The proliferation of data-intensive, low-latency applications has driven the adoption of multi-access edge computing (MEC) to meet the demand for high-performance computing at the network edge. However, ensuring reliable communication under non-line-of-sight (NLoS) conditions remains a significant challenge. While reconfigurable intelligent surfaces (RISs) and the more recent simultaneously transmitting and reflecting RISs (STAR-RISs) offer promising solutions, their passive nature and susceptibility to multiplicative fading limit performance gains. To address these challenges, we propose a novel active STAR-RIS-assisted MEC system that enhances signal strength and adaptability by enabling amplification and joint control over signal transmission and reflection. Our objective is to minimize the energy consumption of user devices, considering both local task computation and uplink task offloading, while maintaining task queue stability. We formulate a joint energy minimization problem with system constraints and long-term queue stability requirements. This problem is decomposed into subproblems: (i) sequential fractional programming is applied to optimize user transmit power, (ii) convex optimization is used to determine partial task offloading ratios, and (iii) a modified Lyapunov optimization combined with double deep Q-networks (DDQN) is proposed to iteratively solve the active STAR-RIS parameters (amplitude and phase shift), amplification control, and task admission at the user side. Numerical results indicate that our proposed system outperforms the conventional passive STAR-RIS-assisted system by 18.64% and the conventional passive RIS-assisted system by 30.43%, respectively.

The use of terahertz (THz) communications with massive multiple input multiple output (MIMO) systems in 6G can potentially provide high data rates and low latency communications. However, accurate channel estimation in THz frequencies presents significant challenges due to factors such as high propagation losses, sensitivity to environmental obstructions, and strong atmospheric absorption. These challenges are particularly pronounced in urban environments, where traditional channel estimation methods often fail to deliver reliable results, particularly in complex non-line-of-sight (NLoS) scenarios. This paper introduces a novel vision-based channel estimation technique that integrates causal reasoning into urban THz communication systems. The proposed method combines computer vision algorithms with variational causal dynamics (VCD) to analyze real-time images of the urban environment, allowing for a deeper understanding of the physical factors that influence THz signal propagation. By capturing the complex, dynamic interactions between physical objects (such as buildings, trees, and vehicles) and the transmitted signals, the model can predict the channel with up to twice the accuracy of conventional methods. This model improves estimation accuracy and demonstrates superior generalization performance. Hence, it can provide reliable predictions even in previously unseen urban environments. The effectiveness of the proposed method is particularly evident in NLoS conditions, where it significantly outperforms traditional methods such as by accounting for indirect signal paths, such as reflections and diffractions. Simulation results confirm that the proposed vision-based approach surpasses conventional artificial intelligence (AI)-based estimation techniques in accuracy and robustness, showing a substantial improvement across various dynamic urban scenarios. This framework provides a promising solution for enabling resilient THz communication, offering scalability and practicality for future 6G deployments in diverse urban landscapes.

The rapid evolution towards the sixth-generation (6G) networks demands advanced beamforming techniques to address challenges in dynamic, high-mobility scenarios, such as vehicular communications. Vision-based beam prediction utilizing RGB camera images emerges as a promising solution for accurate and responsive beam selection. However, reliance on visual data introduces unique vulnerabilities, particularly susceptibility to adversarial attacks, thus potentially compromising beam accuracy and overall network reliability. In this paper, we conduct the first systematic exploration of adversarial threats specifically targeting vision-based mmWave beam selection systems. Traditional white-box attacks are impractical in this context because ground-truth beam indices are inaccessible and spatial dynamics are complex. To address this, we propose a novel black-box adversarial attack strategy, termed Spatial Proxy Attack (SPA), which leverages spatial correlations between user positions and beam indices to craft effective perturbations without requiring access to model parameters or labels. To counteract these adversarial vulnerabilities, we formulate an optimization framework aimed at simultaneously enhancing beam selection accuracy under clean conditions and robustness against adversarial perturbations. We introduce a hybrid deep learning architecture integrated with a dedicated Feature Refinement Module (FRM), designed to systematically reshaping irrelevant, noisy and adversarially perturbed visual features. Evaluations using standard backbone models such as ResNet-50 and MobileNetV2 demonstrate that our proposed method significantly improves performance, achieving up to an +21.07% gain in Top-K accuracy under clean conditions and up to a +37.32% increase in Top-1 adversarial robustness compared to different baseline models.

