personalized update strategy is employed, where batch normalization (BN) layers are regularized within a clustered structure through hierarchical clustering. At the same time, Non-BN layers are updated using similarity-based weighting across all vehicles. We conduct simulations on the nuImages dataset and experiment results demonstrate our approach’s superior performance against baseline methods, particularly under increasing data heterogeneity scenarios.

Federated learning for electric vehicle suspension (FLEVS) is a key technology to address the limitations of battery capacity and the rising use of sensing cameras in electric vehicles. However, current FLEVS systems face challenges such as energy constraints, privacy risks, and copyright issues in car enterprise cloud (CEC) trained models. This paper proposes a frozen watermark-based federated learning incentive mechanism to tackle these issues. It incorporates a global frozen watermark to leverage continuous learning while minimizing training interference. Additionally, a Stackelberg game-based incentive mechanism between the CEC and mobile vehicles (MVs) optimizes information security strategies. The derived optimal reward function and iteration parameters are validated through numerical results, demonstrating the scheme's effectiveness.

Integrating vision and touch is key to understanding the physical world, but it faces two main challenges: effective multimodal fusion and high-fidelity tactile representation. This paper proposes a multimodal semantic communication framework based on foundation models through visual-tactile fusion. First, a multimodal enhancement fusion network extracts deep features from video to improve tactile recognition and semantic understanding. Second, a CLIP-driven framework, grounded in a tactile knowledge base, enhances the accuracy of tactile information transmission. An end-to-end model with joint source-channel coding further improves transmission efficiency. Finally, we introduce a tactile generative reconstruction method using ImageBind, which ensures high similarity in both visual features and pressure distribution. Experimental results confirm the effectiveness of our approach in semantic tactile reconstruction. Overall, the proposed method enables efficient, low-bit-rate communication with high semantic fidelity, offering a promising solution for visual-tactile fusion in real-world applications.

The cellular Internet of Things (IoT) enhanced by federated learning (FL) is a potential paradigm to leverage the vast amount of data generated by the IoT devices and offer various intelligent applications. Through its distributed learning manner, the privacy and delay problems of the learning process are well handled. Nevertheless, in the cellular IoT, FL requires multiple rounds of model parameters exchanging between the parameter server and multiple clients over unstable wireless links, which largely constrains the communication efficiency. Regarding this problem, we propose the training data cost ratio to evaluate the communication efficiency, and then by maximizing this metric, client scheduling, transmitting power, and bandwidth are jointly formulated. The formulated problem is decomposed via problem transformation and derivations, and then, the Lagrange method and greedy-based algorithms are developed to solve the subproblems efficiently. Simulation results verify the advantages of our algorithm in communication efficiency improvement. Moreover, it reveals that the proposed metric and joint optimization substantially obtain superior tradeoff between learning performance and resource consumption compared to the client number oriented optimization.

While being able to avoid single point failures, emerging decentralized security techniques are facing new challenges of reliability, robustness, and privacy preservation in blockchain-enabled Internet of Things (IoT) systems. To circumvent these issues, a zero-trust security scheme is proposed through distributed access control, enhanced authentication, dynamic authorization, and privacy preservation enabled by the consortium blockchain. The proposed scheme integrates three key components, i.e., a distributed recommendation mechanism, where multiple authorized nodes are utilized as referrers to efficiently confer their trust on a new public entity for enhanced authentication; an anonymous credential generation strategy, which is developed for the new entity to further protect its privacy from linking attacks; and an adaptive reputation update strategy, which is proposed for evaluating the nodes’ behaviors in the system for accountability and dynamic multiple-level authorization. The proposed scheme is implemented in a Hyperledge Fabric and the results show that it significantly enhances security and protects private information.

In dynamic and cluttered environments, traditional Simultaneous Localization and Mapping (SLAM) systems often suffer from degraded localization accuracy and unstable map construction due to the presence of moving objects and occlusions. To address these challenges, we propose DFusion-SLAM, a lightweight and robust SLAM framework that integrates an enhanced object detection module into ORB-SLAM3. The detection module is based on an improved D-Fine architecture, in which the original Transformer is replaced with a more efficient PolaLinear Attention mechanism. Furthermore, a MetaFormer-based semantic fusion structure is introduced to strengthen multi-scale feature representation. These architectural improvements jointly enhance detection accuracy while reducing model complexity, achieving a performance increase from 42.8% to 43.7% mean Average Precision (mAP). Experimental evaluations on dynamic RGB-D sequences from the TUM and Bonn datasets demonstrate that DFusion-SLAM significantly improves localization accuracy and mapping stability under dynamic conditions, while maintaining high computational efficiency. These results highlight the framework’s strong potential for real-time deployment in IoT-oriented mobile and robotic platforms operating in complex environments.

To enhance the reliability and stability of simultaneous localization and mapping (SLAM) in dynamic environments, we propose a novel SLAM system integrating an advanced real-time object detection algorithm, the real-time detection transformer (RT-DETR). Our approach combines RT-DETR’s object detection capabilities with an optical flow-based dynamic thresholding method, effectively filtering out feature points associated with dynamic objects and thereby improving SLAM performance in such environments. We have optimized RT-DETR by substituting its original network backbone with lightweight modules, which reduces the number of parameters by 45% while only incurring a 5% reduction in accuracy. This optimization significantly lowers computational costs, making it feasible for deployment on mobile devices. Experiments conducted on the TUM and BONN dynamic datasets demonstrate that our system reduces the root mean square error (RMSE) of absolute trajectory and relative pose error (RPE) by approximately 28.82% compared to oriented fast and rotated brief-SLAM3 (ORB-SLAM3). Furthermore, experiments conducted on both a high-performance device and an embedded device demonstrate that, compared to Crowd-SLAM, which employs you only look once (YOLO) for dynamic object removal, our approach achieves an 8.52% improvement in absolute trajectory error (ATE), while the average frame per second (FPS) only decreases by 3.07%.

Accurate streamflow (SF) forecasting is crucial for effective water-resource management amid global climate change. Traditional ensemble SF-forecasting methods, relying on historical data and watershed characteristics, often produce uncertainties in their input, structure, and parameters, reducing their forecasting accuracy. This study introduces a variance-combined bias-correction (VCB) method, integrated with Internet of Things (IoT) technology to improve ensemble SF forecasts’ accuracy and responsiveness. The VCB method significantly improves the SF-forecasting performance by incorporating variance information from ensemble forecasts along with the ensemble mean. We apply the method to the Shiquan Reservoir in China’s Han River basin, and the results show that the VCB method outperforms the Bayesian joint probability (BJP) method, achieving an increases of 8.8% in the Nash-Sutcliffe efficiency (NSE), 0.7% in the Pearson correlation coefficient (PCC), 2.1% in the qualified rate (QR), and a 7.2% reduction in the mean absolute percentage error (MAPE). Furthermore, IoT technology integration improves method inputs’ accuracy and timeliness, showing the strongest performance during extreme weather events. Thus, by improving uncertainty management and forecasting accuracy, the IoT-integrated VCB method provides more effective support for water-resource management. Future research should apply this approach to diverse hydrological contexts and explore deeper integration with machine-learning techniques.

In the 5G era, the demand for high-quality communication services has rendered spectrum resources increasingly scarce, particularly for remote users (UEs). Unmanned Aerial Vehicles (UAVs) provide a viable solution to this challenge by facilitating dynamic spectrum sharing. This paper proposes a hybrid two-stage Stackelberg game model that enhances UAV-assisted communications by integrating both static and dynamic spectrum-sharing strategies. In this model, UAVs serve as relays for base stations (BSs) to serve remote UEs. They can optimize spectrum allocation and negotiate pricing directly with UEs instead of BS, thereby reducing the burden on BS. The model operates in two stages: In the first stage, UAVs act as followers with BS as leaders; In the second stage, UAVs become leaders in interactions with remote UEs. Our analysis focuses on the effects of spectrum sharing and pricing strategies on system performance, emphasizing the enhanced utility for BS, UAVs, and UEs. We demonstrate that the proposed model significantly improves spectrum efficiency, particularly under high-demand conditions, and maintains stable and efficient operations within UAV-assisted communication systems, as supported by simulation results.

To address the low efficiency of traditional spectrum-sharing systems, UAVs can serve as airborne relays to enhance user communication services. However, the issues of spectrum scarcity and underutilized spectrum holes have not been fully resolved. Therefore, designing an effective spectrum resource reallocation mechanism is essential to improve spectrum utilization efficiency further. Moreover, existing research rarely explores co-channel interference arising from spectrum trading between UAVs and often overlooks queuing mechanisms in spectrum trading scenarios. This paper proposes a dynamic spectrum-sharing scheme (DSS) leveraging UAV-assisted communication to address these challenges. To enhance spectrum utilization, a two-level Stackelberg game-based incentive mechanism is developed for on-demand UAV spectrum trading. Additionally, a co-channel interference preference-based spectrum matching scheme (CIPS) is designed, which comprehensively considers co-channel interference resulting from spectrum sharing and prioritizes the importance of UAV users’ services. Finally, optimal pricing and trading volume strategies are efficiently determined using a gradient-based iterative search algorithm. Simulation results demonstrate that the proposed model achieves higher system revenue, which is 8.97% to 186.82% higher than other models, and ensures flexible spectrum allocation and effective co-channel interference mitigation.

