The unmanned aerial vehicle (UAV) has been widely applied for data collection in Internet of things (IoT) networks due to its advantages of rapid deployment, flexible configuration, and high mobility. Therefore, we propose a multi-UAV cooperative path planning architecture based on machine learning algorithms. This architecture enhances the overall energy efficiency and task completion effectiveness of the data collection system by incorporating communication range constraints and co-optimizing the flight and hovering processes. Specifically, an optimization model is established with the objective of minimizing the weighted task completion time and total energy consumption, which is difficult to directly solve because of the high dimensional and strongly coupled characteristics. To deal with this problem, a multi-UAV cooperative path planning algorithm based on improved clustering and hybrid genetic algorithm (GA) and ant colony optimization (ACO) is proposed. First, the IoTDs are preliminarily clustered using the improved K-means algorithm, and the results are adaptively adjusted by incorporating the maximum UAV communication distance constraint. Second, considering the differences in data volume and priority among nodes within a cluster, a cluster head (CH) selection mechanism based on weighted normalized scoring is designed. Furthermore, the multi-UAV path planning problem is transformed into a traveling salesman problem for solution via a “flight-hover-flight” strategy. Simulation results demonstrate that, compared to traditional baseline schemes, the proposed algorithm fully leverages the positive feedback regulation of ant colony pheromones and the global search capability of the GA, achieving significant advantages in convergence speed and solution quality. Besides, the system’s comprehensive cost can be reduced by up to approximately 15%.

As the frame synchronization of the physical layer signal processing, timing synchronization (TS) is crucial for signal demodulation in vehicular communication systems (VCSs). However, existing TS methods primary rely on known training sequence to identify the first-arriving path, facing significant challenges in the scenarios with prominent Doppler and multipath interfere. Inspired by integrated sensing and communication (ISAC) technology, a sensing-aided TS method is proposed to address these challenges in VCSs. In this method, a detection threshold in the delay-Doppler (DD) domain is designed to extract echo paths. Based on the echo paths, we perform correlation matching between the Doppler prior information and the received communication signal, thereby further refining the sensing prior information for TS. With the assistance of Doppler prior information, the correctness of TS is improved by rectifying the local training sequence to compensate for the Doppler frequency shift of the received communication signal. In addition, an iterative method is developed to identify the first-arriving path by eliminating the impacts of paths stronger than the first one. Simulation results demonstrate that the proposed method significantly reduces TS error probability and exhibits its robustness against parameter variations.

In massive multiple-input and multiple-output (mMIMO) systems, compressed sensing (CS)-based channel state information (CSI) feedback methods still face significant challenges, such as unknown channel sparsity, high computational complexity, and unavoidable channel estimation (CE) errors at the user equipment (UE). These factors degrade the accuracy of downlink CSI reconstruction at the base station (BS). To tackle these challenges, inspired by the work of perception-assisted communication, a perception-assisted CS-based CSI feedback method is proposed in this paper. In this method, an active perception scheme is developed to extract the support set of downlink CSI from the echo signals, addressing the issue of unknown channel sparsity in CS-based methods. With the perceived support set, the perception-assisted reconstruction without perception errors (PaRwoPE) method is proposed to achieve a lower bound of CSI recovery accuracy. This method develops a perception-assisted suppression scheme to reduce CE errors and transceiver noise and uses the perceived support set to avoid iterative reconstruction, thereby significantly improving the recovery accuracy of downlink CSI with markedly reduced computational complexity. To suppress the inevitable perception errors, a perception-assisted reconstruction with perception errors (PaRPE) method is developed. This method utilizes path correlation to eliminate false paths in the downlink CSI, while also developing a low-complexity iterative scheme to recover missed paths. The computational complexity analysis shows that the proposed method notably reduces computational complexity. Furthermore, simulation results demonstrate its effectiveness in improving normalized mean squared error (NMSE) performance and exhibit robustness against parameter variations.

With the continuous improvement of spectrum efficiency and connection density requirements of internet of things (IoT) networks, the integration of non-orthogonal multiple access (NOMA) technology and unmanned aerial vehicle (UAV) communication technology has gradually become a hot research direction. In this paper, a UAV deployment and resource allocation strategy is proposed for the UAV-NOMA based IoT networks. The strategy aims to improve the user connection capability, and comprehensively considers multiple factors such as the UAV height optimization, the users’ transmit power allocation and subcarrier scheduling. Specifically, this proposed strategy is dominated by the genetic algorithm (GA) to achieve the collaborative scheduling of resources by combining power control and channel allocation sub-algorithms. The simulation results show that the proposed strategy has an excellent performance under a variety of system parameter changes, and the average user connection ratio is 10% higher than that of the comparison algorithm. This work provides an effective resource management solution for the UAV-NOMA based system in the future air-ground convergence communication scenario, and thus has good engineering practical value and promotion prospects.