Federated learning (FL) enables privacy-preserving model training across decentralized data. However, significant data heterogeneity, common in domains like the Internet of Things (IoT), hinders generalization. Federated Domain Generalization (FDG) extends the FL paradigm by aiming to train models that generalize effectively to unseen domains, without requiring access to data from those domains during training. Current FDG methods primarily use ResNet backbones pre-trained on ImageNet-1K, limiting adaptability due to architectural constraints and limited pre-training diversity. This reliance has created a gap in leveraging advanced architectures and diverse pre-training datasets to address these challenges. To bridge this gap, we present the first comprehensive investigation into the efficacy of advanced pre-trained architectures such as Vision Transformers, ConvNeXt, and Swin Transformers, in enhancing FDG performance. Unlike ResNet, these architectures capture global context and long-range dependencies, making them well-suited for FDG. Beyond architectural evaluation, we systematically assess the impact of diverse pre-training datasets and compare self-supervised and supervised strategies. Our analysis rigorously investigates the influence of architectural depth, parameter efficiency, and the interplay between diverse model families and dataset characteristics on FDG performance. We find that advanced architectures pre-trained on large datasets significantly outperform ResNet models. Specifically, ConvNeXt architectures outperform all other candidates. We find self-supervised methods using masked image patch reconstruction via discrete token prediction outperform their supervised counterparts. We observe that certain advanced model variants with fewer parameters outperform larger ResNet models. This underscores the need for advanced architectures and scalable pretraining to enable efficient and generalizable FDG.

In this paper, cyber-attack prevention for the prosumer-based electric vehicle (EV) charging stations (EVCSs) is investigated, which covers two aspects: 1) cyber-attack detection on prosumers’ network traffic (NT) data, and 2) cyber-attack intervention. To establish an effective prevention mechanism, several challenges need to be tackled, for instance, the NT data per prosumer may be non-independent and identically distributed (non-IID), and the boundary between benign and malicious traffic becomes blurred. To this end, we propose an edge-assisted federated prototype knowledge distillation (E-FPKD) approach, where each client is deployed on a dedicated local edge server (DLES) and can report its availability for joining the federated learning (FL) process. Prior to the E-FPKD approach, to enhance accuracy, the Pearson Correlation Coefficient is adopted for feature selection. Regarding the proposed E-FPKD approach, we integrate the knowledge distillation and prototype aggregation technique into FL to deal with the non-IID challenge. To address the boundary issue, instead of directly calculating the distance between benign and malicious traffic, we consider maximizing the overall detection correctness of all prosumers (ODC), which can mitigate the computational cost compared with the former way. After detection, a rule-based method will be triggered at each DLES for cyber-attack intervention. Experimental analysis demonstrates that the proposed E-FPKD can achieve the largest ODC on NSL-KDD, UNSW-NB15, and IoTID20 datasets in both binary and multi-class classification, compared with baselines. For instance, the ODC for IoTID20 obtained via the proposed method is separately 0.3782% and 4.4471% greater than FedProto and FedAU in multi-class classification.

The sixth-generation (6G) non-terrestrial networks (NTNs) are crucial for real-time monitoring in critical applications like disaster relief. However, limited bandwidth, latency, rain attenuation, long propagation delays, and co-channel interference pose challenges to efficient satellite communication. Therefore, semantic communication (SC) has emerged as a promising solution to improve transmission efficiency and address these issues. In this paper, we explore the potential of SC as a bandwidth-efficient, latency-minimizing strategy specifically suited to 6G satellite communications. The existing SC methods have demonstrated efficacy in direct satellite-terrestrial transmissions; however, they still encounter certain limitations. Specifically, some ground users (GUs) experience poor signal-to-noise ratios (SNR), making direct satellite communication challenging. To address these issues, we propose a novel framework that optimizes gateway hop-relay selection for GUs with low SNR and integrates gateway-based denoising mechanisms to ensure high-quality-of-service (QoS) in satellite-based SC networks. This approach directly mitigates distortion, leading to significant improvements in satellite service performance by delivering customized services tailored to the unique signal conditions of each GU. Our findings represent a critical advancement in reliable and efficient data transmission from the Earth observation satellites, thereby enabling fast and effective responses to urgent events. Simulation results demonstrate that our proposed strategy significantly enhances overall network performance, outperforming conventional methods by offering tailored communication services based on specific GU conditions.

