Recently, lightweight networks for single image super-resolution (SISR) have surged due to the need of resource-constrained devices, where divide-and-conquer multi-route model exhibits impressive trade-off between performance and computational cost. However, most existing divide-and-conquer multi-route models face two key limitations: (1) possible suboptimal decoupling of image components (e.g. smooth regions, edges and texture details) due to spatial-domain-only processing, and (2) inability to model global dependencies explicitly and capture structural information, hindering further performance gains. To address these drawbacks, we propose a lightweight frequency-selection-based progressive patch Transformer network (FSPPTN) for higher-quality SISR reconstruction. Specifically, we first propose a frequency selection module, in which we develop a frequency enhancement branch (FEB) to dynamically decouple different image components by introducing the window-based Fast Fourier transform (WFFT) and a learnable weight matrix, and a spatial restoration branch (SRB) to recalibrate and fuse cross-granularity features by designing a multi-gate mechanism for reconstructing the component information screened out by the FEB at current level. Secondly, we propose a lightweight multi-branch gradient-guided inter-patch self-attention to explicitly capture global structural similarities by summarizing structural information of each patch into a lower-dimensional space using the statistical properties of first-order gradients, thereby achieving explicit global dependencies modeling and lightweight. Extensive experimental results demonstrate that, in the vast majority of cases, FSPPTN outperforms state-of-the-art lightweight SISR methods in terms of both performance and computational overhead, especially for ×3 and ×4 SR, e.g. FSPPTN outperforms MaIR-Small by even 0.14dB PSNR on Manga109 dataset for ×4 SR even with 48.3% fewer parameters and 63.5% lower FLOPs. The code is available at: https://github.com/yslyangshuli/FSPPTN-main.

The space-air-ground integrated network (SAGIN) is a crucial technology for sixth-generation (6G) wireless communication networks to achieve seamless coverage and high throughput. In this paper, we propose an unmanned aerial vehicle (UAV)-assisted SAGIN structure, where the UAV is responsible for collecting data from ground users (GUs) and transmitting it to low-earth orbit (LEO) satellites. This paper also formulates a joint energy-efficient and fair resource scheduling optimization problem under jamming attacks and limited energy constraints, where the line-of-sight (LoS) links between the UAV and GUs are susceptible to being jammed. Due to the non-convex problem and dynamic environments, a deep reinforcement learning (DRL)-based twin delayed deep deterministic policy gradient (TD3) is developed to search optimal UAV trajectory to maximize energy efficiency (EE) and fairness against jamming. Simulation results verify that the proposed intelligent resource scheduling algorithm outperforms the baseline algorithms in terms of EE and fairness index in different settings.

This letter proposes a high-order probabilistic shaped (PS) system for joint source-channel coding (JSCC) using polar codes, which are employed for both source compression and channel coding. The modulation is based on a selection rule derived from the proposed bit classification distribution matching (BCDM) algorithm. An external binary random sequence is used to select and redundantly insert the codeword sequence, which makes the modulation symbol probability approach the Gaussian distribution, instead of being uniformly distributed as in the conventional constellation mapping. At the receiver, a joint belief propagation (JBP) decoder, which consists of a source and a channel BP decoder, is applied. Simulation results demonstrate that the proposed PS joint source-channel polar-coded modulation (PS-JSCPCM) system yields a significant enhancement to the bit error rate (BER) performance compared with the traditional unshaped joint source-channel code-modulation (JSCCM) system.

With the rapid proliferation of smart devices in wireless networks, more powerful technologies are expected to fulfill the network requirements of high throughput, massive connectivity, and diversify quality of service. To this end, rate splitting multiple access (RSMA) is proposed as a promising solution to improve spectral efficiency and provide better fairness for the next-generation mobile networks. In this paper, the outage performance of uplink RSMA transmission with randomly deployed users is investigated, taking both user scheduling schemes and power allocation strategies into consideration. Specifically, the greedy user scheduling (GUS) and cumulative distribution function (CDF) based user scheduling (CUS) schemes are considered, which could maximize the rate performance and guarantee scheduling fairness, respectively. Meanwhile, we re-investigate cognitive power allocation (CPA) strategy, and propose a new rate fairness-oriented power allocation (FPA) strategy to enhance the scheduled users’ rate fairness. By employing order statistics and stochastic geometry, an analytical expression of the outage probability for each scheduling scheme combining power allocation is derived to characterize the performance. To get more insights, the achieved diversity order of each scheme is also derived. Theoretical results demonstrate that both GUS and CUS schemes applying CPA or FPA strategy can achieve full diversity orders, and the application of CPA strategy in RSMA can effectively eliminate the secondary user’s diversity order constraint from the primary user. Simulation results corroborate the accuracy of the analytical expressions, and show that the proposed FPA strategy can achieve excellent rate fairness performance in high signal-to-noise ratio region.