Accurate acquisition of downlink channel state information (CSI) at the base station (BS) remains a critical challenge in frequency division duplex (FDD) millimeter wave (mmWave) massive multiple-input multiple-output (mMIMO) systems. Although compressive sensing (CS) and deep learning (DL)-based CSI feedback methods demonstrate their advantages, the recovery accuracy of downlink CSI in FDD mmWave mMIMO systems still faces severe challenges due to the facts of significant user equipment (UE) estimation errors, and typical compression requirements. To tackle these challenges, this paper proposes a novel echo sensing-aided CSI feedback framework designed to enhance downlink CSI recovery accuracy. In the proposed method, the communication echo signals observed at the BS are utilized to extract the dedicated sensing prior information for the downlink CSI recovery. With the extracted sensing prior information, a CSI denoising method is developed to suppress the non-path entries of the downlink CSI matrix in the angular-delay domain, thereby improving the recovery accuracy of downlink CSI at the BS. The framework operates as a plug-in module at the BS receiver, requiring no modifications to existing UE hardware. This work establishes a new paradigm for integrating sensing-assisted enhancements into FDD mmWave mMIMO systems without compromising compatibility with standardized UE operations. Simulations validate that the proposed method outperforms conventional CS and DL-based methods in terms of CSI reconstruction accuracy while demonstrating robustness to parameter variations.

Integrated sensing and communication (ISAC) is a promising technique that simultaneously provides communication and sensing services, thereby attracting significant attention as a hot topic for next wireless systems. Leveraging communication signal echoes for environmental sensing holds significant potential. Channel estimation (CE), being closely related to environmental information, stands to benefit from incorporating this echo sensing. However, despite the promise of ISAC, the utilization of communication signal echo sensing in sensing-assisted CE has not been well explored, hampering the progress in enhancing CE accuracy. To bridge this gap and overcome this challenge, we propose a sensing-aided CE method tailored specifically for vehicle-to-everything (V2X) communication scenarios using orthogonal frequency-division multiplexing (OFDM) modulation, extracting sensing prior information from communication echoes. The proposed scheme employs radar signal processing algorithms to extract sensing parameters from received communication echoes at the base station (BS). Subsequently, the false path suppression is performed to refine these sensing parameters, yielding echo sensing-based prior information reflecting the channel attributes between the target vehicle and the BS. By leveraging this prior information, an echo sensing-aided CE is proposed to fully exploit channel sparsity and bounded characteristics in the delay-Doppler (DD) domain, thereby enhancing CE accuracy. Simulation results demonstrate the effectiveness of the proposed method in rectifying estimation error by using echo sensing information. Notably, the proposed method not only achieves significantly improved CE accuracy compared to classic enhancement methods and deep learning (DL) methods, but also exhibits robustness against the parameter variations.

Unmanned aerial vehicle (UAV) has been widely applied to collect data because of its rapid deployment, high flexibility and strong adaptability characteristics. However, due to the data capacity constraints of UAVs, how to effectively deploy UAVs in complex mountain roads to achieve vehicle coverage has become an important research problem. Thus, we propose an optimization method for the coverage deployment of UAVs in the internet of vehicles (IoV) based on complex mountain environments. The method combines the K-means clustering algorithm and the genetic algorithm (GA) with the objective of maximizing the total number of covered vehicles while considering the vehicle data rate requirements and the capacity constraints of UAVs. Firstly, the K-means clustering algorithm was used to cluster the vehicles, and the cluster center was used as the initial UAV position to generate the initial population. Then, the GA is introduced to find the optimal solution that could maximize the number of vehicles covered by the UAVs while meeting the communication requirements. The experimental results show that the proposed method can effectively optimize the coverage deployment scheme of IoV and UAVs in complex mountain environments. This method not only improves the vehicle coverage rate, but also makes full use of the data capacity of the UAV to ensure the effectiveness and stability of data transmission.

Unmanned aerial vehicle (UAV) communication has been recognized as an appealing technology for the efficient data collection in Internet of Things (IoT) networks. Whereas, the majority of existing data collection strategies of UAV-aided IoT networks with wireless power transfer (WPT) or non-orthogonal multiple access (NOMA) technology are mostly only have a single UAV, which cannot meet the requirement of massive IoT networks. Thus, we propose to maximize the minimum data collection rate of UAVs from the IoT devices (IoTDs) in a NOMA-based dual-UAV data collection system by jointly optimizing the UAVs’ trajectories, IoTDs’ scheduling and transmit power under the UAVs’ flight speed constraint, and the IoTDs’ energy harvesting constraint. To solve this non-convex problem, we resort to the alternating optimization and successive convex approximation to convert the original problem into a convex form, and then propose a low-complexity NOMA-based dual-UAV data acquisition algorithm (DUDCA) to settle the transformed problem. Abundant simulation results are given to verify that the proposed DUDCA can effectively enhance the maximization of minimum throughput compare to the benchmark strategies with fixed trajectory or random scheduling of IoTDs.

