Unmanned Aerial Vehicle (UAV) can enhance communication quality in wireless systems. It is helpful to address the blockage problem in mountainous regions. However, it has high energy consumption. In this paper, we propose a novel blockage model converted blockage region constraints into linear constraint. Then, the joint resource allocation and trajectory design scheme is proposed to maximize energy efficiency (EE). Specifically, we model the blockage effect caused by mountains. The Dinkelbach algorithm is designed to address the fractional objective function for EE. Then, we develop an iterative block coordinate descent (I-BCD) algorithm that alternately optimizes resource allocation and trajectory design subproblems. The resource allocation subproblem employs a dual-loop structure with Lagrangian duality to obtain closed-form solutions for power and bandwidth allocation. Meanwhile, the trajectory optimization uses successive convex approximation (SCA) to transform non-convex constraints into convex optimization problems. Simulation results demonstrate that the proposed scheme improves the EE compared with the benchmark schemes for UAV-assisted communications in mountainous regions.

In extremely low signal-to-noise ratio (SNR) region, the useful features of the signal are weakened by higher-power noise, making it difficult for conventional direction-of-arrival (DOA) estimation methods to adequately exploit and extract the low-SNR signal features. Thus, a generative adversarial network (GAN) is presented to learn the underlying features and complex distributions of high-SNR covariance matrices. The introduced GAN establishes a mapping between low-SNR and high-SNR covariance matrices, thereby generating first-rate high-SNR covariance matrices that closely resemble real high-SNR matrices. Also, it effectively captures signal features that are overwhelmed by excessive noise power. Additionally, to improve the performance of convolutional neural network (CNN)-based DOA estimation models in medium-to-high SNR ranges, a deep residual attention network (DRANet) is designed to significantly enhance DOA estimation accuracy in such SNR region. By integrating residual and attention modules, the network effectively filters key features. This enhances feature learning and adaptability, allowing it to capture DOA-related features more proficiently. The experimental results indicate that the developed GAN-DRANet approach can approach the CRLB in the extremely low SNR range and improves the estimation resolution limits of the other two DL-based methods, DNN and CNN, in medium to high SNR conditions.

The scattering environment in offshore regions leads to serious attenuation in wireless transmission, reconfigurable intelligent surfaces (RISs) have emerged as a promising technology for future offshore communication systems. In this paper, we consider an RIS-assisted three-dimensional (3D) offshore communication system. Unlike quality of service (QoS), which does not accurately represent user-centric offshore communication systems, the mean opinion score (MOS) is adopted as a quality of experience (QoE) metric to evaluate device-to-device (D2D) vessel user (DVU) satisfaction. We aim to maximize the sum MOS of DVUs by jointly optimizing power allocation, spectrum reuse, and RIS reflection coefficients, subject to the minimum signal-to-interference-plus-noise ratio (SINR) requirements for unmanned surface vessels (USVs) and the maximum MOS constraints for DVUs. To tackle this non-convex optimization problem, we adopt the block coordinate descent (BCD) method to decompose the original problem into three sub-problems. Specifically, power allocation, spectrum reuse, and RIS reflection coefficients are iteratively optimized using the fractional programming (FP) method, the successive convex approximation (SCA) technique, and the semi-definite relaxation (SDR) algorithm, respectively. Simulation results demonstrate that the proposed RIS-SDR algorithm achieves sum MOS gains of 4%, 17%, 22%, and 46% compared to the baseline schemes, respectively.

This paper investigates unmanned aerial vehicle (UAV) and an active reconfigurable intelligent surface (RIS)-assisted millimeter-wave (mmWave) dual-function radar-communication (DFRC) system. The DFRC base station (BS) employs a hybrid analog-digital (HAD) architecture. Under the constraints of the active RIS and BS power budgets, the unit-modulus analog precoder, and the desired radar beamforming pattern, we jointly optimize the BS hybrid beamforming (HBF) and active RIS beamforming to maximize the signal-to-interference-plus-noise ratio (SINR) of user. Considering the non-convex SINR objective function and unit-modulus constraints, we propose a weighted minimum mean square error (WMMSE) method based on the penalty dual decomposition (PDD) framework and alternating optimization (AO). For the active RIS beamforming design, we introduce the semidefinite relaxation (SDR) method and a majorization-minimization (MM) method. Finally, the simulation results demonstrate the potential of active RIS in DFRC systems compared to the passive RIS.

