In this article, the Bayesian estimator and detector are proposed in the scenario of massive communication. The ultra massive multiple-input-multiple-output (MIMO) is established at the base station (BS), which is communicated with a huge number of online devices in the near field. In order to estimate the uplink channel responses, the novel nonorthogonal pilot sequences are designed and the principle of turbo decoding is applied. Then, the sparse estimation of extra large-scale channel state information (CSI) is performed depending on the extrinsic information transferring in the spatial domain and angular domain. Besides, the mixed analog-to-digital converter (ADC) architecture is considered to accomplish the linear and nonlinear measurements. Based on this framework, the tradeoff between the system performance and hardware overhead can be achieved. Additionally, a submodule-based segmentation technique is addressed to eliminate the energy spreading phenomenon caused by the near filed effects of the ultra massive MIMO. Specifically, we also analyze the theoretical statistical result of sparse channel estimation and device activity detection using the state evolution method. Furthermore, several engineering implementation strategies are provided to enhance the efficiency improvements in the practical system of massive communication. Numerical simulation results demonstrate that the satisfactory performance of estimation/detection is beyond other methods in terms of hardware costs and computational complexity in the extra large Internet of Things (IoT) network.

Extremely large-scale arrays and high frequencies are vital technologies for enhancing the capacity in wireless communications. The employment of these technologies makes the near-field propagation become dominant, where the achievable rate is reduced due to the misfocus effect caused by the beam mismatch. To mitigate it, beamforming schemes assuming spherical wavefront propagation must be investigated. However, the integration of angle and distance information in the beam domain, alongside the impacts of molecular absorption and spherical wave reflection coefficients, has been scarcely explored. We derive the expression of the molecular absorption at high frequencies and formulate the reflection coefficient expression under the spherical wave assumption, and embed them into the design of the beamforming. We then analyze these characteristics and propose a near-field beamforming scheme utilizing the Gauss-Legendre quadrature and design a minimum difference mapping strategy for phase mapping. Based on this scheme, we propose two beamforming algorithms for line-of-sight and non-line-of-sight scenarios, respectively. Numerical results demonstrate that the proposed algorithms are robust against the beam misfocus effect and achieve a higher achievable transmission rate.

Extremely large antenna array (ELAA) is able to significantly improve the spectral efficiency, so it is regarded as one of the most important technologies for the next-generation networks. However, larger antenna aperture and higher frequency make the Rayleigh distances dramatically increased, so in sixth-generation (6G) networks, more and more communication scenarios will take place in the near-field region. Different from traditional far-field communication, electromagnetic waves transmitted in the near-field communication is widely considered to be spherical rather than planar, so techniques designed for far-field scenarios are no longer applicable. In this paper, we study the near-field communication scenario in which the base station is equipped with a cylindrical antenna array (CLA). Specifically, by exploiting the geometrical relationship between CLA elements and the near-field user, codebook design for beamforming in near-field CLA systems is studied for the first time. We first derive the beamforming gain in the elevation angle domain, the azimuth angle domain and the distance domain respectively. Then a 3-D near-field CLA codebook is proposed to make beamforming more effectively in near-field CLA systems. We obtain the sampling method in each domain by controlling the correlation between different codewords. Simulation results prove the effectiveness of the proposed codebook.

Abstract This paper proposes a specific algebraic structure and demonstrates its nature as an extension field, enabling the construction of Golomb Costas (GC) arrays. It provides detailed instructions and examples for constructing GC arrays using this extension field, along with a corresponding flowchart. Additionally, the paper conducts a thorough analysis, incorporating calculations and comparisons, to evaluate the autocorrelation of a GC array derived from the extension field compared to that of a diagonal frequency hopping array. The analysis reveals the superior autocorrelation properties of GC arrays based on the extension field. Furthermore, the paper establishes a mathematical model for the signal coded by the frequency hopping array and subsequently simulates and compares the ambiguity function of the signal coded by a GC array with that of a signal coded by a diagonal frequency hopping array. This comparison underscores the thumbtack ambiguity function of frequency hopping signal coded by a GC array. Moreover, the paper thoroughly investigates the relationship between the correlation function of GC arrays and the roots of an algebraic equation in a finite field, and strictly proves the ideal autocorrelation properties of Golomb Costas arrays.

