Due to the availability of wide bandwidths in the frequency range 2 (FR2) band, sixth-generation (6G) networks can provide both radar and communication services using shared spectrum and hardware, reducing costs and enhancing efficiency via integrated sensing and communication (ISAC) systems. Motivated by the advantages of orthogonal time frequency space (OTFS) modulation in high-mobility scenarios, this paper proposes an iterative hybrid precoder design method and a radar tracking algorithm for OTFS-ISAC systems with aerial targets, i.e., drones. Information is sent to the ground user through communication links using the subarray hybrid precoder to balance radar and communication performance through a weighted summinimization framework. The cubature Kalman filter (CKF) is employed for radar prediction and tracking. Simulation results indicate that the proposed hybrid precoder design algorithm effectively balances radar and communication performance, while the CKF-based radar tracking method outperforms other nonlinear Kalman filters.

The growth of frequency bandwidths in the new generation of wireless networks gives rise to the multitude of wireless communication scenarios and highlights the challenges of generalized capability of the wireless communication system in different scenarios, especially the channel estimation module. In this paper, we propose a large model dubbed Conditional Latent Diffusion Channel Generation Model (C-LCGM) to learn the distributions of channel state information (CSI) in different wireless communication scenarios to form Bayesian Modeling based Channel Estimation Scheme (BMCE) for universal channel estimation. BMCE conducts universal channel estimation by generating reference CSIs from C-LCGM and mapping the reference CSIs to the optimal channel estimation neural network for each scenario. Specifically in C-LCGM, we propose to compress the CSIs into latent codes and design a conditional diffusion model to model the distribution of the latent codes given the large-scale parameters (LSP) of CSIs as the condition. Further in BMCE, we propose to deploy C-LCGM on the server center and design a hyper-network dubbed Parameters Generating Module (PGM) to map the generated CSIs of C-LCGM to the channel estimation networks for the base stations (BS) according to the reported LSPs. The design rationale and training loss of C-LCGM and BMCE are derived theoretically in this paper. We also conduct extensive simulations to verify the performance of C-LCGM and BMCE. The simulation results show that BMCE can achieve optimal channel estimation performance in different and novel scenarios with C-LCGM generating high-quality CSIs approximating the real CSIs in each scenario. Complexity analysis shows BMCE can fit the delay requirement of wireless communication systems.

Deep learning (DL)-based models have been widely applied in wireless communication systems with excellent performance. However, most of these models are task- and scenario-specific, exhibiting limited generalization and contributing to increasing complexity and overhead with their deployment in systems. Inspired by the emergent capabilities and strong generalization exhibited by large models (LMs), represented by large language models (LLMs), this paper analyzes the differences between existing DL-based wireless communication models and LLMs, proposing a framework for designing LMs tailored to wireless communications. Building upon this framework, we integrate channel-related tasks of the physical layer into a unified pre-training task, i.e., channel completion, and propose a pre-trained masked channel model (MCM) with different parameter scales ranging from 5 million to 1 billion (B), enabling simultaneous solving of channel state information (CSI) feedback, prediction, and estimation. Additionally, scaling laws on these downstream tasks are derived to guide the design and deployment of MCMs. The formulated scaling laws indicate that the proposed MCM with 1B parameter not only shows no sign of performance saturation on the pre-trained task but also has the potential to enhance performance at larger model sizes. Simulation results demonstrate that the proposed MCM outperforms the existing algorithms across various downstream tasks while exhibiting superior cross-task and cross-scenario generalization capabilities in both simulated and realistic scenarios.