The development of Industrial Internet of Things (IIoT) applications presents a critical challenge in terms of latency limitation, particularly considering the limited availability of resources that prevent a single fog device from fully executing large-scale computing tasks. In such scenarios, enabling distributed computing across multiple fog servers or collaborating with cloud servers holds promising potential. To improve the efficiency of task offloading while accounting for the crucial role of movable fog devices (e.g., robots and unmanned cars), we formulate a joint optimization problem as a partially observable Markov decision process (POMDP), incorporating offloading decisions, computing resource allocation, and trajectory optimization under constraints related to available resources and collision avoidance. Due to the nondeterministic polynomial-time hardness (NP-hardness) in the problems of task offloading and resource allocation, we reformulate a matroid-constrained submodular maximization problem and propose an iterative low-complexity algorithm to find solutions. Subsequently, extracting better solutions from submodular optimization, we propose a multiagent reinforcement learning (MARL)-based algorithm to solve the trajectory optimization problem for the movable fog devices acting as agents, making decisions based on their local observations. Finally, simulation results have validated that the proposed scheme has a superior performance compared to the baselines.

We investigate the spectral and energy efficiencies of the uplink in an integrated satellite-terrestrial cell-free massive multiple-input multiple-output (IST-CF-mMIMO) system assisted by rate-splitting multiple access (RSMA). In the IST-CF-mMIMO system, the terrestrial users employ RSMA to transmit a message as a superposition of two parts with different power to the terrestrial access points and low-Earth-orbit satellite. Taking realistic conditions such as the spatially correlated Ricean fading channels, imperfect channel knowledge, and successive interference cancellation into account, we derive rigorous closed-form expressions for uplink achievable spectral and energy efficiencies and evaluate these performance metrics across a range of system configurations. Additionally, to enhance the system energy efficiency, we formulate the design of users’ power control coefficients as an energy efficiency optimization problem and design an efficient algorithm based on Lagrangian dual transformation and quadratic transformation techniques to solve it. Comprehensive simulations validate our theoretical propositions and evaluate the efficacy of the proposed energy efficiency maximization algorithm.

In this article, a novel multiuser multiple-input-multiple-output (MIMO) communication system for Internet of Things (IoT) is proposed, where the aerial reconfigurable intelligent surface (ARIS) and nonorthogonal multiple access (NOMA) are used as the sum rate enhancement pathway. The base station (BS) has multiple antennas that transmit superimposed signals to multiple users. The passive ARIS serves as a flexible transmit relay to reduce path loss and improve channel gains. Users are divided into several groups based on their channel status, each sharing a radio frequency (RF) chain. To maximize the sum rate of all users, the placement of ARIS, the passive/active beamforming design and the power allocation among users are jointly optimized. As the joint optimization for user grouping, passive/active beamforming and power distribution is formulated as a mixed-integer nonlinear program (MINLP) which is nonconvex and coupled and hence, obtaining an optimal solution is challenging. In this article, the problem is decoupled into three subproblems and solved alternately efficiently. The numerical results demonstrate that the suggested MIMO-ARIS-NOMA system can achieve higher sum rate performance than traditional schemes.

In Industrial Internet of Things (IIoT), timely detection of equipment failures and predictive maintenance are crucial. Leveraging Federated Learning (FL) allows for distributed model training on inspection devices, enabling predictive maintenance without compromising data privacy. However, Traditional FL faces communication and scalability challenges in large scale industrial scenarios. While hierarchical federated learning (HFL) improves flexibility, it struggles in signal-unstable scenarios. This paper proposes a UAV-assisted HFL framework for distributed remote inspection in IIoT, where UAVs enhance communication via high-altitude links and act as edge servers to collect and aggregate model parameters, reducing the central server’s communication burden and improving training efficiency. In this framework, energy-constrained edge clients face challenges of energy efficiency and data silos, while UAV deployment and energy limitations must also be addressed. To optimize fair and energy-saving training, we formulate an optimization problem to minimize energy consumption based on communication and training costs. This is decomposed into two sub-problems: (1) client selection, tackled as a multi-objective optimization using a MAB-based algorithm with a customized reward function balancing energy use and fairness; (2) UAV scheduling, addressed with a heuristic algorithm to optimize edge server deployment. Combining these schemes enables efficient scheduling for large-scale IIoT inspections. Finally, simulation experiments demonstrate the proposed strategy’s significant advantages in reducing system energy consumption, enhancing model accuracy, and improving fairness.

This paper explores the potential of employing rate-splitting multiple access to enhance the achievable rate and energy efficiency (EE) of an uplink cell-free massive multiple-input multiple-output (MIMO) system, where the access points (APs) are configured with low-resolution analog-to-digital converters (ADCs) to minimize the hardware expense and power consumption. Taking the large-scale fading decoding, ADC quantization, and imperfect successive interference cancellation into consideration, a rigorous closed-form rate expression is derived within Ricean fading environments. This analytical framework facilitates an in-depth analysis of the rate performance with respect to various system parameters. To quantify the benefits of low-resolution ADCs, a power consumption model is subsequently incorporated into the analysis, facilitating an evaluation of the system’s EE. Furthermore, the optimization of power control coefficients and receiver weights is tackled through the formulation of weighted sum-rate (WSR) and EE maximization problems. Two efficient alternative algorithms are then proposed to determine their optimal solutions. The theoretical propositions and the efficacy of the proposed WSR and EE optimization algorithms are substantiated through comprehensive simulations.

Most kernel-driven models for urban thermal anisotropy (UTA) assume the hotspot aligns with the sun, yet field observations often show a notable angular offset. Its impact on model performance remains underexplored. This letter evaluates four representative models—two single-kernel (ROU, RL) and two dual-kernel (VRO, VRL)—using UAV-based multi-angular thermal observations. Replacing the sun position with the observed hotspot significantly has reduced hotspot–sun angular offsets (to 2.6° for single-kernel and 1.8° for dual-kernel models) and improved UTA simulation accuracy (with RMSEs of 2.9 °C for single-kernel and 3.9 °C for dual-kernel models). In contrast, sun-based single-kernel models showed large angular errors (approx. 19.3°) and higher RMSE (approx. 3.4 °C). Dual-kernel models, however, exhibited lower sensitivity to the offset (approx. 8.8°, RMSE approx. 1.7 °C), which is likely due to the compensatory effect of the empirical base shape kernel. We further constructed offset-aware models using modified sun positions. This improved single-kernel model performance (offset approx. 16.0°, RMSE approx. 2.2 °C), with marginal benefits for dual-kernel models (offset approx. 7.5°, RMSE approx. 1.8 °C). Overall, dual-kernel models demonstrated greater robustness and accuracy. Future research should prioritize physics-informed semi-empirical dual-kernel formulations that explicitly account for directional thermal radiation features. This letter provides a theoretical basis for optimizing kernel-driven UTA modeling.

Clustered vehicular federated learning (CVFL) facilitates data sharing and collaborative decision-making among vehicles, thus refining traffic behavior and demonstrating the immense potential for transforming intelligent transportation systems into a reality. However, non-independent and identically distributed data and diverse model requirements among vehicular clients hinder the feasibility of a one-size-fits-all model. Besides, “selfish” vehicular clients may be unwilling to participate in learning tasks because of the huge resource consumption of the training process. To address these challenges, in this paper, we first group local models using the adaptiveK-means-based model grouping method and then aggregate the models within each group to generate CVFL models for subsequent multi-model training. Secondly, we propose a dynamic matching-based clustering method based on the local data quality and similarity to achieve efficient vehicular client clustering. Subsequently, a meticulously crafted hierarchical incentive mechanism, grounded in a three-stage Stackelberg game, is introduced to incentivize both cluster heads and members in a layered fashion, with the initiation stemming from the CVFL server. To determine the optimal strategies for the three-stage game, an iterative algorithm is proposed, and near-optimal analytical solutions are obtained with reduced complexity. The simulation results demonstrate that our CVFL system, augmented with the hierarchical incentive mechanism, can effectively motivate multiple clusters to train multiple models in parallel, thus improving overall efficiency.

In space communications, the signal’s long-distance transmission between a flying transmitter-receiver pair encounters two obstacles: a huge path-loss and a high-speed movement. The huge path-loss results in a low signal-to-noise ratio (SNR) and the high-speed movement brings a dynamic Doppler-shift, thus posing a great challenge for Doppler-shift acquisition. Under the low SNR, the Doppler-shift acquisition has to accumulate many symbols in a long-time period. However, during this period, the dynamic Doppler-shift disperses all these symbols’ total energy over a wide range, thus causing the energy dispersion problem. To address this problem, we propose a probabilistic-search and neighbor-density (PSND) scheme, where the probabilistic-search considers the element’s amplitude and sacrifices some redundant signal elements for a narrower search-range, while the neighbordensity sums the signal element’s all neighbors for a larger signal energy. The PSND scheme includes two algorithms: the Generic PSND and Iterative PSND. The Generic PSND algorithm first selects some search-elements with their probabilities to construct a probabilistic-search-range, then selects some density-elements with their neighbor-elements to derive the neighbor-densities, and finally searches the largest neighbor-density to obtain the acquisition result. Built upon the Generic PSND algorithm above, the Iterative PSND algorithm iteratively updates the searchelements to further strengthen the neighbor-density in a narrower probabilistic-search-range. Moreover, the simulations results have demonstrated our PSND scheme’s higher acquisition probability, as compared with the existing schemes.