Abstract In order to balance accuracy and real‐time performance in semantic segmentation, this paper proposes a real‐time semantic segmentation algorithm model based on attention mechanism and multi‐branch feature fusion using Fast convolutional neural network model (Fast‐SCNN). In this method, the spatial detail feature enhancement branch is introduced to enhance spatial detail features firstly. Then, through rational design of fusion module, the feature information of each branch is optimized to achieve better fusion of deep and shallow features. At the end of the feature fusion module, an adaptive feature enhancement focus module is introduced to capture the interdependence between remote pixels. The experimental results show that the proposed algorithm achieves 71.55% segmentation accuracy on Cityscapes dataset, the reasoning speed FPS is 97.6 frames/s, and the number of parameters is 1.39 M, which verifies the effectiveness of the network model constructed by the algorithm. Code is available at https://github.com/ccchhheeennn/model .

Extremely large antenna array (ELAA) is regarded as one of the most crucial technologies for the next-generation communications due to its ability to significantly improve spectral efficiency. However, larger antenna aperture and higher frequency make the Rayleigh distances dramatically increased, resulting in more and more communications taking place in the near-field region. Different from traditional far-field communications, near-field communications are widely considered to be spherical wavefront-based rather than planar wavefront based, thus techniques designed for far-field scenarios might be no longer applicable. In this paper, we study the near-field communication system with an extremely large cylindrical antenna array (CLA). Under such a setup, we study the near-field beamforming, exploiting the geometrical relationship between CLA and user with the spherical-wavefront model. Specifically, we analyze the beamforming gain in the elevation angle, azimuth angle domain and distance domains, respectively. We then study the beam focusing properties in near-field CLA systems, namely the asymptotic orthogonality and the depth of focused beams. Moreover, a three-dimensional (3-D) near-field CLA codebook is proposed to make beam focusing more effective. Simulation results demonstrate that the proposed near-field codebook can effectively focus the beam to a certain location and thus improve the system achievable rate.

Integrated sensing and communication (ISAC) has been seen as a promising technology to satisfy the dual requirements of communication and sensing for the emerging applications in the next-generation wireless networks. In this paper, we research one down-link multi-cell orthogonal frequency division multiple access (OFDMA) ISAC system, in which a group of collaborative ISAC base stations send signals to their corresponding communication users, and concurrently work with multiple sensing receivers to estimate locations of multiple targets. Specifically, we investigate the joint sub-channel assignment and power allocation for users and targets to maximize the sum-rate, while ensuring the minimal signal-to-interference-plus-noise ratio (SINR) constraint for each user and the maximal Cramer-Rao lower bound (CRLB) requirement for each target. We propose a deep reinforcement learning (DRL) approach to address the above sub-channel assignment and power allocation problems. In our approach, we adopt the dueling deep Q network (DDQN) and the deep deterministic policy gradient (DDPG) network to output the sub-channel assignment policy and power allocation policy separately. Simulation results aim to prove the effectiveness of our proposed algorithm.

We propose a learned factor graph based on convolutional neural network (CNN) and Bi-directional Long Short Term Memory (BiLSTM) to realize signal detection under the scenario of no channel model. It can solve the inevitable over-reliance on channel state information (CSI) of model-based signal detection methods and avoid the shortcomings of large training scale of general data-driven methods by using relatively small training samples. The proposed method uses a network of CNN-BiLSTM structure with strong learning capabilities to determine the statistical relationship of the channel model which is what traditional model-based methods rely on. Based on above, the parameter estimation (Gaussian mixture model considering Akaike information criterion) and non-parametric estimation (adaptive kernel density) are adopted to learn a factor node together. The simulations show that, the proposed method can guarantee the accuracy of signal detection and robustness to the training of imperfect CSI.

In this paper, a model-driven signal detection method with deep transfer learning (DTL) is proposed for downlink multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) systems. Specifically, we first introduce some learnable parameters to an unfolded iterative algorithm for MIMO detection and improve it through a preconditioned process to speed up its convergence. Then we combine this modified algorithm with the successive interference cancellation (SIC) structure in NOMA detection to propose our learned preconditioned conjugate gradient descent network with SIC (LPCG-SIC). Furthermore, to improve the reusability of the trained network, a DTL-based detection algorithm and three model-driven transfer strategies are proposed for our LPCG-SIC detector. Simulation results show that the proposed detection network outperforms conventional detectors, and the transfer strategies can obtain significant performance gain compared to no-transfer methods.