Federated learning (FL) makes it possible to advance towards edge intelligence by enabling collaborative and privacy-preserving model training across distributed edge devices. One of the main challenges in FL is non-IID (not Independent and Identically Distributed) nature of data distribution across edge devices, which results in inconsistent update directions of local and global models, thus hindering model convergence. Moreover, recent studies have shown that FL models can significantly degrade performance under adversarial attacks, which further poses challenges for deployment at edge sides. In this work, we attempt to improve the robustness of FL model under adversarial attacks in non-IID settings by sharing knowledge between a central server and edge devices via knowledge distillation. Specifically, we propose a new knowledge distillation-based federated adversarial training (FAT) framework, termed FedAdv (Federated Adversarial), which involves an edge server collecting global prototypes by aggregating local prototypes obtained from participating devices after adversarial training (AT). These global prototypes are subsequently distributed to the edge devices for regularization. This regularization mechanism aims to encourage each device to align its local representation with the corresponding global prototype. By doing so, it helps prevent significant deviations of local model updates from the global model. Experimental results on MNIST and Fashion-MNIST show that our strategy yields comparable or superior performance gains in both natural and robust accuracy compared to several baselines.

The future cellular networks, known as Next Generation (NextG), are anticipated to employ infrastructure based on cloud computing, with programmable, virtualized, and disaggregated designs. The separation of control functions from physical infrastructure will be implemented, and the utilization of standardized interfaces will facilitate the establishment of tailored closed-control loops. The O-RAN (Open Radio Access Network) paradigm aims to resolve the issue of limited control over the RAN by proposing an open design framework that enables data-driven and intelligent optimization at the individual user level. The growing ubiquity of O-RAN networks has underscored the significance of network traffic categorization in effectively managing O-RAN networks and preserving cybersecurity. This article analyzes the O-RAN alliance’s disaggregated network architecture, focusing on its significant contribution to NextG networks. This paper proposes a novel approach to examine and assess traffic patterns inside the O-RAN architecture. The ongoing acquisition of knowledge regarding encrypted traffic is of utmost importance in light of the perpetual advancements in applications and the advent of encryption technologies. The ability to dynamically adjust in traffic analysis is crucial for effectively addressing the evolving network environment, specifically inside the O-RAN architecture. To address this, we propose a new method named Incremental O-RAN Traffic Categorization (IORTC), specially designed to categorize encrypted data within the O-RAN framework. The IORTC system manages the continuous collection of knowledge from encrypted traffic in the O-RAN framework. It is designed to adapt to the evolution of various encrypted traffic categories while retaining information about earlier encrypted traffic. Based on the experimental results, our method demonstrates a remarkable ability to assimilate new traffic patterns while managing the retention of previously acquired knowledge, and it performed well in all evaluation criteria with an average accuracy of 98%.

The semantic communication system has become one of the promising communication technologies to support high data-intensive artificial intelligence (AI) applications and services such as meta-verse, 3D maps, and so on for achieving low communication overhead. Unlike traditional communication system, accurate channel estimation is a vital issue in semantic wireless communication since a semantic transmitter is required to send the core meaning of a message rather than an entire bit streams for the receiver. Thus, designing a semantic communication framework is challenging due to the dependencies of the semantic encoder and decoder over the orthogonal frequency division multiplexing (OFDM) setting. Therefore, first, this work designs a holistic semantic communication system model that is composed of a semantic encoder, a 3GPP-defined cluster delay line (CDL) wireless channel model, and a semantic decoder for AI services. Second, this paper proposes a semantic communication framework for AI services, 1) a masked autoencoder (MAE)-based channel estimation, and 2) a hierarchical reinforcement learning (HRL)-based pilot allocation method. Third, the proposed semantic communication framework is trained in an end-to-end manner, combined with OFDM layers, considering the image reconstruction and the performance of vision AI applications. Finally, the proposed MAE-based channel estimation and HRL-based pilot allocation RL agent are integrated into the semantic communication framework. Finally, Experimental results show that the proposed semantic framework demonstrates up to a 21.25% performance improvement in image segmentation tasks. Furthermore, the proposed channel estimator and pilot allocator also show higher channel estimation accuracy compared to existing channel estimators and pilot allocation methods.