Convolutional neural networks (CNNs) have received widespread attention due to their powerful modeling capabilities and have been successfully applied in natural language processing, image recognition, and other fields. On the other hand, traditional CNN can only deal with Euclidean spatial data. In contrast, many real‐life scenarios, such as transportation networks, social networks, reference networks, and so on, exist in graph data. The creation of graph convolution operators and graph pooling is at the heart of migrating CNN to graph data analysis and processing. With the advancement of the Internet and technology, graph convolution network (GCN), as an innovative technology in artificial intelligence (AI), has received more and more attention. GCN has been widely used in different fields such as image processing, intelligent recommender system, knowledge‐based graph, and other areas due to their excellent characteristics in processing non‐European spatial data. At the same time, communication networks have also embraced AI technology in recent years, and AI serves as the brain of the future network and realizes the comprehensive intelligence of the future grid. Many complex communication network problems can be abstracted as graph‐based optimization problems and solved by GCN, thus overcoming the limitations of traditional methods. This survey briefly describes the definition of graph‐based machine learning, introduces different types of graph networks, summarizes the application of GCN in various research fields, analyzes the research status, and gives the future research direction.

The multipath fading and Doppler effect are well‐known phenomena affecting channel quality in mobile wireless communication systems. Within this context, the emergence of reconfigurable intelligence surfaces (RISs) brings a chance to achieve this goal. RISs as a potential solution are considered to be proposed in sixth generation (6G). The core idea of RISs is to change the channel characteristic from uncontrollable to controllable. This is reflected by some novel functionalities with wave absorption and abnormal reflection. In this paper, the multipath fading and Doppler effect are characterized by establishing a mathematical model from the perspective of reflectors and RISs in different mobile wireless communication processes. In addition, the solutions that improve the multipath fading and Doppler effect stemming from the movement of mobile transmitter are discussed by utilizing multiple RISs. A large number of experimental results demonstrate that the received signal strength abnormal fluctuations due to Doppler effect can be eliminated effectively by real‐time control of RISs. Meanwhile, the multipath fading is also mitigated when all reflectors deployed are coated with RISs.

With the development of 5G, the Internet of Vehicles (IoV) evolves to be one important component of the Internet of Things (IoT), where vehicles and public infrastructure communicate with each other through a IEEE 802.11p EDCA mechanism to support four access categories (ACs) to access a channel. Due to the mobility of the vehicles, the network topology is time varying and thus incurs a dynamic network performance. There are many works on the stationary performance of 802.11p EDCA and some on real-time performance, but existing work does not consider real-time performance under extreme highway scenario. In this paper, we consider four ACs defined in the 802.11p EDCA mechanism to evaluate the limit of the real-time network performance in an extreme highway scenario, i.e., all vehicles keep the minimum safety distance between each other. The performance of the model has been demonstrated through simulations. It is found that some ACs can meet real-time requirements while others cannot in the extreme scenario.

Various emerging vehicular applications such as autonomous driving and safety early warning are used to improve the traffic safety and ensure passenger comfort. The completion of these applications necessitates significant computational resources to perform enormous latency-sensitive/nonlatency-sensitive and computation-intensive tasks. It is hard for vehicles to satisfy the computation requirements of these applications due to the limit computational capability of the on-board computer. To solve the problem, many works have proposed some efficient task offloading schemes in computing paradigms such as mobile fog computing (MFC) for the vehicular network. In the MFC, vehicles adopt the IEEE 802.11p protocol to transmit tasks. According to the IEEE 802.11p, tasks can be divided into high priority and low priority according to the delay requirements. However, no existing task offloading work takes into account the different priorities of tasks transmitted by different access categories (ACs) of IEEE 802.11p. In this paper, we propose an efficient task offloading strategy to maximize the long-term expected system reward in terms of reducing the executing time of tasks. Specifically, we jointly consider the impact of priorities of tasks transmitted by different ACs, mobility of vehicles, and the arrival/departure of computing tasks, and then transform the offloading problem into a semi-Markov decision process (SMDP) model. Afterwards, we adopt the relative value iterative algorithm to solve the SMDP model to find the optimal task offloading strategy. Finally, we evaluate the performance of the proposed scheme by extensive experiments. Numerical results indicate that the proposed offloading strategy performs well compared to the greedy algorithm.