Research on sixth-generation (6G) wireless networks has gained significant attention as wireless communications technologies advance. In the upcoming 6G era, artificial intelligence (AI) is expected to play a significant role in enhancing mobile communications. In particular, the application of AI techniques in channel estimation can enable accurate channel state information, even in dynamic scenarios. However, the limited computational resources in user equipment often prevent the deployment of complex algorithms, necessitating adaptive channel estimation solutions, balancing the accuracy and complexity dynamically. Conventionally, AI-based channel estimation algorithms rely on explicitly stacking deep learning (DL) layers/blocks, making adaptation challenging. This paper proposes an adaptive Implicit DL Channel Estimation Network (ICENet) that employs a lightweight, implicit network design to achieve dynamic adaptability. Numerical results show that our approach can achieve the trade-off between algorithm complexity and channel estimation accuracy by adapting based on channel quality. Additionally, it offers reduced memory cost compared to explicit layer/block-stacked networks while maintaining or surpassing their estimation accuracy. Furthermore, we analyze key factors influencing forward and backward propagations in ICENet and regularize the Jacobian matrix to ensure stable convergence during the training process.

The architectural design of the air interface plays a critical role in wireless communications, embedding crucial functionality to guarantee both efficiency and robustness. Physical layer algorithms often face performance challenges in real-world scenarios owing to the basic assumptions of Gaussian noise, channel model linearity, and functional separation. This paper explores intelligent air interface (IAI) algorithms for multiple-input multiple-output (MIMO) systems to overcome the limitations of these assumptions. The physical layer link is restructured as a composite of various functions and framed as a mathematical optimization problem aimed at maximizing transmission rates, solved through optimization sub-problems for each function using specialized neural networks. Additionally, this paper presents the intelligent modulation and demodulation network (IMD-Net) with an adaptive adjustment sub-network, joint channel feedback and prediction network (CFP-Net), and GEM-Net for joint channel estimation and signal detection, using an unfolded generalized expectation maximization algorithm. Simulation results indicate that the proposed algorithms surpass traditional linear methods and the independent deep learning (DL) based methods in various scenarios and configurations.

This paper investigates intelligent predictive beamforming design for simultaneous wireless information and power transfer-integrated sensing and communication (SWIPT-ISAC) systems for low-altitude economy wireless networks. Considering the downlink scenario where the base station aims to localize the moving targets/communication users and also transfer power to them, we formulate a weighted sum optimization problem to balance the trade-off between achievable communication rate and harvested energy, subject to sensing accuracy constraints defined by the Cramér–Rao lower bound. To address the non-convexity of the problem, we propose the Time-Spatial Fusion Network (TSFusionNet), an unsupervised deep learning (DL) framework that leverages multi-step historical channel state information for predictive beamforming design. TSFusionNet integrates convolutional and recurrent layers with a differential attention mechanism to capture spatial-temporal dependencies and mitigate non-stationary channel dynamics. We introduce a dynamic penalty-based loss function to enforce sensing constraints during training. Simulation results show that by adjusting the weight factor, the proposed method achieves a trade-off between rate and energy while meeting sensing accuracy requirements. Moreover, it significantly reduces computational complexity by up to approximately 96.8% in parameters and 81.5% in FLOPs, compared to existing DL frameworks.

The channel estimation and signal detection are key issues in the Multi-Input Multi-Output and Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system. However, there exist severe impacts of phase noise (PN) on the estimations with the application of higher frequency in 5th Generation New Radio (5G-NR). In this paper, the joint channel estimation and signal detection (JCESD) method based on the maximum a posteriori (MAP) criterion under the assumption of Wiener process for PN is proposed in MIMO-OFDM system, which is called as the JCESD-PN-MAP method. Firstly, the MAP criterion is derived based on Bayesian theories and the structures of matrices in MAP criterion are analyzed to simplify the optimizations. Secondly, the optimizations for PN of receiving and transmitting antennas are translated into solving a tridiagonal linear equation and a sparse linear equation, respectively, which are optimized by the Gaussian elimination (GE) method with low computation complexity. To further reduce the computational complexity, the latter is solved by the alternating direction method of multipliers (ADMM) method. Thirdly, the optimizations for channel responses and transmitted signals are translated into solving two block diagonal linear equations, which are solved by calculating the inverse matrix with low computation complexity. The numerical results and complexity analysis confirm the effectiveness of our proposed method in terms of the accuracy and computation complexity.