This article introduces a novelattentive drivingframework in intelligent transportation systems (ITS) to investigate the influence of cognitive behavior on distracting driving activities that lead to inattention while driving. Therefore, this work proposes a holistic computational and communication framework that can monitor on-compartment real-time multimodal sensory observation such as physiological, camera, and environmental inputs while capable of distraction detection and emotion recognition for driver's mood stabilization. In particular, this work develops a capsule network for distraction detection, a 1-D convolutional neural network for emotion recognition, an a priori algorithm for sequential context fusion, and a Bayesian network for recommending auditory stimulus content for driver mood stabilization and audio-visual safety messages for road safety. Further, an asynchronous client control scheme has developed to overcome the challenges of multitime scale sensory observations and communicate among the multimodel sensory hubs. Finally, a prototype is developed and tested in a simulation environment. The quantitative analysis results show that the proposed framework can successfully detect around 89% and 87% of distractive activities and the affective state of a driver, respectively. Finally, based on experimental results, the proposed system demonstrates the capability to sustain a driver's attention for approximately 97% of the time, with a confidence level of 95%.

Explainable artificial intelligence (XAI) twin systems will be a fundamental enabler of zero-touch network and service management (ZSM) for sixth-generation (6G) wireless networks. Thus, a reliable XAI twin system becomes essential to discretizing the physical behavior of the Internet of Everything (IoE) and identifying the reasons behind that behavior for enabling ZSM. To address the challenges of extensible, modular, and stateless management functions in ZSM, a novel neuro-symbolic XAI twin framework is proposed that to enable trustworthy ZSM for a wireless IoE. The proposed neuro-symbolic XAI twin framework consists of two learning systems: 1) implicit learner that acts as an unconscious learner in physical space and 2) explicit leaner that can exploit symbolic reasoning based on implicit learner decisions and prior evidence. The physical space of the XAI twin executes a neural-network-driven multivariate regression to capture the time-dependent wireless IoE environment while determining unconscious decisions of IoE service aggregation, such as uplink, downlink, and service provisioning. Subsequently, the virtual space of the XAI twin constructs a directed acyclic graph (DAG)-based Bayesian network that can infer a symbolic reasoning score over unconscious decisions through a first-order probabilistic language model. Furthermore, a Bayesian multiarm bandit-based learning problem is proposed for reducing the gap between the expected explained score and the current obtained score of the proposed neuro-symbolic XAI twin. Experimental results show that the proposed neuro-symbolic XAI twin can achieve around 96.26% accuracy while guaranteeing from 18% to 44% more trust score in terms of reasoning and closed-loop automation.

Accurate channel estimation is an essential factor in determining the efficiency of a wireless communication system. Moreover, in Reconfigurable Intelligent Surfaces(RIS)-Assisted wireless networks using millimeter wave (mmWave), it is crucial to optimize each RIS element's phase shift. Therefore, in this paper, we propose a channel estimation method in TDD-based wireless communication system using auto encoder in RIS-Assisted wireless networks. The trade-off relationship between channel estimation accuracy and the number of pilot signals is optimized when performing channel estimation. Through denoising autoencoder and Average Percentage of Zeros(APoZ), we find the optimal pilot pattern considering not only the number of pilots but also the location. As a result of the experiment, the proposed method has little difference in performance or outperforms the full neural network without pruning.

In this article, the design of a rational decision support system (RDSS) for a connected and autonomous vehicle charging infrastructure (CAV-CI) is studied. In the considered CAV-CI, the distribution system operator (DSO) deploys electric vehicle supply equipment (EVSE) to provide an electrical vehicle (EV) charging facility for human-driven connected vehicles (CVs) and AVs. The charging request by the human-driven EV becomes irrational when it demands more energy and charging period than its actual need. Therefore, the scheduling policy of each EVSE must be adaptively accumulated the irrational charging request to satisfy the charging demand of both CVs and autonomous vehicles (AVs). To tackle this, we formulate an RDSS problem for the DSO, where the objective is to maximize the charging capacity utilization by satisfying the laxity risk of the DSO. Thus, we devise a rational reward maximization problem to adapt the irrational behavior by CVs in a data-informed manner. We propose a novel risk adversarial multiagent learning system (RAMALS) for CAV-CI to solve the formulated RDSS problem. In RAMALS, the DSO acts as a centralized risk adversarial agent (RAA) for informing the laxity risk to each EVSE. Subsequently, each EVSE plays the role of a self-learner agent to adaptively schedule its own EV sessions by coping advice from RAA. The experiment results show that the proposed RAMALS affords around 46.6% improvement in charging rate, about 28.6% improvement in the EVSE’s active charging time, and at least 33.3% more energy utilization, as compared to a currently deployed ACN EVSE system, and other baselines.