In this paper, we study joint beamforming and resource allocation in downlink multi-cell orthogonal frequency division multiple access (OFDMA) systems. We design a multi-agent deep Q-network (MADQN) algorithm to solve this problem. Furthermore, in order to improve the adaptability of neural networks for different wireless environment, we propose a transfer learning framework based on MADQN called TL-MADQN to dynamically output optimal beamforming and resource allocation policy. Finally, we adjust the allocation policy to maximize the sum-rate of all users by updating the weights of each neural network. Simulation results illustrate that the proposed TL-MADQN algorithm has higher sum-rate and faster convergence speed compared with the baseline algorithms.

In order to reduce the consumption cost for successive interference cancellation in non-orthogonal multiple access(NOMA), we propose a resource allocation scheme that involves both orthogonal multiple access and NOMA technologies. The scheme uses deep learning to choose the appropriate access according to the communication environment. Moreover, the scheme jointly allocates subcarrier and power resources for users by utilizing a deep Q network and a multi-agent deep deterministic policy gradient network. Meanwhile, an adaptive mechanism combining online learning and offline learning is introduced into allocation scheme to flexibly adapt to the communication environment. Results show that the proposed scheme can achieve better system performance in sum-rate. In order to better cope with changes in the environment and make the resource allocation strategy more robust, we propose a novel resource allocation algorithm combining transfer learning and deep reinforcement learning. The algorithm can effectively improve the model convergence speed when changing the communication environment. Furthermore, the algorithm allows us to transfer the subcarrier allocation network and the power allocation network simultaneously or separately depending on the environment.

For a multi-cell OFDM downlink network, a basic problem is to perform resource allocation to maximize the spectral efficiency (SE). Doppler shift, however, leads to a loss of subcarrier orthogonality, resulting in inter-carrier interference (ICI), especially in a high speed environment. In this paper, we solve the resource allocation problem by considering ICI caused by Doppler spread and imperfect channel state information (CSI) caused by estimation errors, quantization errors and feedback delay. However, the resultant resource allocation algorithm is so complicated that it may not be applicable to the wireless communications environment under high mobility since it may change rapidly and therefore needs real-time computation. As such we propose a deep neural network (DNN) approach to approximate the resource allocation algorithm, which greatly reduces the computation time while achieving very good prediction accuracy. Simulation results verify the influence of Doppler shift on the SE performance and the effectiveness of DNNs in terms of computing time.

This paper proposes a deep learning-based receiver scheme with soft information for uplink multiple-input single-output (MISO) non-orthogonal multiple access (NOMA) systems, named by DLSI. In the proposed DLSI, we first perform QL-decomposition for channel matrix and iteratively construct the solution of the objective function for signal detection. Then deep neural networks (DNNs) are used to realize iteration steps and restore the symbols of the transmitted signals one by one. After all symbols of a user are detected, the successive interference cancellation (SIC) algorithm is used to detect the symbols of the next user. The output of each DNN is added with a soft decision layer, and the soft information will be input to the next DNN to improve the accuracy of training. Soft information contains more signal knowledge than hard decision, so it is also used in the SIC step, which reduces error propagation to a certain extent. Simulation results show that the performance of the DLSI is better than other deep learning methods.

Non-orthogonal multiple access (NOMA) has been recently considered in millimeter-wave (mmWave) massive MIMO systems to further enhance the spectrum efficiency. Massive connectivity and low latency are two important challenges for the Internet of Things (IoT) to achieve the quality of service provisions required by the numerous devices. Motivated by these challenges, we propose a power domain mmWave NOMA scheme based on user clustering. In particular, considering the quality of service (QoS) requirements, the machine type communication (MTC) devices are assigned to different ranks in the NOMA cluster, where they are transmitted through the same frequency resource. In this paper, investigate the power allocation problem as a weighted sum rate maximization problem. To solve this non-convex problem with high-dimensional variables, we transform the problem into a convex form by introducing two sets of auxiliary variables. In addition, we propose an iterative algorithm to obtain the optimal solution of power allocation by updating the weight factors and the auxiliary variables. Finally, we give the simulation results to verify the effectiveness of our scheme.

Non-orthogonal multiple access (NOMA) technology can meet user access requirements and improve system capacity. In this paper, we investigate the joint subcarrier assignment and power allocation problem in an uplink multi-cell NOMA system to maximize the energy efficiency (EE) while ensuring the minimum data rate of all users. We propose a multi-agent deep reinforcement learning (MADRL) method with centralized training and distributed execution to solve this dynamic optimization problem. In our method, we design a deep q-network (DQN) with parameter sharing to generate the subcarrier assignment policy, and use multi-agent deep deterministic policy gradient (MADDPG) network for power allocation of NOMA user. Finally, we adjust the entire resource allocation policy by updating the parameters of neural networks according to the reward. The simulation shows that our method has better and more stable sum EE than centralized and distributed methods.