Radio frequency fingerprint (RFF) identification is a promising solution for Internet of Things (IoT) device authentication. However, this technique encounters practical challenges such as noise interference, channel coupling, and open-set recognition (OSR). This paper proposes a unified RFF-OSR framework to jointly address these problems in complex environments. Firstly, the framework mitigates the noise interference by employing a low-pass filter-integrated autoencoder, where the low-pass filter is used to obtain a “quasi-clean” signal as the autoencoder reference, thereby reducing the demand for ideal signals. Then, the channel influence on RFF is modeled as three types: frequency offset, phase noise, and amplitude distortion. Based on this model, parameterized channel augmentation is performed to improve the generalization ability of RFF identification in unknown channel scenarios. In terms of OSR, instead of a coarse-grained uniform probability threshold for rogue device recognition, we conduct independent similarity judgments for all legitimate classes, each with an individual threshold. It effectively reduces information loss in the feature probability transformation and increases OSR performance. Under additive white Gaussian noise (AWGN) and multipath channel conditions, our method achieves OSR accuracies of 99.37% and 97.05% in ZigBee device identification, respectively, which demonstrates the effectiveness of our approach.

The security of virtual power plant (VPP) communication networks is paramount, particularly owing to growing increase in the reliance on distributed energy resources (DERs) using cloud-edge architectures. VPPs are increasingly vulnerable to cyber intrusion owing to the large number of access devices involved. Existing intrusion detection methods often face challenges in addressing the complexity of VPP networks, and lack adaptability to diverse attack patterns. To address the dynamic nature of VPPs, this study proposes a novel intrusion detection approach called dynamic detection combining transformer with feature filtering (DTF-VPP), which integrates principal component analysis (PCA) with a transformer-based model to improve the detection efficiency and accuracy. The key contributions of this study include a feature selection process that uses PCA to reduce the model complexity, and a dynamic loss-weighting mechanism that adapts to high-frequency attacks. The experimental results on the NSL-KDD dataset demonstrate that DTF-VPP outperforms conventional models in terms of the accuracy and F1-score. Therefore, this approach offers a scalable and adaptive solution for enhancing the security of VPPs against cyber threats.

Traditional cell-free massive multiple-input multiple-output (CF-mMIMO) systems face challenges of resource scarcity, cognitive limitations, and coverage blind spots, which primarily stem from the extensive deployment of long cables connecting each access point to the central processing unit in the system. To maximize the minimum achievable user rate and enhance the performance of a downlink CF-mMIMO system, we propose an innovative scheme that jointly integrates user association, unmanned aerial vehicle (UAV) placement, and transmission power allocation, with UAV-satellite assisted. The scheme also considers stringent constraints, including maximum power capacities, cross-layer interference limitations, and essential coverage demands. Confronting the complexity of the initial non-convex optimization challenge, we dissect it into more tractable sub-problems that encompass user association, UAV placement, and power allocation. Our approach employs an iterative algorithm, systematically resolving these sub-problems in sequence. Simulation results conclusively demonstrate the efficacy of the proposed scheme in optimizing system resource allocation and achieving comprehensive coverage.

Unmanned aerial vehicles (UAVs) are increasingly pivotal as mobile access points in cell-free massive multiple-input multiple-output (CF-mMIMO) systems, supporting both communication and task execution. To extend UAV endurance during complex missions, this paper explores the energy transmission and trajectory design for UAVs utilizing wireless power transfer (WPT) in the CF-mMIMO systems. By optimizing UAV flight trajectory, charging/discharging slots, and beamforming, communication fairness among outage users (UEs) is enhanced while considering the energy consumption constraints imposed by energy replenishment from access points during mission execution. To address this complex problem, we propose an angle search-based communication-assisted deep Q-network (DQN) algorithm, facilitating targeted spatial exploration. Simulation results demonstrate that the proposed approach effectively balances energy efficiency and communication requirements, improving UAV resource utilization and ensuring communication fairness for interrupted UEs, ultimately achieving dynamic regional coverage.

Federated Learning (FL) is a new way of training models used in Internet of Things (IoT) systems. It is a method that maintains the privacy of client devices while improving model accuracy and reliability. However, there is a problem in FL applications due to the lack of incentives. Clients have different motivations and produce different quality datasets, which leads to a divergence in the quality of local models uploaded to the central server. To address this issue, we propose a new incentive model based on the Stackelberg game. The mechanism we suggest distributes rewards based on the quality of the models uploaded to the server by each client, rather than the amount of data trained. We transform the model into two optimization problems, and we propose a linear complexity algorithm to solve them. This algorithm can achieve the optimal solution and greatly reduce computational complexity, as shown in our experimental results.

Incentive mechanism is an effective approach to encourage user participation in the Federated Learning (FL) process and improve training efficiency. However, current research often focuses on scenarios with complete information or weak information asymmetry between the server and users, and few studies consider incentive mechanism design in strong asymmetric information scenarios. Meanwhile, most works assume that users' resource contributions to model performance are independent of each other, which is not consistent with practical situations. To tackle these challenges, we design an incentive contract tailored for scenarios with strong information asymmetry. Our contract leverages the probability distribution of user types to ensure its appropriateness. Furthermore, taking into account the correlation of the users' resource contributions, we propose an iteration algorithm to determine the set of optimal contract items that satisfy the constraints of individual rationality (IR) and incentive compatibility (IC). Our simulation results show that our contract can effectively motivate multiple users to take part in the training process, enabling the server to achieve utility close to those in weak asymmetric information scenarios while maintaining robustness.

Abstract In recent years, the Integrated Satellite Aerial Terrestrial (I‐SAT) network has garnered significant attention as an innovative and integrated communication system. However, it still encounters interference in the face of the complex external environment. In this context, reconfigurable intelligent surface (RIS) provides a key way of solving this problem and effectively improves the performance and stability of the I‐SAT network. This article considers the combination of unmanned aerial vehicle (UAV) and RIS and proposes a novel architecture for sub‐connected active RIS (ARIS) under the energy consumption constraints of UAV and ARIS. The authors first provide a UAV‐ARIS based position prediction strategy for the vehicle. Then, a joint RIS phase shift, amplification and UAV trail optimization algorithm is proposed to pursue a high achievable rate. The interference between each link and the total energy consumption are all taken into consideration. In addition, a deep deterministic policy gradient (DDPG) algorithm is utilized for the optimization problem, and achieves convergence in continuous action space. Finally, the simulation results affirm the precision of the proposed method in significantly enhancing performance compared to other schemes.

Deep learning (DL)-based automatic modulation classification (AMC) has made breakthroughs and is generally used for signal detection and recognition in wireless communication systems, unmanned aircraft vehicle (UAV) systems, and other fields. However, high storage and computational demands limit its use in resource-constrained UAV systems. This paper presents an AMC method featuring a streamlined design with lower computational needs, using the ultra-lite convolutional neural network (ULCNN). This innovative model combines data augmentation, complex-valued convolution, separable convolution, channel attention, and shuffling techniques for enhanced performance. The proposed ULCNN model balances efficiency and accuracy, with simulations showing it achieves 62.47% accuracy on the RML2016.10a dataset using only 9,751 parameters. Furthermore, we evaluated the actual speed of ULCNN on a Raspberry Pi, an edge platform with roughly equivalent computing power to a conventional UAV, achieving an inference speed of only 0.775 ms per sample. This high performance, coupled with a significantly smaller model size, underscores the potential of ULCNN for integration into resource-constrained UAV systems, thereby enabling rapid and efficient data processing.

With rapid adoption in vertical industries and further assistance of edge computing, Internet-of-Things (IoT) applications are experiencing phenomenal growth. However, the concurrence of heterogeneous IoT devices, limited system resources, and varying network conditions poses an ultimate challenge to resource scheduling for meeting the increasingly diverse requirements of IoT applications. Most existing resource scheduling techniques are achieved using common performance indicators for all devices as the optimization objective, which may lose effectiveness when dealing with the diverse requirements across heterogeneous IoT devices. Towards this end, we focus on enhancing IoT device-specific Quality of Experience (QoE) through jointly optimizing communication and computation resources. First, a three-layer QoE assessment model is constructed to characterize the general correlation between resource provisioning and device-specific QoE. Then, to maximize the overall QoE amongst IoT devices, a two-stage resource scheduling scheme is proposed to realize the simultaneous optimization of IoT devices and the edge system. Specifically, during stage I, a distributed resource scheduling algorithm with low complexity is designed for each IoT device to optimize the local computing rate by considering its resource-constrained nature. During stage II, a Proximal Policy Optimization (PPO)-based online learning approach is proposed on the edge system to schedule communication bandwidth and optimize computational rate. Finally, extensive experiments demonstrate that our proposal outperforms the existing works from the perspective of QoE performance.

Federated learning (FL) framework enables user devices to collaboratively train a global model based on their local data sets without privacy leak. However, the training performance of FL is degraded when the data distributions of different devices are incongruent. Fueled by this issue, we consider a clustered FL (CFL) method where the devices are divided into several clusters according to their data distributions and are trained simultaneously. Convergence analysis is conducted, which shows that the clustered model performance depends on cosine similarity, device number per cluster, and device participation probability. Besides, to quantify the training performance, the utility of clustered model training is defined based on the analysis results. Then, aiming at optimizing the system utility, a joint problem of resource allocation and device clustering is formulated, which is solved by decoupling it into two subproblems. First, given the results of device clustering, a low-complexity iterative algorithm based on the convex optimization theory is proposed to make the bandwidth allocation and the transmit power control. Then, according to the individual stability, a coalition formation algorithm is proposed for the device clustering. Finally, the real-data experiments on the classification tasks (e.g., MNIST, CIFAR-10, and CIFAR-100) validate the results of convergence analysis and advantages of the proposed algorithm in terms of the test accuracy.