Recently, unmanned aerial vehicles (UAVs)-assisted multi-access edge computing (MEC) systems emerged as a promising solution for providing computation services to mobile users outside of terrestrial infrastructure coverage. As each UAV operates independently, however, it is challenging to meet the computation demands of the mobile users due to the limited computing capacity at the UAV’s MEC server as well as the UAV’s energy constraint. Therefore, collaboration among UAVs is needed. In this article, a collaborative multi-UAV-assisted MEC system integrated with an MEC-enabled terrestrial base station (BS) is proposed. Then, the problem of minimizing the total latency experienced by the mobile users in the proposed system is studied by optimizing the offloading decision as well as the allocation of communication and computing resources while satisfying the energy constraints of both mobile users and UAVs. The proposed problem is shown to be a nonconvex, mixed-integer nonlinear programming (MINLP) problem that is intractable. Therefore, the formulated problem is decomposed into three subproblems: 1) users tasks offloading decision problem; 2) communication resource allocation problem; and 3) UAV-assisted MEC decision problem. Then, the Lagrangian relaxation and alternating direction method of multipliers (ADMMs) methods are applied to solve the decomposed problems, alternatively. Simulation results show that the proposed approach reduces the average latency by up to 40.7% and 4.3% compared to the greedy and exhaustive search methods.

The network capacity is fastened by utilizing unmanned aerial vehicles (UAVs) and mobile users can get feasible services independent of the infrastructure coverage. Furthermore, with the help of network virtualization technology, mobile network operators (MNOs) can lease their cellular network infrastructures and wireless network resources to the service providers (SPs) who are providing specific services to their mobile users. Wireless resource leasing among SPs, on the other hand, is problematic because each aims to maximize its own profit whilst assuring the QoS requirement of their users. Thus, in this paper, we propose a wireless resource sharing problem in the UAVs-assisted virtualized wireless networks with the goal of maximizing the total profit of SPs whilst guaranteeing the QoS requirement of each mobile user and satisfying the resource constraint of the UAVs. Then, we deploy the Lagrangian relaxation-based solution approach in order to address our proposed problem. Finally, we provide detailed numerical results to show the effectiveness of our proposed algorithm.

Recently, we have witnessed an increasing demand in augmented reality (AR)-based fifth-generation (5G) and beyond applications, such as smart gaming, smart navigation, smart military wearable, and smart industries. These AR-based applications require on-demand computational and caching resources with low latency that can be provided via multiaccess edge computing (MEC) server. However, due to the massive growth of AR-enabled devices, the MEC server resources might be insufficient. To overcome this challenge, we can utilize the computational and caching resources of user equipment (UE) to serve the other UEs in its close vicinity. Successfully enabling such interaction among devices requires an attractive incentive mechanism. Therefore, we propose a contract theory-based incentive mechanism for enabling on-device caching for AR-based applications. In our approach, the MEC offers a reward to the UE for providing its resources (i.e., storage capacity, power, etc.). Furthermore, under the information asymmetry problem, we derive an optimal mechanism via the contract theory for enabling on-device caching subject to the individual rationality and incentive-compatible constraints. Finally, we perform numerical evaluations to validate the effectiveness of our proposed scheme.

Unmanned aerial vehicles (UAVs) can provide an effective solution for improving the coverage, capacity, and the overall performance of terrestrial wireless cellular networks. In particular, UAV-assisted cellular networks can meet the stringent performance requirements of the fifth generation new radio (5G NR) applications. In this article, the problem of energy-efficient resource allocation in UAV-assisted cellular networks is studied under the reliability and latency constraints of 5G NR applications. The framework of ruin theory is employed to allow solar-powered UAVs to capture the dynamics of harvested and consumed energies. First, the surplus power of every UAV is modeled, and then it is used to compute the probability of ruin of the UAVs. The probability of ruin denotes the vulnerability of draining out the power of a UAV. Next, the probability of ruin is used for efficient user association with each UAV. Then, power allocation for 5G NR applications is performed to maximize the achievable network rate using the water-filling approach. Simulation results demonstrate that the proposed ruin-based scheme can enhance the flight duration up to 61% and the number of served users in a UAV flight by up to 58%, compared to a baseline SINR-based scheme.