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

Abstract Non‐orthogonal multiple access (NOMA) has attracted great attention due to its potential of providing high spectral efficiency and massive connectivity. Combining it with multiple‐input multiple‐output (MIMO) technology can further improve the spectrum efficiency. In this paper, the power allocation problem in downlink multi‐cluster MIMO‐NOMA systems is investigated for maximizing the fairness utility function. First, a long‐term fairness function is considered and the optimization problem is formulated as a weighted sum‐rate maximization problem. The problem is transformed into a convex form by introducing two sets of auxiliary variables, and propose an iterative algorithm to update the weight factors and the auxiliary variables. Then, an instantaneous fairness is considered and the optimization problem is formulated as a minimum data‐rate maximization problem. It is transfiormed into a one‐dimensional optimization problem based on an iterative algorithm and a closed‐form power allocation expression is deduced. Simulation results illustrate that the proposed two fairness power allocation schemes have better performance of edge‐user rate than the comparable schemes.

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

In this paper, we introduce a full‐duplex backscatter‐assisted wireless powered communication network (FDBA‐WPCN) with a full‐duplex access point (FAP) and multiple energy harvesting wireless devices (WDs). The communication mode is a combination of backscatter communication (BC) and harvest‐then‐transmit (HTT). The entire time period of network is divided into energy harvesting/backscattering (EHB) period and information transmission (IT) period. In the EHB period, each WD either reflects information to the FAP by backscatter or harvests energy to prepare for the IT period. In the IT period, the WDs use their harvested energy to transmit information to FAP in time division multiple access (TDMA). However, under the setting, WDs with different distances from FAP will encounter unfairness in throughput due to the round‐trip path loss in backscatter and the doubly near‐far problem in HTT. To overcome the drawback, an optimization problem is considered to maximize the sum throughput under the condition of ensuring throughput fairness. By using convex optimization techniques, we obtain the optimal time allocation and the maximum same throughput of each WD. Comparing to the other two benchmark schemes, the simulation results prove the superiority of our proposed method.

Considering a multi-cell OFDM downlink network, a basic problem is to perform resource allocation to maximize the spectral efficiency (SE). In this paper, we divide it into a user scheduling subproblem and a power allocation subprolem, and then adopt a resource allocation algorithm based on imperfect channel state information (CSI). Universal frequency reuse is considered, and the cochannel interference is dealt with via the cooperation of multiple base stations (BSs) sharing CSI but not user data. Since the wireless communication environment may change rapidly and need real-time computation, we then propose a deep neural network (DNN) approach to approximate the resource allocation algorithm, which greatly reduces the computation time and is capable of ”on-the-fly” adaptation to a time-varying environment. Simulation results verify the effectiveness of the DNN implementation, especially when the number of cells and subcarriers is large.

Nonorthogonal multiple access (NOMA) is one of the promising technologies to meet the huge access demand and high data-rate requirements of the next-generation networks. In this article, we investigate the joint subchannel assignment and power allocation problem in an uplink multiuser NOMA system to maximize the energy efficiency (EE). Different from conventional model-based resource allocation methods, we propose three deep-reinforcement-learning (DRL)-based frameworks to solve this nonconvex optimization problem, referred to as the discrete DRL-based resource allocation (DDRA) framework, continuous DRL-based resource allocation (CDRA) framework, and joint DRL and optimization resource allocation (DORA) framework. Specifically, for the DDRA framework, a multi-DQN-based network is designed to dynamically allocate resources discretely, which can reduce the output dimension and improve the learning efficiency. To overcome the loss of power discretization in DDRA, a joint DQN and deep deterministic policy-gradient (DDPG)-based network (CDRA framework) is designed to generate the resource allocation policy. The DORA framework is then proposed as a performance boundary. Finally, an event-triggered learning method is combined with all three frameworks to further reduce the computational consumption. The numerical results show that the proposed frameworks can improve the EE performance of the uplink NOMA system and reduce the computation time.

Mobility and green are of great significance to develop in the future wireless communications. In this paper, a joint transmission mode selection and power optimization scheme is researched to maximize the energy efficiency (EE) for distributed antenna system (DAS) in high-speed railway (HSR) communications. This work can be divided into two aspects: power optimization and transmission mode selection. For the power optimization, we first formulate a non-convex optimization problem and convert it into an equivalent convex form. Then, the optimization problem is solved by Lagrange method. With regard to the transmission mode selection, it can be switched between multiple-input multiple-output (MIMO) and single-input multiple-output (SIMO) freely, and the transmission mode with higher EE is selected to transmit signals. Simulation results show that our proposed scheme outperforms that without transmission mode selection, and it can significantly improve the system EE compared with the scheme without power optimization.