Mobile edge computing (MEC) enables communication users with limited computation power to offload computation-intensive tasks to the edge server, thus dramatically enhancing the limited computing capabilities of the users. As the reality of scarce spectrum resources and the energy-constrained nature of communication users, this paper introduces non-orthogonal multiple access (NOMA) and simultaneous wireless information and power transfer (SWIPT) techniques to achieve more efficient task offloading in MEC. To minimize the number of computationally failed tasks while simultaneously satisfying different quality of service (QoS) requirements of users, a joint resource management problem of the spectrum, computation, and energy resources is formulated. Due to the non-convexity of the offloading optimization problem and the stochastic nature of the constructed MEC environment, a multiple agents deep deterministic policy gradient (MADDPG)-based resource management algorithm is proposed to manage each user’s multidimensional resources without collaborating. The simulation results show that compared to other benchmark schemes, the proposed algorithm can effectively improve both the communication and computational performances in MEC.

Rate-splitting multiple access (RSMA) is promising to be developed as a key enabling technology for 6G. This paper investigates the resource allocation problem in a downlink multi-user and multiple-input single-output (MU-MISO) RSMA system with successive interference cancellation (SIC) errors for ultra-reliable and low-latency communications (URLLC). The single-carrier RSMA (SC-RSMA) resource allocation scheme with URLLC is first given, where the beamforming vector and the transmission rate are optimized to maximize the effective throughput (ET). To solve the non-convex optimization problem formulated in the SC-RSMA scheme, an iterative algorithm based on block coordinate descent (BCD) and successive convex approximation (SCA) is proposed to alternately optimize the beamforming factor and the transmission rate. Furthermore, the multicarrier RSMA (MC-RSMA) scheme is developed for the URLLC access of large-scale users. Based on the results of the SC-RSMA scheme, a low-complexity three-step optimization algorithm is proposed to solve the resource allocation problem formulated in the MC-RSMA scheme. Finally, the simulation results show that the RSMA scheme and MC-RSMA scheme can respectively achieve higher ET than the non-orthogonal multiple access (NOMA) scheme and multi-carrier NOMA (MC-NOMA) scheme in the URLLC scenario, and verify that RSMA can reduce the latency and improve the reliability of the system.

An active reconfigurable intelligent surface (RIS)-aided multi-user downlink communication system is investigated, where non-orthogonal multiple access (NOMA) is employed to improve spectral efficiency, and the active RIS is powered by energy harvesting (EH). The problem of joint control of the RIS’s amplification matrix and phase shift matrix is formulated to maximize the communication success ratio with considering the quality of service (QoS) requirements of users, dynamic communication state, and dynamic available energy of RIS. To tackle this non-convex problem, a cascaded deep learning algorithm namely long short-term memory-deep deterministic policy gradient (LSTM-DDPG) is designed. First, an advanced LSTM based algorithm is developed to predict users’ dynamic communication state. Then, based on the prediction results, a DDPG based algorithm is proposed to joint control the amplification matrix and phase shift matrix of the RIS. Finally, simulation results verify the accuracy of the prediction of the proposed LSTM algorithm, and demonstrate that the LSTM-DDPG algorithm has a significant advantage over other benchmark algorithms in terms of communication success ratio performance.

Non-orthogonal multiple access (NOMA) assisted semi-grant-free (SGF) transmission has recently received significant research attention due to its outstanding ability of serving grant-free (GF) users with grant-based (GB) users’ spectrum, which greatly improves the spectrum efficiency and effectively relieves the massive access problem of 5G and beyond networks. In this paper, we first study the outage performance of the greedy best user scheduling SGF scheme (BU-SGF) by considering the impacts of Rayleigh fading, path loss, and random user locations. In order to tackle the admission fairness problem of the BU-SGF scheme, we propose a fair SGF scheme by applying cumulative distribution function (CDF)-based scheduling (CS-SGF), in which the GF user with the best channel relative to its own statistics will be admitted. Moreover, by employing the theories of order statistics and stochastic geometry, the outage performances of both BU-SGF and CS-SGF schemes are analyzed. Theoretical results show that both schemes can achieve full diversity orders only when the served users’ data rate is capped, which severely limits the rate performance of SGF schemes. To further address this issue, we propose a distributed power control strategy to relax such data rate constraint, and derive analytical expressions of the two schemes’ outage performances under this strategy. Finally, simulation results validate the fairness performance of the proposed CS-SGF scheme, the effectiveness of the power control strategy, and the accuracy of the theoretical analyses.