On the road to 6G, the growing number of antennas and mobility-related applications emphasize the urgency of addressing the channel aging issue. Traditional channel prediction methods are no longer valid due to simplified assumptions. Deep learning (DL)-based predictors, even with attractive performance improvements, generally lack the utilization of extra correlations and flexible inference with accuracy-efficiency trade-off. In this paper, by representing the topology structure of nearby users (UEs) as a graph, a multi-user channel prediction algorithm is proposed for learnable UE correlation extraction, called LUCE, to improve prediction performance. Instead of simple summation-based fusion, LUCE introduces a predefined geographic embedding and a learnable embedding to offset the position information of the cross-attention (CA) to learn and interact UE features on the graph automatically. Furthermore, a lightweight LUCE is proposed to leverage the homogeneity of CSIs by sharing sub-networks. In addition, a variable-depth learning architecture is proposed, called adaptive LUCE (AdaLUCE), and its number of blocks can be dynamically adjusted for each input by tuning a desired threshold. In particular, AdaLUCE utilizes a hierarchical triple residual architecture to promote its training efficacy and produce predictions at its internal blocks without increasing complexity, and adopts a fitting inspired criterion (FIC) to make real-time decisions for adaptive inference. In total, AdaLUCE is optimized by the weighted sum of multiple loss functions, and a multi-step training scheme is presented. We show that AdaLUCE preserves and releases computing resources for various speeds in sample-wise, improving both prediction accuracy and inference efficiency.

In the era of upcoming sixth-generation (6G) wireless systems, the intelligent integrated sensing and communication (ISAC) paradigm has emerged as a pivotal research domain, catalyzing advancement across a wide range of applications. In this paper, we investigate an ISAC-assisted anti-eavesdropping communication system, where an ISAC ground base station exploits its radar function to track potential aerial eavesdroppers and implements predictive beamforming to ensure secure communications with multiple ground users. We harness the powerful capability of the Transformer for time series prediction to establish a novel deep neural network, termed the ISACformer, for constructing predictive beamformers via exploiting previously estimated channel state information in an unsupervised manner. By eliminating the need for explicit channel prediction, our proposed framework effectively reduces signaling overhead and complexity. In addition, by formulating a weighted objective function, our design meticulously balances the trade-off between the ergodic achievable worst-case secrecy rate for ground users and the ergodic Cramér-Rao lower bound for the kinematic parameters of potential aerial eavesdroppers. Simulation results demonstrate that the proposed ISACformer can deliver the desired predictive beamforming for harmonizing radar and communication functionalities effectively. Moreover, our method achieves performance approaching the theoretical upper bound obtained by ignoring multi-user interference, thereby highlighting the robustness of the proposed approach.

For the signal detection problem in a multiple-input multiple-output (MIMO) system, it has been demonstrated that deep learning can improve the detection accuracy and/or reduce the complexity of traditional detection algorithms under the assumption that the channel scenario remains the same in training and test. However, this assumption is not appropriate since the communication environment in practice is constantly changing. As a result, the performance of deep-learning-based detection methods will degrade significantly due to their lack of generalization ability. To address this problem, we model the channel scenario adaptation problem as a multi-scenario learning task and propose two schemes to improve the adaptability of model-driven detection network to cross-channel scenarios. For the case where the test channel scenario has been seen in the training stage, a hypernetwork is introduced to the deep-learning-based iterative soft thresholding algorithm (DISTA) to generate a personalized set of network parameters for each channel scenario, which is named hyperDISTA. Experimental results show that hyperDISTA trained in multiple channel scenarios can not only adapt to each seen channel scenario but also outperform existing deep-learning-based detectors trained in the single channel scenario at high signal-to-noise ratio (SNR) regimes. For the case where the test channel scenario is unseen in the training stage, we propose to retrain the hyperDISTA in a semi-supervised manner. Experimental results show that the retrained hyperDISTA achieves a performance that is comparable to that of the maximum likelihood detection algorithm (MLD).