Automatic modulation classification (AMC) holds a significant position in physical-layer security, offering an innovative method to enhance the security of data transmission and anti-interference ability. Recently, deep learning (DL) has seen extensive application in radar and communication signal classification, which requires sufficient labeled training data to ensure great classification performance. However, obtaining a significant amount of labeled samples is extremely challenging in complex and ever-changing electromagnetic environments. Therefore, we propose a novel few-shot AMC method using architecture search and knowledge transfer. This method first utilizes an advanced neural architecture search algorithm,$\Lambda $-DARTS, to automatically search for the optimal network structure (i.e., Auto-MCNet) based on the auxiliary sample set. Then, the Auto-MCNet model is pretrained on the auxiliary data set to explore prior knowledge about signal classification. Finally, we transfer the knowledge to a few-shot training data set and fine-tune the Auto-MCNet model to enhance its generalization ability. The simulation results indicate that when the signal-to-noise ratio (SNR) is greater than 0 dB and the shot of each class is 3 and 10, the average accuracy of the proposed Auto-MCNet is higher than 81% and 90%, respectively. Moreover, compared to advanced competitors, Auto-MCNet achieves higher classification performance with lower model complexity.

This letter establishes a novel transmission framework that amalgamates downlink (DL) training with rate-splitting multiple access, thereby being expected to enhance the spectral efficiency (SE) of a cell-free massive multiple-input multiple-output enabled Internet of Things (IoT) system. Considering a correlated Ricean fading environment coupled with imperfect channel knowledge, we derive a closed-form expression for the achievable SE and evaluate the DL SE under a variety of system configurations. Our comprehensive simulations corroborate the theoretical findings and yield critical insights pertinent to the system’s architectural design.

This article proposes a new framework of aerial reconfigurable intelligent surface (ARIS) enhancing the nonorthogonal multiple access (NOMA) system. The base station (BS) transmits superimposed signals to multiple users with different channel gains through ARIS which can flexibly change channel conditions and perform intelligent NOMA operations. It ensures that our system can perform well in providing services to multiple users simultaneously. In this system, the placement of the unmanned aerial vehicle (UAV) is jointly optimized along with the AIRS passive beam and the multiuser power allocation in order to maximize the communication sum rate. Since the joint optimization problem is nonconvex and coupled, it is hence disintegrated into three subproblems and it is solved alternately through the successive convex approximation (SCA). Moreover, semi definite programming (SDP) is used to deal with the rank one constraint of RIS reflection matrix and comparisons are made using particle swarm optimization (PSO). The numerical results show that the proposed ARIS-NOMA framework can achieve better sum rate performance than traditional NOMA with fixed RIS and OMA-ARIS.

Fault prediction is an important application in the Industrial Internet of Things (IIoT) to ensure the safety of industrial systems and factories. Currently, deep learning-based fault prediction models are more popular, and multi-factory co-operation is required to improve the accuracy and generality of fault prediction models. Federated learning can coordinate multiple clients to train models together while protecting client privacy, and thus is widely used for training fault prediction models. How to incentivise more factories to participate in model training is crucial, however, most of the existing incentive mechanisms focus on the problem of fair measurement of client contributions and ignore the problem of incentive allocation in scenarios with limited incentive budgets. In this paper, we design a self-safeguarding incentive mechanism for large scale-federated industrial maintenance based on double layer reinforcement learning, known as Dual Layer Incentive (DLI). The method enables the central server to achieve higher model training accuracy within a limited incentive budget through rational allocation of incentives, which ultimately reduces the overall cost of model training. In addition, we categorise participating clients into “diligent clients”“, inefficient clients” and “malicious clients” based on their contributions and design tailor-made incentives for each client type, which saves training costs and enhances the safety of the model training process. Finally, the proposed approach is evaluated through experiments using various datasets. The results show that the method significantly improves the accuracy and safety of industrial fault prediction model compared to other existing methods.

The Industrial Internet of Things (IIoT) is emerging as a promising technology that can accelerate the application of industrial intelligence to smart factories. Because of the sensitive nature of user data, federated learning (FL) which performs distributed machine learning while preserving data privacy, is leveraged to meet the accuracy and privacy requirements of IIoT end devices/clients. However, the unreliable communications in IIoT may result in possible single-point failures in the typical single-server FL framework, thereby negatively affecting the training efficiency. In this paper, we study on the client scheduling problem in a multi-server FL framework for the communication reliability and training efficiency improvement. Specifically, we focus on a semi-decentralized FL (SD-FL) framework, where edge servers and clients collaborate to train a shared global model through unreliable intra-cluster model aggregation and inter-cluster model consensus because of the model transmission error in client-server and server-server communication. Then, a client-server association optimization problem is formulated, with the objective of minimizing the global training loss. Resorting to the convergence analysis of SD-FL, the original problem is simplified and transformed into an integer nonlinear programming problem to guide us to design a high-efficiency client scheduling scheme. Finally, experimental results show that the proposed scheme significantly outperforms the baselines in terms of the test accuracy and training loss.

Integrated sensing and communication in 6G, particularly for air-ground surveillance using automatic dependent surveillance-broadcast (ADS-B) and multi-lateration (MLAT) systems, is gaining significant research interest. This letter investigates the problem of optimal anchor station selection for tracking aerial vehicles, and proposes a novel heuristic learning scheme termed as fishing net-like optimization (FNO). Specifically, we perform constrained random walk steps on a two-dimensional surface to optimize the initial anchor stations’ parameters. FNO also incorporates with new evaluation strategies and acceleration techniques to accelerate the convergence speed. Experimental results demonstrate that FNO can achieve better selection of the anchor stations, and the accuracy of the chosen MLAT can be improved by ten times or more with the anchors optimization.

AutoDock Vina and its derivatives have established themselves as a prevailing pipeline for virtual screening in contemporary drug discovery. Our Vina-GPU method leverages the parallel computing power of GPUs to accelerate AutoDock Vina, and Vina-GPU 2.0 further enhances the speed of AutoDock Vina and its derivatives. Given the prevalence of large virtual screens in modern drug discovery, the improvement of speed and accuracy in virtual screening has become a longstanding challenge. In this study, we propose Vina-GPU 2.1, aimed at enhancing the docking speed and precision of AutoDock Vina and its derivatives through the integration of novel algorithms to facilitate improved docking and virtual screening outcomes. Building upon the foundations laid by Vina-GPU 2.0, we introduce a novel algorithm, namely Reduced Iteration and Low Complexity BFGS (RILC-BFGS), designed to expedite the most time-consuming operation. Additionally, we implement grid cache optimization to further enhance the docking speed. Furthermore, we employ optimal strategies to individually optimize the structures of ligands, receptors, and binding pockets, thereby enhancing the docking precision. To assess the performance of Vina-GPU 2.1, we conduct extensive virtual screening experiments on three prominent targets, utilizing two fundamental compound libraries and seven docking tools. Our results demonstrate that Vina-GPU 2.1 achieves an average 4.97-fold acceleration in docking speed and an average 342% improvement in EF1% compared to Vina-GPU 2.0.

Most existing works on dual-function radar-communication (DFRC) systems mainly focus on active sensing, but ignore passive sensing. To leverage multi-static sensing capability, we explore integrated active and passive sensing (IAPS) in DFRC systems to remedy sensing performance. The multi-antenna base station (BS) is responsible for communication and active sensing by transmitting signals to user equipments while detecting a target according to echo signals. In contrast, passive sensing is performed at the receive access points (RAPs). We consider both the cases where the capacity of the backhaul links between the RAPs and BS is unlimited or limited and adopt different fusion strategies. Specifically, when the backhaul capacity is unlimited, the BS and RAPs transfer sensing signals they have received to the central controller (CC) for signal fusion. The CC processes the signals and leverages the generalized likelihood ratio test detector to determine the present of a target. However, when the backhaul capacity is limited, each RAP, as well as the BS, makes decisions independently and sends its binary inference results to the CC for result fusion via voting aggregation. Then, aiming at maximize the target detection probability under communication quality of service constraints, two power optimization algorithms are proposed. Finally, numerical simulations demonstrate that the sensing performance in case of unlimited backhaul capacity is much better than that in case of limited backhaul capacity. Moreover, it implied that the proposed IAPS scheme outperforms only-passive and only-active sensing schemes, especially in unlimited capacity case.

Rate-splitting multiple access (RSMA) has emerged as a potent paradigm shift in wireless communications, demonstrating resilience to channel state information (CSI) inaccuracies and significant rate enhancements. This work investigates RSMA’s application within the context of ultra-reliable and low-latency communication (URLLC) for the forthcoming Internet-of-Everything networks. Specifically, we integrate RSMA with a cell-free massive multiple-input multiple-output (MIMO) architecture to support URLLC demands. Considering the imperfect CSI, attributable to pilot contamination and thermal noise, we derive rigorous lower-bound expressions for the downlink achievable rates. These expressions are applicable to short-packet communication scenarios and RSMA strategy over spatially correlated Rician fading channels. Utilizing these analytical expressions, we perform an exhaustive rate performance evaluation, varying system parameters such as the numbers of pilots, access points (APs), devices, and antennas per AP, alongside different multiple access techniques. Furthermore, we address the power control coefficient design for both common and private streams, framing it as an optimization problem aimed at maximizing the weighted sum-rate and enhancing URLLC service quality. To tackle this non-convex challenge, we introduce a geometric programming-based path-following algorithm, which iteratively converges to the solution. The theoretical underpinnings and the efficacy of the proposed power optimization algorithm are corroborated through extensive simulation results.