Without steering wheel and driver's seat, the self-driving cars will have new interior outlook and spaces that can be used for enhanced infotainment services. For traveling people, self-driving cars will be new places for engaging in infotainment services. Therefore, self-driving cars should determine themselves the infotainment contents that are likely to entertain their passengers. However, the choice of infotainment contents depends on passengers' features such as age, emotion, and gender. Also, retrieving infotainment contents at data center can hinder infotainment services due to high end-to-end delay. To address these challenges, we propose infotainment caching in self-driving cars, where caching decisions are based on passengers' features obtained using deep learning. First, we proposed deep learning models to predict the contents need to be cached in self-driving cars and close proximity of self-driving cars in multi-access edge computing servers attached to roadside units. Second, we proposed a communication model for retrieving infotainment contents to cache. Third, we proposed a caching model for retrieved contents. Fourth, we proposed a computation model for the cached contents, where cached contents can be served in different formats/qualities based on demands. Finally, we proposed an optimization problem whose goal is to link the proposed models into one optimization problem that minimizes the content downloading delay. To solve the formulated problem, a block successive majorization-minimization technique is applied. The simulation results show that the accuracy of prediction for the contents that need to be cached is 97.82% and our approach can minimize the delay.

Vehicular Mobile Edge Computing is a promising technology to leverage the bottleneck at a base station (BS) at peak hours. However, to deploy Vehicular Mobile Edge Computing requires to deal with the challenges in how to incentive vehicles to resource sharing and how to assign tasks and computation resource to minimize the total network delay. In this paper, we develop a two-stage incentive mechanism and task assignment and resource allocation scheme by combining auction game, matching theory, and convex optimization method. In the first stage, we present the incentive problem between the BS and nearby vehicles, which leverages a reserve auction. Then we study the network delay minimization problem. The problem is decoupled into two subproblems for determining task assignment and computing resource allocation, respectively. Finally, numerical results show the effectiveness and efficiency of our scheme.

Unmanned Aerial Vehicle (UAV) is mobile and has the advantage of being equipped with cameras, sensors, computing resources and devices for communication. By combining the advantage of communication technology and UAV, rapid response can be made at disaster area and used as a mobile base station in place where traffic demand is high, such as concert venue and sports stadium. In addition, by using data that have been collected by mounted sensors and cameras, the UAV can provide data-based application. However, these services usually use big data processing and machine learning techniques which require high computing power and the UAV is not sufficiently capable of process those applications due to lack of computing resources and battery limitation. To overcome this problem, the UAV can offload task to near Mobile Edge Server that can provide computing resources. Mobile Edge Server can be cellular base station, Wi-Fi access point and so on. When tasks occur in a specific area, one or more UAV need to move the location to acquire data and process. If data processing is too heavy to process at local, the UAV can cooperate mobile edge server. In this situation, we can find out two problems. (i)When the tasks occur, which UAV can process occurred task (ii) When UAV is assigned a task, then a mobile edge server can cooperate with UAV. In this paper, based on Hungarian algorithm which is one of matching algorithm, we propose optimal task-UAV-edge server matching algorithm which minimizes energy consumption and processing time.

Multi-access Edge Computing (MEC) is recently acknowledged as one of the key pillars for the next revolution of mobile communications area to provide lower latency and more computation capability for cellular base stations (BSs). The trade-off of delay performance and energy cost which is fully controlled by the association decisions among systems of edge sites of mobile users and the service rate scaling of MEC servers to serve the user tasks is analyzed. In this paper, we formulate a joint user association and MEC server scaling optimization problem, namely MEC - MP. Accordingly, we first propose a centralized algorithm by iteratively solving the user association and MEC server scaling subproblems to obtain a suboptimal solution approach. We then propose a distributed algorithm based on a greedy user association strategy and decentralized solutions of the MEC server scaling problem.