In this paper, we investigate a power allocation scheme in downlink multi-carrier non-orthogonal multiple access (MC-NOMA) systems for maximizing weighted sum-rate. Taking user-priority into account, we add the weighting factors into the formulated optimization problem. Firstly, we give sufficient and necessary concavity conditions that should be satisfied by the proposed weighted sum-rate maximization problem. Then, for more generally non-concave case, we use a first order approximation to convert the optimization problem and provide an iterative power allocation algorithm to find the globally optimal solution. Simulation results show that our proposed algorithm is superior to orthogonal frequency division multiple access (OFDMA) scheme and average power allocation scheme.

Heterogeneous cellular networks (HetNets) are to be deployed for future wireless communication to meet the ever-increasing mobile traffic demand. However, the dense and random deployment of small cells and their uncoordinated operation raise important concerns about various costs issues, among which notably is energy efficiency. Base station (BS) cooperation is set to play a key role in managing interference in HetNets. In this paper, we consider BS cooperation in the downlink HetNets where BSs from different tiers within the respective cooperative clusters jointly transmit the same data to a typical user, and in particular focus on the optimization of the energy efficiency performance. First, based on a proposed clustering model, we derive the spectral efficiency using tools from stochastic geometry. Furthermore, we formulate a power minimization problem with a minimum spectral efficiency constraint and derive the optimal received signal strength (RSS) thresholds under certain approximation. Building upon these results, we could address the problem of how to design appropriate RSS thresholds, taking into account the tradeoff between spectral efficiency and energy efficiency. Simulations show that the proposed clustering model is more energy-saving than the geometric clustering model, and deploying a multitier HetNet is significantly more energy-saving compared to a macro-only network.

In this paper, a resource allocation algorithm for maximizing energy efficiency (EE) is studied in multi-cell orthogonal frequency division multiple access (OFDMA) wireless networks. The resource allocation is designed based on imperfect channel state information (CSI). We formulate the resource allocation problem as a mixed non-convex probabilistic optimization problem. The user scheduling, data rate adaptation and power allocation are jointly designed to maximize the system EE, under the maximum transmitted power constraint and the outage probability constraint. An iterative algorithm is proposed in which the EE keeps improving until algorithm convergence. In each iteration, the energy-efficient power allocation optimization problem is solved by a lower bound problem and a parameterized transformation. Numerical results illustrate the convergence and the effectiveness of the proposed algorithm.

Heterogeneous cellular networks (HetNets) are to be deployed for future wireless communication to meet the ever-increasing mobile traffic demand. However, the dense and random deployment of small cells and their uncoordinated operation raise important concerns about energy efficiency. In this paper, we consider the base station (BS) cooperation solution for improving energy efficiency of the HetNets where BSs from each tier within the cooperative cluster jointly transmit the same data to a typical user. Firstly, based on the proposed clustering model, we precisely derive the ergodic rate expression using tools from stochastic geometry. Furthermore, we formulate a power minimization problem with minimum ergodic rate constraint and derive a closed-form approximated result of the optimal cooperative radii. Building upon these results, we could effectively address the problem how to design appropriate cooperative radii, taking into account the trade-off of ergodic rate and energy efficiency. Simulation results also indicate that under the proposed clustering model, deploying a two-tier HetNet is more energy-saving compared to a macro-only network.

Coordinated multipoint has been widely introduced to enhance the capacity, especially that of users at cell edge. Recently energy efficient transmission techniques are increasingly important due to the increase of energy consumption in wireless communication systems. In this paper, an energy efficient cooperative transmission algorithm using coordinated beamforming is proposed for multi-cell MIMO networks. We formulate the problem as a non-convex optimization problem in a fractional form. Then we transform the problem into an equivalent form and propose an iterative algorithm to solve it. In each iteration, a simplified zero-forcing coordinated beamforming using beam tracing and an optimal power allocation algorithm for maximizing energy efficiency are derived. Simulation results demonstrate that the proposed algorithm has a better energy efficiency performance than the traditional capacity maximizing method. With the lower complexity, the proposed method using beam tracing approaches the energy efficiency performance of the subspace decomposition method in slowly varying channels.