In recent years, with the globalization and advancement of the telecommunications industry, the competition in the telecommunications market has become more intense, accompanied by high customer churn rates. Therefore, telecom operators urgently need to formulate effective marketing strategies to prevent the churning of customers. Customer churn prediction is an important means to prevent customer churn, but due to the imbalance of data in the telecommunications industry, the prediction results are always unsatisfactory. To improve prediction performance, the most common method is to oversample the minority class. Standard methods such as SMOTE usually only focus on the minority class samples, and it is easy to ignore the connection between the minority class samples and the majority class samples. In addition, in the case of high-dimensional, complex data distribution, the Euclidean distance used in the SMOTE algorithm is not particularly meaningful and tend to underperform. While Generative Adversarial Networks (GANs) are able to model complex distributions and can in principle be used to generate minority class cases. Therefore, this paper adopts a comprehensive GAN model (CWGAN) based on Wasserstein GAN with Gradient Penalty (WGANGP) and Conditional GAN (CGAN) to handle the imbalanced data in the telecom industry. This is also the first time that GAN has been used to deal with the data imbalance problem in the telecom industry. At the same time, this paper also introduces a hybrid attention mechanism (CBAM) to further assist the generator to focus on features related to classification tasks. Afterwards, the effectiveness of the adopted method is demonstrated on four commonly used machine learning classifiers.

Abstract Ultra‐reliable low‐latency communication (URLLC) has the most stringent end‐to‐end communication performance requirements among the three major 5G scenarios. The URLLC enhancement research on 5G‐advanced and 6G needs to be explored continuously. First, through the analysis of the mmWave downlink channel model with finite block length, the CRC detection error feedback mechanism is introduced, and a variable code rate CRC‐AFC cascaded coding scheme is designed. The re‐encoding process of the proposed scheme can effectively improve the system reliability in a wide SNR range. Then, a URLLC dynamic spectrum optimisation algorithm based on CRC‐AFC cascade coding is proposed by analysing the relationship between the latency constraint range of URLLC data, the SNR, and the coding error rate. While ensuring the quality of non‐URLLC communication, the proposed algorithm can dynamically allocate unlicensed spectrum based on the code rate and URLLC traffic, so as to improve reliability within a wide SNR range and improve latency performance under a large number of URLLC users.

The combination of energy harvesting (EH), cognitive radio (CR), and non-orthogonal multiple access (NOMA) is a promising solution to improve energy efficiency and spectral efficiency of the upcoming beyond fifth generation network (B5G), especially for support the wireless sensor communications in Internet of things (IoT) system. However, how to realize intelligent frequency, time, and energy resource allocation to support better performances is an important problem to be solved. In this paper, we study joint spectrum, energy, and time resource management for the EH-CR-NOMA IoT systems. Our goal is to minimize the number of data packets losses for all secondary sensing users (SSU), while satisfying the constraints on the maximum charging battery capacity, maximum transmitting power, maximum buffer capacity, and minimum data rate of primary users (PU) and SSUs. Due to the non-convexity of this optimization problem and the stochastic nature of the wireless environment, we propose a distributed multidimensional resource management algorithm based on deep reinforcement learning (DRL). Considering the continuity of the resources to be managed, the deep deterministic policy gradient (DDPG) algorithm is adopted, based on which each agent (SSU) can manage its own multidimensional resources without collaboration. In addition, a simplified but practical action adjuster (AA) is introduced for improving the training efficiency and battery performance protection. The provided results show that the convergence speed of the proposed algorithm is about 4 times faster than that of DDPG, and the average number of packet losses (ANPL) is about 8 times lower than that of the greedy algorithm.

With the advent of the Internet of Everything era, communication data has exploded, which requires more communication resources, such as frequency, time, and energy. In this context, this paper presents a machine learning-based data packet scheduling scheme to achieve efficient data packet transmission in the 5G/6G communication systems. To minimize the average number of packet overflows (APNO), we propose distributed deep deterministic policy gradient (DDPG)-based algorithm for multidimensional resource scheduling. To improve the algorithm stability and training efficiency, the strategy of centralized training and distributed execution is adopted, and an Action Adjuster is designed. The proposed algorithm enables the multidimensional resource management of the 5G/6G commu-nication systems without any information interaction between each agent. Simulation results show that the proposed Action Adjuster DDPG algorithm achieves faster convergence and less data overflow compared to other benchmark algorithms.