Specific emitter identification (SEI) based on radio frequency fingerprinting (RFF) is a physical layer authentication method in the field of wireless network security. RFFs are unique features embedded in the electromagnetic waves, which come from the hard imperfections in the wireless devices. Deep learning has been applied to many SEI tasks due to its powerful feature extraction capabilities. However, the success of most methods hinges on massive and labeled samples, and few methods focus on a realistic scenario, where few samples are available and labeled. In this paper, to overcome data limitations, we propose a few-shot SEI (FS-SEI) method based on self-supervised learning and adversarial augmentation (SA2SEI). Specifically, to overcome the limitation of label dependence for auxiliary dataset, a novelty adversarial augmentation (Adv-Aug)-powered self-supervised learning is designed to pre-train a RFF extractor using unlabeled auxiliary dataset. Subsequently, to overcome the limitation of sample dependence, knowledge transfer is introduced to fine-tune the extractor and a classifier with target dataset including few samples (5-30 samples per emitter in this paper) and corresponding labels. In addition, auxiliary dataset and target dataset are come from different emitters. An open-source large-scale real-world automatic-dependent surveillance-broadcast (ADS-B) dataset and a Wi-Fi dataset are used to evaluate the proposed SA2SEI method. The simulation results show that the proposed method can extract more discriminative RFF features and obtain higher identification performance in the FS-SEI. Specifically, when there are only 5 samples per Wi-Fi device, it can achieve$83.40\%$identification accuracy, in which$38.63\%$identification accuracy improvement comes from the Adv-Aug of pre-training process. The codes are available athttps://github.com/LIUC-000/SA2SEI.

Cyber security has always been an important issue in the Internet of Everything topic. In the physical layer of the Internet, specific emitter identification (SEI) technology is widely researched as a simple and effective intrusion prevention technology. Existing SEI research only focused on radio frequency (RF) signals from a single receiver. However, in real scenes such as the Industrial Internet of Things (IIoT), vehicle-to-everything applications, and intelligent sensing systems, etc., RF signals are received from different types of sensors deployed at different locations. Therefore, this paper proposes a multisource heterogeneous SEI (MH-SEI) method and proposes a multi-source heterogeneous attention-based feature fusion network (MHAFFN) to achieve excellent identification performance. The proposed MHAFFN utilizes a multi-channel convolutional network as the RF fingerprinting (RFF) extraction module for multisource heterogeneous RF signals and equips an attention-based RFF fusion module to obtain mixed RFF for the automatic classifier. The experimental results show that the identification accuracy of MHAFFN is 99.196% in a perfect environment. Furthermore, robustness verification has proved that MHAFFN keeps advantages in noisy environments. Through fault tolerance mechanism verification experiment, it is proved that MHAFFN is able to work stably in real-world complex scenarios.

Reconfigurable intelligent surface (RIS) is envisioned as a potential technology to improve spectrum efficiency with low energy consumption. Moreover, the spectrum reuse technologies are also extensively applied in various networks, such as vehicle-to-vehicle (V2V) in transportation system, machine-to-machine (M2M) in industrial Internet of Things (IIoT) system and so on. In this paper, we investigate the performance of the general RIS-assisted device-to-device (D2D) communication. We consider the limited feedback system where the channel state information (CSI) is imperfectly known. The analytical expression of the ergodic achievable rate (EAR) for beamforming (BF) strategy and interference cancellation (IC) strategy are derived. For exploring engineering design, we investigate the tight bounds of EAR with much simpler form. Then, the EAR gain brought by RIS compared to the traditional D2D system is analyzed. Further, four specific scenarios are discussed in detail, including the weak interference case, the high SNR case, the large number of BS antennas case and the large number of reflective elements case. We derive the EAR approximations of these four cases and explore a series of insights. Numerical Results shows the perfect agreement between the analytical results and simulations.

Clustered Vehicular Federated Learning (CVFL) can be used to improve traffic safety, increase traffic efficiency, and reduce vehicle carbon emissions. Therefore, it is extremely promising in intelligent transportation systems. However, in practice, it is difficult to accurately cluster vehicular clients with mobility according to data distribution. In addition, vehicular clients may be reluctant to contribute their computation and communication resources to perform learning tasks if the CVFL server does not give them proper incentives. In this paper, we would like to address the above issues. Specifically, considering the mobility of vehicular clients, we first propose a clustering method to cluster vehicular clients into several clusters based on the cosine similarity between the model gradient of local vehicular clients and the K-means method. Then, we design a set of optimal contracts specifically for the clusters, aiming to motivate them to select the optimal number of intra-cluster iterations for model training and give the closed-form solution to the contracts under the constraints of individual rationality, incentive compatibility, and task accuracy. The proposed contract theory based incentive mechanism not only effectively motivates every cluster, but also overcomes the information asymmetry problem to maximize the utility of the CVFL server. Finally, simulation results validate the effectiveness of the proposed clustering method and the designed contract.

Reconfigurable intelligent surface (RIS) is a promising paradigm for implementing intelligent reconfigurable wireless propagation environments in the 6G era. However, most of the existing studies focus on utilizing RIS deployed on buildings to provide services to users or constructing a RIS-assisted system framework for static users, which greatly limited application in real-time changing vehicular communication environments. As a result, combining unmanned aerial vehicles (UAVs) with RIS (RIS-UAV) plays a crucial role in various wireless networks due to their high mobility. To maximize the communication rate between base station (BS) and mobile vehicle, we propose a position prediction strategy for vehicles that facilitates real-time adjustment of UAV trajectories and RIS phase shifts, enhancing communication in dynamic environments. Deep reinforcement learning (DRL) algorithm is utilized to solve the above question, which achieves a good effect on convergence in continuous action space. Simulation results demonstrate that compared with benchmark schemes, the algorithm we suggested has significant performance gains, that is to maximize the communication rate under system constraints and guarantee the reliability of the communication.

Text-to-image person re-identification (ReID) is a common subproblem in the field of person re-identification and image-text retrieval. Recent approaches generally follow the structure of a dual-stream network, extracting image and text features. There is no deep interaction between images and text in this approach, making it difficult for the network to learn a highly semantic feature representation. In addition, for both image data and text data, the feature extraction process is modeled in a regular way, such as using Transformer to extract sequence embeddings. However, this type of modeling disregards the inherent relationships among multimodal input embeddings. A more flexible approach to mining multimodal data, which uniformly treats the data as graphs, is proposed. In this way, the extraction and interaction of multimodal information are accomplished by means of messages passing between graph nodes. First, a unified multimodal feature extraction and fusion network is proposed based on the graph convolutional network, which enables the progression of multimodal information from ‘local’ to ‘global’. Second, an asymmetric multilevel alignment module, which focuses on more accurate ‘local’ information from a ‘global’ perspective, is proposed to progressively divide the multimodal information at each level. Last, a cross-modal representation matching strategy based on similarity distribution and mutual information is proposed to achieve cross-modal alignment. The proposed algorithm in this paper is simple and efficient, and the testing results on three public datasets (CUHK-PEDES, ICFG-PEDES and RSTPReID) show that it can achieve SOTA-level performance.

This paper investigates the achievable rate and spectral efficiency (SE) of an uplink cell-free massive multiple-input multiple-output Internet-of-Things (mMIMO-IoT) network over Ricean fading channels, where both access points and user equipments (UEs) are equipped with multiple antennas. We derive tight closed-form expressions for the lower-bound achievable rate and SE under maximum ratio combining and imperfect channel state information (CSI). Moreover, we propose a target-signal-to-interference-plus-noise-ratio-tracking opportunistic power control (TOPC) algorithm with gradual soft UE removal to mitigate the effects of unsupported UEs. The proposed TOPC algorithm is fully distributed, as each UE updates its transmit power based on local CSI. Numerical results show that adding more antennas at the UEs can enhance the achievable rate, but may degrade the achievable SE due to the increased pilot overhead. Moreover, the Ricean fading channels offer much higher achievable rate and SE than the Rayleigh fading channels, and our TOPC algorithm exhibits satisfactory performance in various aspects.

Specific emitter identification (SEI) uses advanced techniques to identify radio equipment by analyzing unique characteristics in radio frequency signals. Recently, deep learning (DL) has been considered a promising tools for designing various intelligent SEI methods. This is primarily due to its ability to fully exploit hidden data features and make autonomous classification decisions, leading to effective performance. The existing DL-SEI methods are based on the availability of extensive labeled datasets, however, collecting and annotating such data is challenging and time-consuming in real-world scenarios. Furthermore, these datasets often contain both device-specific and irrelevant features, which limits the adaptability of models to fixed channels. To overcome these challenges, we propose a robust variable-channel SEI (VC-SEI) method. This method uses semantic consistency-powered semi-supervised domain adaptation (SSDA). We introduce domain adversarial training to ensure global semantic consistency (GSC), allowing the extraction of channel-irrelevant features. Additionally, we design two loss functions to maintain local semantic consistency (LSC) for extracting category-relevant features. This approach enables effective domain adaptation. Our SSDA-based VC-SEI method has been rigorously evaluated using the ORACLE RF fingerprinting datasets from 16 USRP X310 radios. When only 1% of training samples in the target domain are labeled, our method achieves 84.20% identification accuracy in the target domain and 92.00% identification accuracy in the source domain. These results surpass those of current state-of-the-art methods. Simulation results confirm the robust identification performance of our proposed VC-SEI method in both source and target domains across all scenarios. Our code can be downloaded fromhttps://github.com/frownean/VC-SEI-based-SSDA.