The transmission capacity of a vehicular network is still an interesting and challenging problem as capacity is impacted by transmission distance between both vehicles, density of vehicles, relay among vehicles, noise and interference. This study analyses the transmission capacity of vehicular device‐to‐device relay networks with multi‐users (service vehicle (SV) and helper vehicle (HV)) in the overlay mode. SVs coexisting with HVs share the spectrum resources. Utilising stochastic geometry theory, SVs and HVs are modelled as the Poisson point process in vehicular networks, respectively. Subsequently, the HVs existence probability and the expectation distance with HV link are derived to calculate the successful transmission probabilities for SV to SV communication. With this characteristic HV relay transmission signals exceed transmission distance, the authors further calculate the transmission capacities with SV to SV communication assisted by HVs and reveal the influence of vehicles' density and transmission power. Besides, the relationship between transmission capacities, the variable direct link distance of SV to SV communication is also analysed. Simulation results indicate that transmission capacity can be improved by an assisted HV and influenced by a few system parameters, including the direct link distance between source SV and destination SV, SVs density and HVs density.

Packet collision and packet delay are considered to be critical for safety applications in vehicular networks. This paper designs a new analytical model to evaluate the performance of channel switching for IEEE 802.11p/WAVE in vehicular networks. Under this model, it explicitly expresses the WAVE channel switching, and constructs contention window size and number of vehicles as packet collision probability and packet delay time function of variables. Finally, we evaluate accuracy of the designed model of collision caused by channel switching and transmission delay in vehicular networks. The results show that the model could analyzes perfectly packet collision which is caused by channel switching and packet delay in vehicular networks.

Node location information with high accuracy is very important in many applications of wireless sensor networks. In addition, the nodes are power-limited, hence, we need to save energy to guarantee the operations of network. These two metrics positioning accuracy and energy consumption should be balanced, mean that one should improve them both at the same time. In this paper, we model the energy consumption of nodes in the network by using the carrier-sense multiple-access/collision-avoidance (CSMA/CS) technique in combination with request-to-send (RTS)/clear-to-send (CTS) mechanism based IEEE 802.11 protocol to perform the transmission process of nodes. Otherwise, based on the mathematical model of direction-of-arrival (DoA) estimation error variance as a function of Received-Signal-Strength (RSS) we derive the Cramer-Rao lower bound (CRLB) of achievable accuracy of the target node that jointly utilizes difference-received-signal-strength (DRSS) and DoA measurements to estimate location as the objective function of positioning error. The Non-dominated Sorting Genetic Algorithm (NSGA-II) optimization algorithm can effectively find the Nash Equilibrium or Pareto optimal solutions of our dual objective optimization problem. The results show a high performance in both localization accuracy and energy consumption of the proposed algorithm.

In this paper, we give a closed form expression for the statistics of two independent exponential for two-hop links of vehicular networks. Then these statistics results help us to analyze the performance of two-hop vehicular communication networks with vehicle relay based on Amplify and Forward (AF) protocol over flat Rayleigh-fading channels. It is shown that the choice of gain of AF effects on bounds on the performance of these relay vehicular networks. And outage probability formula is obtained. Furthermore, we give out specifically a vehicle relay selection scheme. The "best" vehicle relay has been selected by satisfying specific criteria in respect of signal-to-noise ratio (SNR). Finally, simulation results display the difference between regeneration and non-regeneration vehicular systems. At low average SNR, AF relay vehicular networks have better performance. However, these two kinds of systems have similar outage probability at high average SNR.