The Industrial Internet of Things (IIoT) has attracted tremendous interest from both industry and academia as it can significantly improve production efficiency and system intelligence. However, with the explosive growth of various types of user equipment (UE) and data flow, IIoT experiences spectrum resource scarcity for wireless applications. In this article, we propose a solution for spectrum resource management for the IIoT network, with the objective of facilitating the limited spectrum sharing between different kinds of UEs. To overcome the challenges of unknown dynamic IIoT environments, a modified deep $Q$ -learning network (MDQN) is developed. Considering the cost effectiveness of IIoT devices, the base station (BS) acts as a single agent and centrally manages the spectrum resources, which can be executed without coordination or exchange between UEs. In this article, we first built a realistic IIoT model and design a simple medium access control (MAC) frame structure to facilitate the environment state observation. Then, a new reward function is designed to drive the learning process, which takes into account the different communication requirements of various types of UEs. In addition, to improve the learning efficiency, we compress the action space and propose a priority experience replay strategy based on decreasing temporal difference (TD) error. Finally, simulation results show that the proposed algorithm can successfully achieve dynamic spectrum resource management in the IIoT network. Compared with other algorithms, it can achieve superior network performance with a faster convergence rate.

The success of convolutional neural network (CNN) based single image dynamic scene blind deblurring (SIDSBD) methods mainly stems from the multi-scale/multi-patch model and the designs of the encoder-decoder architecture, and the residual block structure, which make different contributions to SIDSBD. In this paper, we further exploit the advantages of the multi-scale model, the encoder-decoder module, and the residual block structure, respectively, and propose a novel multi-scale channel attention network (MSCAN) for effective single image dynamic scene blind deblurring. Different from existing multi-scale models, in our proposed network, each scale consists of multiple levels, in which a novel spatial pyramid pooling channel attention (SPPCA) strategy is proposed to adaptively rescale the channel-wise features by using both the global and local feature statistics for more powerful network representation. Extensive experiments on both the synthetic benchmark datasets and the real blurred images show that our method can produce better deblurring results than the state-of-the-art SIDSBD methods in terms of both qualitative evaluation and quantitative metrics.

In this paper, a cumulative distribution function (CDF)-based scheduling scheme for uplink non-orthogonal multiple access (NOMA) network is investigated. With considering imperfect successive interference cancellation (SIC) and SIC power constraint, closed-form expressions for the outage probability of two scheduled users are derived in cognitive-radio-inspired power allocation (CPA) scenario. To get more insights, high SNR approximations of the outage probabilities are given, and the results reveal that the two users can achieve a diversity order linear with the number of users. Simulation results validate the accuracy of the analytical expressions.

Internet of Things (IoT) has attracted tremendous interest since it can improve production efficiency and system intelligence significantly. However, with the explosive growth of various types of device and data flow, IoT suffers spectrum resource scarcity for wireless applications. In this paper, we propose a solution for spectrum resource sharing in the IoT network, with the objective to facilitate the limited spectrum sharing between different kinds of sensors. To overcome the challenges of unknown dynamic IoT environment, the deep Q-learning network (DQN) is adopted. BS acts as the single agent and centrally manages all spectrum resources. First, a new reward function is designed to drive the learning process, which takes into account the different communication requirements of various sensors. In addition, to improve the learning efficiency of DQN, we compress the action space. Finally, simulation results show that compared with other algorithms, the proposed algorithm can achieve good network performance.

Internet of Things (IoT) has attracted much interest due to its wide applications, such as smart city, manufacturing, transportation, and healthcare. Social and cognitive IoT is capable of exploiting social networking characteristics to optimize network performance. Considering the fact that the IoT devices have different Quality-of-Service (QoS) requirements [ranging from ultrareliable and low-latency communications (URLLCs) to minimum data rate], this article presents a QoS-driven social-aware-enhanced device-to-device (D2D) communication network model for social and cognitive IoT by utilizing social orientation information. We model the optimization problem as a multiagent reinforcement learning formulation, and a novel coordinated multiagent deep-reinforcement-learning-based resource management approach is proposed to optimize the joint radio block assignment and the transmission power control strategy. Meanwhile, the prioritized experience replay (PER) and the coordinated learning mechanisms are employed to enable communication links to work cooperatively in a distributed manner, which enhances the network performance and access success probability. The simulation results corroborate the superiority in the performance of the presented resource management approach, and it outperforms other existing approaches in terms of meeting the energy efficiency and the QoS requirements.