Abstract Due to the implementation bottleneck of training data collection in realistic wireless communications systems, supervised learning‐based timing synchronization (TS) is challenged by the incompleteness of training data. To tackle this bottleneck, the computer‐aided approach is extended, with which the local device can generate the training data instead of generating learning labels from the received samples collected in realistic systems, and then construct an extreme learning machine (ELM)‐based TS network in orthogonal frequency division multiplexing (OFDM) systems. Specifically, by leveraging the rough information of channel impulse responses (CIRs), i.e. root‐mean‐square (r.m.s) delay, the loose constraint‐based and flexible constraint‐based training strategies are proposed for the learning‐label design against the maximum multi‐path delay. The underlying mechanism is to improve the completeness of multi‐path delays that may appear in the realistic wireless channels and thus increase the statistical efficiency of the designed TS learner. By this means, the proposed ELM‐based TS network can alleviate the degradation of generalization performance. Numerical results reveal the robustness and generalization of the proposed scheme against varying parameters.

Data-dependent superimposed training (DDST) scheme has shown the potential to achieve high bandwidth efficiency, while encounters symbol misidentification caused by hardware imperfection. To tackle these challenges, a joint model and data driven receiver scheme is proposed in this paper. Specifically, based on the conventional linear receiver model, the least squares (LS) estimation and zero forcing (ZF) equalization are first employed to extract the initial features for channel estimation and data detection. Then, shallow neural networks, named CE-Net and SD-Net, are developed to refine the channel estimation and data detection, where the imperfect hardware is modeled as a nonlinear function and data is utilized to train these neural networks to approximate it. Simulation results show that compared with the conventional minimum mean square error (MMSE) equalization scheme, the proposed one effectively suppresses the symbol misidentification and achieves similar or better bit error rate (BER) performance without the second-order statistics about the channel and noise.

Due to the nonlinear distortion in Orthogonal frequency division multiplexing (OFDM) systems, the timing synchronization (TS) performance is inevitably degraded at the receiver. To relieve this issue, an extreme learning machine (ELM)-based network with a novel learning label is proposed to the TS of OFDM system in our work and increases the possibility of symbol timing offset (STO) estimation residing in intersymbol interference (ISI)-free region. Especially, by exploiting the prior information of the ISI-free region, two types of learning labels are developed to facilitate the ELM-based TS network. With designed learning labels, a timing-processing by classic TS scheme is first executed to capture the coarse timing metric (TM) and then followed by an ELM network to refine the TM. According to experiments and analysis, our scheme shows its effectiveness in the improvement of TS performance and reveals its generalization performance in different training and testing channel scenarios.

We study the optimal precoding for a full-duplex (FD) system, where one FD multi-antenna base station (BS) respectively transmits to and receives from two half-duplex single-antenna mobile users (MUs) on the same time slot and frequency band. At the FD BS, the received signal from the desired MU is severely affected by the extremely strong self-interference (SI) from its transmit antennas to the receive antennas. In the presence of residual SI after imperfect SI cancellation, the downlink transmission rate maximization problem subject to a targeted uplink rate is formulated as a non-convex optimization problem to characterize the achievable rate region for the considered system. Considering the case in which the SI channel is strongly correlated, the above problem is transformed into a convex problem by exploiting the rank-one property of the SI channel, which can be solved efficiently. Finally, numerical results validate the effectiveness of the proposed scheme.

In this paper, we investigate the effect of shadowing on optimal power allocation of amplify- and-forward cooperative relaying systems. Considering the joint effects of path loss, correlated shadowing and flat Rayleigh fading, the approximate outage probability at high signal-to- noise ratio (SNR) is first derived. Then we solve the power allocation problem by minimizing the approximate outage probability subject to a total power constraint. It is shown by the analytical results that the correlation coefficients and the standard deviations of shadowing have a significant impact on the optimal power allocation. The simulation results show that the proposed power allocation scheme yields about 2dB SNR gain compared to the equal power allocation in the high SNR regime.

To obtain the receive diversity of timing acquisition, the cooperative processing of multiple distributed received antennas is considered in this paper. In the flat Rayleigh channels, we assume two remote antennas at the base station for receiving the signal transmitted from the mobile station with a single antenna. By utilizing the coverage range of each remote antenna, a constraint is exploited to associate the time-delays from the mobile station to the two remote antennas. With this constraint, we propose a maximum likelihood-based cooperative timing acquisition method to improve the probability of correct acquisition for each remote antenna. Also, a lower bound of the probability of correct acquisition is derived to evaluate the performance of the proposed method. Compared to the independent timing acquisition, the analysis and simulations show that the probability of correct acquisition for each remote antenna can be improved by the cooperation of the two remote antennas.

This paper investigates the cooperative timing acquisition (CTA) for distributed antenna systems (DAS). As a preliminary study, the path loss and additive white Gaussian noise (AWGN) channel are considered without assuming multipath fading and shadowing. In the DAS coverage region, two remote antennas (RA) are assumed at base station (BS) for receiving the signal transmitted from the mobile station (MS) with a single antenna. Under the constraint that is derived from the known locations of the two RAs, a maximum-likelihood (ML)-based CTA method is proposed. By the analysis and simulation, it is shown that the probability of correct acquisition for each RA can be improved by the cooperation of the two RAs.