Contactless Wi-Fi sensing, using channel state information (CSI) fingerprints, plays a pivotal role in communication, smart healthcare, and industrial automation. Deep learning has revolutionized the efficiency of non-contact sensing technology. Owing to its robust feature extraction capabilities and the interconnectedness of diverse sensing tasks, methods that address multiple tasks at once, like joint activity recognition and indoor localization (JARIL), have gained prominence. The primary goal of JARIL is to improve performance while reducing computational demands. Nevertheless, there remains substantial potential for enhancing its effectiveness through additional refinement and optimization measures. To address this, we introduce a regularized multi-label learning (RML) framework specifically designed for JARIL. This framework combines a parameter-efficient backbone network based on multi-scale separable convolution with residual connections, and a regularization training strategy. The latter strategy boosts performance by linearly combining two distinct CSI samples with their labels, creating new training instances in the training process. Simulation results show that the proposed method boasts a recognition accuracy of 91.73% and a localization precision of 99.64%. This marks an improvement of 4.32% and 3.60% respectively, in comparison to the prior ResNet1D+-based JARIL method. The codes can be downloaded fromhttps://github.com/BeechburgPieStar/JARIL.

Rate splitting multiple access (RSMA) provides a flexible transmission framework that can be applied in mobile edge computing (MEC) systems. However, the research work on RSMA-assisted MEC systems is still at the infancy and many design issues remain unsolved, such as the MEC server and channel allocation problem in general multi-server and multi-channel scenarios as well as the user fairness issues. In this regard, we study an RSMA-assisted MEC system with multiple MEC servers, channels and devices, and consider the fairness among devices. A max-min fairness computation offloading problem to maximize the minimum computation offloading rate is investigated. Since the problem is difficult to solve optimally, we develop an efficient algorithm to obtain a suboptimal solution. Particularly, the time allocation and the computing frequency allocation are derived as closed-form functions of the transmit power allocation and the successive interference cancellation (SIC) decoding order, while the transmit power allocation and the SIC decoding order are jointly optimized via the alternating optimization method, the bisection search method and the successive convex approximation method. For the channel and MEC server allocation problem, we transform it into a hypergraph matching problem and solve it by matching theory. Simulation results demonstrate that the proposed RSMA-assisted MEC system outperforms current MEC systems under various system setups.

In the realm of industrial Internet of Things, the imperative for ultra-reliable and low-latency communication (URLLC) is underscored by the demand for up to 99.999% reliability and sub-microsecond latency. In this paper, we delve into a downlink cell-free massive multiple-input multiple-output (MIMO) system designed to facilitate URLLC, operating over spatially correlated Rician fading channels with inherent phase shifts. Utilizing short-packet transmission and accounting for imperfect channel state information, we derive stringent closed-form expressions for the lower-bound achievable rates, considering both phase-aware and phase-unaware minimum mean squared error estimations. Employing these expressions, we execute an in-depth performance analysis across diverse system configurations, including the availability of phase shifts and the counts of access points (APs), connected devices, antennas per AP, and pilot sequences. Additionally, we propose a path-following power control algorithm that employs geometric programming to enhance the downlink sum-rate. This algorithm is meticulously designed to meet the stringent latency and reliability requirements of URLLC for all connected devices. The theoretical underpinnings and the efficacy of the proposed power control algorithm are substantiated through extensive simulations.

In this paper, we investigate the secure transmission in the downlink of a cell-free massive multiple-input multiple-output (mMIMO) system that relies on rate-splitting multiple access (RSMA). We specifically evaluate the impact of hardware impairments (HWIs) originating from non-ideal access points (APs), user equipments (UEs), and Eavesdroppers (Eves) on the system’s secrecy performance. The investigation encompasses scenarios with both colluding and non-colluding Eves orchestrating pilot spoofing attacks against a designated UE, subsequently intercepting transmissions from both common and private streams. By taking into account a spatially correlated Ricean fading channel model and imperfect channel state information, we derive closed-form expressions for both legitimate and secrecy rates. The secrecy performance is scrutinized across different system configurations, including varying HWI levels, power splitting ratios, AP/Eve transmission powers, spatial correlations, line-of-sight components, and the presence of colluding versus non-colluding Eves. To enhance the secrecy rate for the compromised UE, we propose a secure power control strategy for adjusting the downlink transmission powers of the common and private streams. A sequential convex approximation-based algorithm is introduced to iteratively address this non-convex problem. Through comprehensive simulations, we validate our theoretical propositions and extract pivotal insights for system design.

Reconfigurable intelligent surface (RIS) is considered as a crucial technology for changing the propagation environment to enhance signal reception, extend coverage, and improve link quality. It can flexibly serve the massive Internet of Things (IoT) devices with low energy consumption. This paper focuses on a multi-RIS assisted communication system, where the channels are assumed to follow Weibull fading. The closed-form expressions of outage probability (OP), ergodic achievable rate (EAR) as well as average symbol error probability (SEP) are provided, respectively. It is worthy noting that all the analytical results are suitable for arbitrary system parameters such as the number of elements on RIS, topological structure, transmit power, etc. Simulation results show that the multi-RIS assistance has a significant improvement on the system performance.

Federated learning (FL) emerges as a privacy-preserving paradigm to effectively integrate edge computing for the implementation of deep learning-based vehicular applications. Nevertheless, the incentive mechanism for the vehicles to participate with varied learning tasks, has not been well explored yet. In this paper, for the training control among vehicles, a multi-task FL framework is investigated, where multiple edge servers collectively coordinate numerous vehicular models from different learning tasks. Aiming at motivating the vehicles to actively participate in training while improving the system utility of multiple learning tasks, a problem of multi-task contract design is formulated, and an iterative reward allocation algorithm is proposed based on the property of the convergence performance and the contract constraints. Extensive experiments validate that the proposed algorithm can achieve the balance between the system utility and the cluster utility, with higher test accuracy.

To reduce the outage of the connection between unmanned aerial vehicles (UAVs) and cellular networks in complex real-time channel state, and reduce the energy consumption of UAV during flight mission, an online trajectory optimization scheme of UAV based on outage probability knowledge map reconstruction is proposed. The outage probability knowledge map is a database that simulates the connection between UAV and the cellular network during real hovers. The UAV first samples sparsely from the target area and calculates the outage probability of the sampling point, and then uses the Kriging algorithm to reconstruct the outage probability knowledge map. Based on the reconstructed outage probability knowledge map, with the goal of minimizing the energy consumption of UAV task execution, the UAV trajectory optimization problem is established, and a trajectory optimization algorithm based on deep reinforcement learning (DRL) is proposed to solve it. Numerical results show that the proposed online trajectory optimization scheme based on outage probability knowledge map can obtain great returns in terms of maintaining connectivity, reducing task completion time and energy consumption.

Bistatic backscattering communication (BackCom) allows passive tags to send signals over long distances, but requires proximity to the carrier emitter (CE). Otherwise, the system would suffer from severe path loss, which need to be compensated by a high transmitting power of the CE. This paper presents an inventive BackCom system that makes use of the Simultaneous Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS), which could improve the deployment flexibility of BackCom devices at both sides of STAR-RIS simultaneously. With the ensurance of the BackCom performance, we focus on minimizing the CE transmitting power through optimizing STAR-RIS phase shift and power splitting coefficient of tags. Numerical results reveal that the CE transmitting power in bistatic BackCom systems can be greatly saved with the assistance of STAR-RIS.

Abstract Energy efficiency (EE) is an important indicator in ultra‐reliable and low‐latency communication (URLLC). Power allocation is considered as an effective method to achieve high EE in URLLC. However, since the EE optimization problem is non‐convex, it is difficult to obtain the analytical solution efficiently. Moreover, to ensure reliable and low‐latency communication within a finite blocklength, the Shannon formula becomes impractical for URLLC. Therefore, finite blocklength coding theory is used to meet the requirements of URLLC. In this paper, the EE problem of URLLC is formulated and the power allocation function is parameterized to be optimized through a deep neural network (DNN). The DNN is trained through the primal‐dual iterative algorithm offline in the unsupervised manner, and can be deployed online to achieve real time power allocation results. The numerical results show the effectiveness of the proposed method.

Integrating reconfigurable intelligent surface (RIS) into cell-free massive multiple-input multiple-output (MIMO) is a promising approach to enhance the coverage quality, spectral efficiency (SE), and energy efficiency. In this paper, an RIS-assisted cell-free massive MIMO downlink system suffering from the transceiver hardware impairments (T-HWIs) is investigated. To improve the accuracy of the direct estimation (DE) scheme, a modified ON/OFF estimation (MOE) with moderate pilot overhead is proposed. Relying on the knowledge of imperfect channel state information, we derive closed-form expressions of the lower-bound achievable SE with T-HWIs under both DE and MOE schemes. The closed-form results facilitate the investigation of how RIS improves the downlink SE under various system settings and allow us to explore the trade-off strategies between using more hardware-impaired APs and low-cost RISs in terms of the downlink SE and power consumption. Numerical results validate the theoretical analysis and show that the proposed MOE scheme outperforms the DE scheme in terms of the downlink SE. Moreover, the benefits of introducing RIS into hardware-impaired cell-free massive MIMO systems are also illustrated.