Solving constrained nonlinear programs (NLPs) is of great importance in various domains such as power systems, robotics, and wireless communication networks. One widely used approach for addressing NLPs is the interior point method (IPM). The most computationally expensive procedure in IPMs is to solve systems of linear equations via matrix factorization. Recently, machine learning techniques have been adopted to expedite classic optimization algorithms. In this work, we propose using Long Short-Term Memory (LSTM) neural networks to approximate the solution of linear systems and integrate this approximating step into an IPM. The resulting approximate NLP solution is then utilized to warm-start an interior point solver. Experiments on various types of NLPs, including Quadratic Programs and Quadratically Constrained Quadratic Programs, show that our approach can significantly accelerate NLP solving, reducing iterations by up to 60% and solution time by up to 70% compared to the default solver.

Abstract Based on empirical data of an orthogonal frequency division multiplexing system in realistic environments of next‐generation cellular networks, a new analytical model of phase noise and numerical characteristics of the common phase error and intercarrier interference are derived. Applying an asymptotic theory of probability, analytical expressions are present to approximate the mean vector and the covariance matrix of the intercarrier interference. The approximation expression of the covariance matrix is accurate enough and only has three parameters. When applied to estimate original symbols based on additive white Gaussian noise channel, a Gibbs sampler performs better than the current estimation algorithm following Weiner process phase noise.

The growth of frequency bandwidths and applications with the forthcoming generations of wireless networks will give rise to a multitude of wireless transmission scenarios, topologies and channel structures. In this work, we go beyond existing learning-based channel estimation methods tailored for specific scenarios, to develop an adaptive learning-based channel state information (CSI) estimation approach. We offer the adaptivity in the learning approach through extracting the scenario embeddings of CSI and adjusting the channel estimation method with the extracted information automatically in each scenario. Specifically, Learning-Based Scenario-Adaptive Channel Estimation Algorithm (LACE) is designed. LACE is based on a Scenario-Aware Hyper-Network (SAH-Net) that incorporates the embedding loss to make the Convolutional Neural Network (CNN) based encoder learn to extract the effective scenario embeddings from the time-space two dimensional features of the CSI. The extracted embeddings are utilized by a Multi-Layer Perceptron (MLP) based tuning module to tune the parameters of the channel estimation method. Our learning design is complemented with analysis to verify that the theoretical performance of LACE is strictly superior to that of the mix-training method, which involves conventionally training the deep network-based channel estimation method using samples from all scenarios. Our results show that the performance of LACE trained in finite scenarios is comparable to that of the deep network-based channel estimation method trained in each scenario, while having lower complexity. Further more, the performance of LACE trained in infinite scenarios is demonstrated to be superior to that of the mix-training method in all test scenarios.

This paper works on the detection of physical random access channel (NPRACH) in Narrowband Internet of Things (NB-IoT) system. The frequency hopping preamble design and increasing number of IoT terminals lead to inter-cell interference among different cells, resulting in inevitable increase of false alarm rate. Due to the ambiguity between preamble and interference, it is a great challenge for NPRACH detection methods to achieve low false alarm rate when having strong interference. In this paper, we analyze the difference between preamble and interference in the propagation environments of NPRACH signals in the 2-dimensional Fast Fourier Transformation (2-D FFT) domain. Then we propose a deep learning-based NPRACH detection method, dubbed Mask Assisted Anti-Interference Universal Detection Scheme (MIUS), in the 2-D FFT domain for preamble detection with inter-cell interference in different repetition cases. In the proposed MIUS, the Mask-ResNet Block is designed as a building block to extract features distinguishing the preamble and interference based on masking operations. Our proposed MIUS utilizes the Mask-ResNet Block in a separate manner to detect the preambles in sequential repetitions across different repetition cases. Simulation results show that MIUS can simultaneously maintain the low false alarm rate and achieve high detection accuracy in low Signal to Interference and Noise Ratio (SINR) regime in all repetition cases.