Smart factory under Industry 4.0 and industrial Internet of Things (IoT) has attracted much attention from both academia and industry. In wireless industrial networks, industrial IoT and IoT devices have different quality-of-service (QoS) requirements, ranging from ultra-reliable low-latency communications (URLLC) to high transmission data rates. These industrial networks will be highly complex and heterogeneous, as well as the spectrum and energy resources are severely limited. Hence, this article presents a heterogeneous radio frequency (RF)/visible light communication (VLC) industrial network architecture to guarantee the different QoS requirements, where RF is capable of offering wide-area coverage and VLC has the ability to provide high transmission data rate. A joint uplink and downlink energy-efficient resource management decision-making problem (network selection, subchannel assignment, and power management) is formulated as a Markov decision process. In addition, a new deep post-decision state (PDS)-based experience replay and transfer (PDS-ERT) reinforcement learning algorithm is proposed to learn the optimal policy. Simulation results corroborate the superiority in performance of the presented heterogeneous network, and verify that the proposed PDS-ERT learning algorithm outperforms other existing algorithms in terms of meeting the energy efficiency and the QoS requirements.

With the rapid development of Internet of Things (IoT) in the smart city, smart grid and smart industry, indoor communication and positioning are important fields of applications for indoor IoT. This paper presents an integrated visible light communication and positioning (VLCP) system for indoor IoT, in order to provide the high-speed data rate and high-accuracy positioning for IoT devices. where the filter bank multicarrier-based subcarrier multiplexing (FBMC-SCM) technique is exploited to effectively reduce the out-of-band interference (OOBI) on both adjacent communication and positioning subcarriers. After that, we propose a coordinated resource allocation approach for the system with the purpose of maximizing the sum rate while guaranteeing the minimum data rates and positioning accuracy requirements of devices. To this end, we solve the optimization problem by decomposing it into two subproblems, where a low-complexity suboptimal subcarrier allocation approach is proposed and the sequential quadratic programming (SQP) method is adopted to solve the non-linearly constrained power allocation optimization problem. Numerical results verify the superiority in performance of the presented integrated VLCP system for indoor IoT, and the results also reveal that the proposed coordinated resource allocation approach can effectively improve the sum rate and the positioning accuracy compared with other resource allocation approaches.

With the continuous development of social networks, it is more and more important to obtain users' personalized preferences and predict users' next step through the analysis of users' check-in data. The check-in information of users' contains comments on the check-in location, which contains a large number of personal preference information and location features. In this paper, we predict the users' next visit intention by the use of hidden Markov model and then we analyze the comment information of users' comment and checkin location through the topic model. And we make location prediction by analyzing topic similarity. The prediction range of the next azimuth location is gradually reduced and the accuracy is improved. Experiments on real data show the effectiveness of the proposed method.

A robust data-aided (DA) signal-to-noise ratio (SNR) estimation algorithm in the time domain is proposed in this paper, aiming at the volatile Doppler shift and carrier wave phase offset under dynamical scenarios for M-ary phase shift keying (MPSK) over the flat-fading complex channel. The proposed algorithm exploits data aided, delay conjugate multiplies the received signal, converts Doppler shift into fixed phase factors, and overcomes the impacts of Doppler shift and carrier wave phase offset. Furthermore, the impact of noise is analyzed and simulation results show that, compared with algorithms based on the spectrum analysis (FFT), the proposed algorithm is superior in the performance, especially in the estimation accuracy under low SNR scenarios and has low complexity.

This paper proposes an optimal non-cooperative power allocation game scheme for multi-user multiple-input multiple-output (MU-MIMO) with signal to leakage and noise ratio (SLNR) precoding. The proposed game scheme sets the value of per user SLNR and allocated power as reference for punishment price. Considering the effect of channel correlation and channel estimation error, an alternative robust power allocation scheme is presented based on the game model for per user in order to guarantee the desired QoS of the users and achieve Nash Equilibrium (NE). Simulation results show that both the schemes considerably improve the average bit error rate performance and obtain excellent sum capacity performance than other schemes in the presence of channel correlation and incomplete channel state information.