This paper investigates the uplink performance of a general cell-free massive multiple-input multiple-output (CF-mMIMO) system, in which all access points (APs) and user equipments (UEs) suffer from hardware impairments (HWIs). Besides, there are several reconfigurable intelligent surfaces (RISs) that aim to improve the coverage quality, spectral efficiency (SE), and energy efficiency (EE). Relying on the knowledge of only imperfect channel state information, a tight closed-form expression for the lower-bound achievable SE is derived. Based on this expression, we quantitatively investigate the impacts of different system parameters on uplink SE and EE, and conduct a tradeoff analysis between using more APs versus using more RISs with respect to the above performance metrics. In addition, we also design a max-min SE algorithm that takes into account both large-scale fading decoding weights and power control coefficients to guarantee UE fairness. Specifically, the proposed algorithm admits a closed-form solution and is therefore memory-efficient and time-saving. Both the theoretical analysis and the effectiveness of the proposed max-min SE algorithm are verified via extensive simulations.

Unsupervised dimension reduction and clustering are frequently used as two separate steps to conduct clustering tasks in subspace. However, the two-step clustering methods may not necessarily reflect the cluster structure in the subspace. In addition, the existing subspace clustering methods do not consider the relationship between the low-dimensional representation and local structure in the input space. To address the above issues, we propose a robust discriminant subspace (RDS) clustering model with adaptive local structure embedding. Specifically, unlike the existing methods which incorporate dimension reduction and clustering via regularizer, thereby introducing extra parameters, RDS first integrates them into a unified matrix factorization (MF) model through theoretical proof. Furthermore, a similarity graph is constructed to learn the local structure. A constraint is imposed on the graph to guarantee that it has the same connected components with low-dimensional representation. In this spirit, the similarity graph serves as a tradeoff that adaptively balances the learning process between the low-dimensional space and the original space. Finally, RDS adopts the$\ell _{2,1}$-norm to measure the residual error, which enhances the robustness to noise. Using the property of the$\ell _{2,1}$-norm, RDS can be optimized efficiently without introducing more penalty terms. Experimental results on real-world benchmark datasets show that RDS can provide more interpretable clustering results and also outperform other state-of-the-art alternatives.

Mobile edge computing (MEC) is a promising paradigm to handle the mismatch between computation-intensive applications and resource-limited devices. Nevertheless, as most Internet of Things (IoT) terminals are battery-limited, the computation gain of MEC may be compromised due to insufficient battery energy for task offloading. Wireless power transfer (WPT) and full duplex (FD) communications are economical charging and transmission methods for battery-limited IoT terminals. However, when integrating wireless power transfer and FD into MEC, the incentive problem should be jointly addressed with task offloading, because the WPT facilities and their powered IoT nodes belong to different service operators. In this paper, we investigate the efficiency of WPT from the perspective of battery saving, and propose an efficient wireless powered task offloading and incentive mechanism in FD MEC-enabled cellular IoT networks. The battery saving efficiency, which addresses both the total cost of WPT and saved energy of battery, is proposed as the performance metric. By adopting this metric as the utility function of the network operator (NO), the task offloading and incentive problem are jointly formulated as a Stackelberg game. We then propose an efficient alternating direction iteration-based algorithm to solve its equilibrium efficiently. Simulation results demonstrate the benefits of our algorithm in battery saving by comparisons with utility oriented benchmarks. Moreover, it reveals the tradeoff between the utility of NO and battery saving, which verifies the positive effects of FD communications and WPT in improving the efficiency of battery saving.

Energy consumption is one crucial aspect in IoT and healthcare applications. Reconfigurable intelligent surface (RIS) is composed of man-made passive reflective elements which can configure the channel environment with lower energy consumption. In this paper, we focus on the RIS-assisted D2D networks. We obtain analytical closed-form expressions for the outage performance. Based on this, we then discuss the performance under high SNR case, as well as weak interference case. The corresponding closed-form simpler approximations are also presented. Due to the existence of interference, 0 order outage diversity is obtained. Numerical results show the agreement between Monte Carlo simulations and analytical results in various network configurations.

Federated learning (FL) framework enables user devices collaboratively train a global model based on their local datasets without privacy leak. However, the training performance of FL is degraded when the data distributions of different devices are incongruent. Fueled by this issue, we consider a clustered FL (CFL) method where the devices are divided into several clusters according to their data distributions and are trained simultaneously. Convergence analysis is conducted, which shows that the clustered model performance depends on cosine similarity, device number per cluster, and device participation probability. Then, aiming at optimizing the model training performance, a joint problem of resource allocation and device clustering is formulated, which is solved by decoupling it into two sub-problems. Specifically, a coalition formation algorithm is proposed for the device clustering sub-problem, and the sub-problem of bandwidth allocation and transmit power control is solved directly due to its convexity. Finally, simulation experiments are conducted on the MNIST dataset to validate the performance of the proposed algorithm in terms of test accuracy.

This paper studies a new framework of aerial reconfigurable intelligent surface (ARIS) assisted non-orthogonal multiple access (NOMA) for wireless communication systems. The base station transmits superimposed signals to multiple users with different channel gains through ARIS which can be deployed flexible. The placement of the unmanned aerial vehicle (UAV) and the passive beamforming of the ARIS are jointly optimized to maximize the sum rate. The non-convex problem is decomposed into two subproblems and solved alternately through the successive convex approximation (SCA). The numerical results show that our proposed NOMA-ARIS framework can achieve better sum rate performance than traditional NOMA with fixed RIS and OMA-ARIS.

The ultra-reliable and low-latency communication (URLLC) is one of the critical scenarios in future communications. Energy efficiency (EE), as an important indicator in URLLC, has attracted more and more attention especially in the fields of industrial internet and automation control, etc. At present, power allocation is considered as an effective method to achieve high EE in URLLC. However, since the EE optimization problem in URLLC is usually formulated in the form of fractions with several statistical constraints, it is difficult to obtain the real time analytical solution. Moreover, the traditional expression based on Shannon formula is no longer applicable. In this paper, we formulate the EE problem of URLLC and adopt an unsupervised learning method to parameterize the power allocation function to be optimized through a deep neural network (DNN). The DNN is trained through the primal-dual iterative algorithm offline, and can be deployed online to achieve real time power allocation results. The numerical results show the effectiveness of the proposed method.

Compared with 5G networks, 6G networks are guaranteed to provide various tailored end-to-end network services and emerging cloud-edge applications. Network slicing (NS) is regarded as the key enabler of 6G networks. Softwarization and virtualization technologies, such as software-defined networking and network function virtualization, are accelerating the way toward NS of 6G networks. The resource allocation issue in 6G NS is very crucial, worthy more research attention. In this article, we propose one efficient resource allocation algorithm, labeled asTailoredSlice-6G, so as to realize the tailored slices in 6G. When receiving one slice request, ourTailoredSlice-6Gwill identify the slice resource type in the first place. Then, ourTailoredSlice-6Gwill select its most suitable subalgorithm to do the resource allocation and slicing deployment. Each type of slice corresponds to its specific resource allocation subalgorithm, inserted in theTailoredSlice-6Galgorithm. In addition, each subalgorithm inTailoredSlice-6Gis guaranteed to run within polynomial time. Thus,TailoredSlice-6Ghaving the potential to be promoted to real networking application. To highlight the merits ofTailoredSlice-6G, we do the comprehensive simulation. Simulation results vividly reveal that ourTailoredSlice-6Goutperforms the selected heuristics that are representative in the literature.

Energy harvesting (EH)-enabled cellular Internet of Things (IoT) is a promising solution to handle the charging and accessing of massive IoT nodes. However, limited by the high-frequency band of future 5G, the radius of the small base station (SBS) is reduced, hence greatly increasing the cost of the network operators (NOs). In this article, we consider the joint cell association, cell sleeping (CS), and incentive decision problem for EH-aided cellular IoT with full-duplex (FD) self-backhauls. We formulate a Stackelberg game to investigate the coordination between the utilities of NO and energy transmitters (ETs), where both the features of FD self-backhauls and CS are introduced to reduce the expense of NO. We then propose an alternative direction algorithm to solve the equilibrium of the game efficiently, where the relationship of the formulated constraints and variables are utilized to transform the original problem into two subproblems. We propose a two-level Lagrangian relaxation to solve the first subproblem, while the other is proved to be convex and solved by an efficient iteration. Simulation results demonstrate the benefits of our algorithm in utility improvement and expense reduction. Moveover, it shows that our algorithm can obtain high efficiency by adjusting the tradeoff between the number of active SBS and transmitting power of ETs according to the network deployment.

In this article, the performance of simultaneous wireless information and power transfer (SWIPT) in downlink (DL) Internet of Things (IoT) networks relying on the cell-free massive multiple-input–multiple-output (CF-mMIMO) technique is investigated. In such a network, the access points (APs) beam the radio-frequency (RF) energy toward IoT sensors during the DL wireless power transfer phase. Tight closed-form expressions for DL harvested energy (HE) and achievable rate with conjugate beamforming (CB) and normalized CB (NCB) are, respectively, derived, which enable us to analyze the behaviors of CB and NCB schemes in terms of both HE and achievable rate. Apart from this, to guarantee sensor fairness with respect to the HE and achievable rate, a max–min power control strategy based on the accelerated projected gradient (APG) method is proposed. Specifically, the proposed APG-based power control is able to determine the optimal solution in closed form and is more memory efficient than the convex-solver-based counterpart. These analytical results as well as the effectiveness of the proposed power control policy are verified by experimental simulations.

This paper investigates the secure transmission in downlink cell-free massive multiple-input multiple-output (MIMO) systems in the presence of an active multi-antenna eavesdropper (Eve) over Rician fading channels, assuming that each access point (AP) possesses multiple antennas which are connected with low-resolution digital-to-analog converters (DACs). Closed-form expressions of the achievable secrecy rate relied on the additive quantization noise model are derived. Based on these analytical results, we quantify the impacts of key system parameters, such as the antenna array number, DAC resolution, Rician$\mathcal K$-factor, and balance factor between data and artificial noise power on secrecy enhancement. Several interesting insights are attained by assuming that Eve can or cannot perfectly remove inter-mobile-terminal interference. Moreover, we also propose a power control algorithm that maximizes the achievable secrecy rate, which can be represented as a series of second-order-cone programs for which efficient solvers exist. All the theoretical analyses and the effectiveness of the proposed algorithm are corroborated by simulation experiments.

Vehicular ad-hoc network (VANET) is an emerging aspect of the 5G vertical application. Network function virtualization (NFV) is the key enabling technology of 5G and beyond 5G (B5G) networks. In NFV-enabled vehicular and 5G networks, all underlying nodes (e.g. vehicular, edge, core) can be completely virtualized and easy to be managed and allocated. Network service providers can implement each dynamically requested virtual network service (VNS), having arbitrary topology and customized resource demands, on top of the NFV-enabled networks. However, network elements (e.g. nodes and links) may come into failures accidentally. Consequently, it will lead to the performance degradation of implemented VNSs that run on top of the failed network elements. It is vital to guarantee the survivable services even though the network elements fail accidentally. Therefore, we propose the dynamic virtual resource allocation mechanism in this paper. Firstly, we introduce the business model and formulate the dynamic virtual resource allocation in NFV-enabled networks. Secondly, we detail all modules of our proposed mechanism. Especially, the initial resource allocation and re-allocation modules of achieving the survivable network services are detailed. Finally, we execute the comprehensive simulations by comparing with the typical virtual resource allocation mechanisms. The simulation results are discussed so as to highlight the merits of the proposed mechanism.

It is an irreversible trend to build a green and sustainable vehicular network facing with the dramatic increase in urban traffic. Reducing energy consumption has been an important aspect for green transportation. Reconfigurable intelligent surface (RIS) is considered as a promising technology to enhance the communication quality with higher energy efficiency. In this paper, we focus on the RIS-assisted vehicular networks. We obtain the closed-form analytical expressions for outage probability, ergodic achievable rate and average energy efficiency. A series of insights are further explored. Based on these, we discuss the performance under high SNR case, as well as, weak interference case. And then, the approximations in simpler form expressions are provided for each case, respectively. Outage diversity order and high SNR rate slope are also investigated. In addition, we propose a power allocation algorithm to maximize the ergodic achievable sum rate guaranteeing the outage probability and average energy efficiency. Numerical results show that our analytical results agree well with the Monte Carlo simulations in various network configurations. Besides, our proposed power allocation scheme significantly enhances the ergodic achievable sum rate compared with the equal power strategy.

The edge access component of the Internet of Vehicles has a high computational rate and energy consumption. This paper proposes a distribution offloading algorithm based on deep Q-learning network (DQN) to achieve the best latency and sustainable scheduling. Firstly, the computational tasks of various vehicles are prioritized using the analytic hierarchy process (AHP) to assign different weights to the task processing rate in order to establish a relationship model. Secondly, by introducing edge computing based on DQN, the task offloading model is established by using the weighted sum of task processing rate as the optimization goal, which realizes the long-term utility of offloading strategies. The performance evaluation results show that, when compared to the Q-learning algorithm, the proposed method can reduce the average task processing delay by 17%, effectively improving the sustainable task offload efficiency.

Multipath transmission has been widely used in vehicle heterogeneous networks. The diversity of interfaces will lead to differences in the characteristics of transmission paths. Different paths also have differences in parameters such as bandwidth and delay. Out of order will result in greatly reduced multipath transmission performance. In this paper, we propose a sustainable forward-delay-based multipath transmission path scheduling method for vehicular heterogeneous networks so as to solve the multipath transmission problem. The main idea of this method is to schedule data packets through the concurrent path according to the forward delay and throughput difference estimated by the sender. We conduct the simulation in NS-3. Simulation results show that, compared with the previous algorithm, our proposed algorithm can significantly reduce the out-of-order problem of data packets at the receiver. This algorithm improves overall system throughput and network utilization. In this way, sustainable path propagation is guaranteed.

In this paper, we consider a hierarchical federated learning system and formulate a joint problem of edge aggregation interval control and time allocation to minimize the weighted sum of training loss and training latency. To quantify the learning performance, an upper bound of the average global gradient deviation, in terms of the edge aggregation interval, the time allocated for training, and the number of successfully participating devices, is derived. Then an alternative problem is formulated, which can be decoupled into two sub-problems and solved with two steps. In the first step, given the time allocation strategy, a relaxation and rounding method is proposed to optimize the edge aggregation interval. In the second step, with the results of the obtained edge aggregation interval and based on the convex optimization theory, an optimal time allocation can be evaluated. Simulation results show that the proposed scheme, compared to the benchmarks, can achieve higher learning performance with lower training latency.

Abstract This paper proposes a data‐driven method of mmWave beam selection in multi‐cell systems to achieve a near‐optimal fast beam allocation with low complexity. In particular, an online learning algorithm based on support vector machine (SVM) equipped with the radial basis function kernel, namely SVM‐based online beam selection (SBOS) algorithm is proposed. The proposed algorithm starts with an adaptive beam selection process for certain traffic pattern that uses an SVM learning model to adaptively refine the beam selection strategy. Specifically, SVM‐based model labels the feedback (the average information rate) from the cellular system, then learns from samples, and makes the scheme space smaller by maximising samples' minimum distances to all labelled samples in the sample space constrained by newly learned boundaries. Then, according to the aggregated data about the traffic patterns and the performance of corresponding beam selection strategy, SBOS algorithm exploits beam selection schemes recorded in the database or explores new schemes for unknown situations, respectively, and how to tune the hyperparameters for the SBOS algorithm is discussed. Furthermore, the extensive simulation results show that the proposed algorithm achieves a better performance versus upper confidence bound and Random methods.

Abstract Ultra‐dense networking is considered an effective solution to achieve high capacity in 5G networks. However, the densely distributed base stations (BSs) in ultra‐dense networks (UDNs) make the inter‐cell interference much more serious than that in traditional cellular networks. Therefore, it is important to mitigate inter‐cell interference in the UDNs to improve network performance. To tackle this problem, we propose a novel virtual resource mapping algorithm that includes a resource reservation (RR) algorithm and a real‐time resource embedding (RE) algorithm. Specifically, according to the number of services predicted by a dynamic service model, the RR algorithm is proposed to determine the sets of multiplexing BSs in the next time cycle and reserve channel resource required by each BS. Then, to further reduce inter‐cell interference, the real‐time RE algorithm is proposed to allocate the channel resource in real time. Finally, simulation results show that the proposed algorithm has better performance in terms of signal‐to‐interference‐plus‐noise ratio and acceptance ratio, compared to the existing algorithms, such as the frequency reuse channel allocation algorithm and inter‐cell interference coordination algorithm.

Millimeter-wave (mmWave) bands are expected to be an important choice for future vehicular communication to support Gbps links for reliable data transfer in high-rate applications. The recent online learning technologies addressed the problem of fast beam tracking by exploiting user location information and mining received data in mmWave vehicular systems to adapt to the vehicle's environmental situation. However, the fairness and efficiency over mmWave beams are difficult to maintain on the move, especially for high-density traffic, since the number of available beams is quite limited by hardware and cost for current antenna arrays. Fortunately, the social structure of preferences between the neighboring smart cars and their passengers can be leveraged to improve the beam coverage efficiency by performing the broadcast transmission via a single beam. In this article, we propose a double-layer online learning algorithm, namely, context- and social-aware machine learning (CSML), that is based on the context and social preference information of vehicles and passengers, to realize fast beam access with broadcast coverage in mmWave communication systems. Based on the multiarmed bandit model, CSML embodies the selection of appropriate beams in the first layer and steers the broadcast angle along these beams in the second layer by aggregating the received data. Furthermore, CSML needs to adjust the timing of exploration and exploitation based on the social information, i.e., the probability of vehicles meeting with each other that have the same preference. Finally, we perform an extensive evaluation using realistic traffic patterns and show that CSML increases the efficiency of mmWave base stations by using social data and can achieve near-optimal system performance.

SUMMARY With the rapid development of intelligent transportation, vehicle terminals generate a large number of data messages that need to be processed in real time, and the required computing and storage resources far exceed the load capacity of vehicle terminals. Mobile edge computing enables data resources to be processed near device terminals, and provides low‐latency and high‐reliability computing services to meet the power and service quality requirements of terminal devices. Therefore, in order to achieve better data resource management, this paper introduces mobile edge computing technology, and mainly researches secure message transmission optimization algorithms based on mobile edge computing. Firstly, we prioritize secure messages through the analytic hierarchy process. This can guarantee that the most urgent messages get the highest transmission level. Secondly, we establish an optimal task offloading model of delay and energy loss by assigning different weight factors to delay and energy loss. The Lagrangian relaxation method is used to transform the nonconvex problem into a convex problem. We use greedy algorithm to solve the main problem. Finally, the vehicle transmits secure messages through the topology of the local network within its defined communication range. Performance evaluation results show that the scheme not only reduces the redundant transmission of messages, but also improves the performance of end‐to‐end delay and message deliver success ratio of secure messages.