Channel state information (CSI) plays a critical role in achieving the potential benefits of massive multiple input multiple output (MIMO) systems. In frequency division duplex (FDD) massive MIMO systems, the base station (BS) relies on sustained and accurate CSI feedback from users. However, due to the large number of antennas and users being served in massive MIMO systems, feedback overhead can become a bottleneck. In this paper, we propose a model-driven deep learning method for CSI feedback, called learnable optimization and regularization algorithm (LORA). Instead of using$l_{1}$-norm as the regularization term, LORA introduces a learnable regularization module that adapts to characteristics of CSI automatically. The conventional Iterative Shrinkage-Thresholding Algorithm (ISTA) is unfolded into a neural network, which can learn both the optimization process and the regularization term by end-to-end training. We show that LORA improves the CSI feedback accuracy and speed. Besides, a novel learnable quantization method and the corresponding training scheme are proposed, and it is shown that LORA can operate successfully at different bit rates, providing flexibility in terms of the CSI feedback overhead. Various realistic scenarios are considered to demonstrate the effectiveness and robustness of LORA through numerical simulations.

High peak-to-power ratio (PAPR) is a significant drawback of the orthogonal frequency division multiplexing (OFDM) systems. The iterative clipping and filtering (ICF) method has been employed to reduce PAPR, which is effective but leads to nonlinear distortion in the systems. The modified iterative receiver (MIR) is a useful method to deal with the nonlinear distortion. However, the MIR suffers from high computational complexity with the increasing iterations. In order to improve the efficiency of receiver, a dynamic modeling iterative receiver (DMIR) is proposed, which employs the dynamic hybrid evolutionary modeling algorithm (DHEMA) to modify the formulas for iterations instead of the original linear ones of MIR. Furthermore, an improved segmentation adjusted dynamic modeling iterative receiver (SA-DMIR) is proposed combining the DMIR with a module of segmentation adjustment, which processes the peaks differently from other parts of signals for precise recovery. The simulation results demonstrate the superiorities of the proposed DMIR and SA-DMIR in terms of the computation consumption and accuracy.

Accurate channel state information (CSI) is critical for achieving high performance in massive multiple input multiple output (MIMO) systems. While existing deep learning (DL) based methods have achieved notable success for CSI feedback in the frequency division duplex (FDD) mode, they typically learn one set of neural network (NN) parameters for all CSI. However, only one set of parameters restricts the representation power of the NN, resulting in the limited performance. In addition, the channel estimation error is usually considered with discrete levels among the researches of CSI feedback, which limits the performance when channel estimation errors are successive. To address these issues, we propose a model-driven DL method with sample-relevant dynamic parameters using hyper-networks and unfolding. The proposed method can generate the parameters of the task network distinctly for each CSI by a hyper-network, which improves the representation power and recovery performance of the task network. Additionally, instead of assuming each CSI has the same level of channel estimation error, the proposed method automatically adjusts task network parameters to account for different levels of channel estimation error, resulting in significant performance gains. The numerical experiments demonstrate the superiority of the proposed method in terms of performance and robustness.

Signal detection plays a significant role at the receiver of current multiple-input multiple-output (MIMO) communication systems. In this paper, we propose a deep learning aided Douglas-Rachford network (DRNet) for MIMO signal detection. Specifically, DRNet is developed based on Douglas-Rachford splitting approach, which is a classic method for non-smooth convex signal recovery. It is known that the transmitted signal in MIMO systems is drawn from a discrete quadrature amplitude modulation (QAM) constellation and ordinary least square (OLS), namely zero-forcing (ZF), performs poorly in small size MIMO systems. In order to obtain better performance, we design an implicit penalty for the unknown transmitted signal and use a deep neural network (DNN) to learn the corresponding proximal gradient of the penalty. Meanwhile, we vectorize the hyper-parameters in the Douglas-Rachford splitting approach and make them learnable. Simulation results show that the proposed DRNet outperforms the original Douglas-Rachford splitting approach and is robust to varying signal-to-noise ratio (SNR). Moreover, compared with existing model-driven deep MIMO detectors, DRNet also has lower bit-error-rate (BER).

In this paper, we develop a dynamic detection network (DDNet) based detector for multiple-input multiple-output (MIMO) systems. By constructing an improved DetNet (IDetNet) detector and the OAMPNet detector as two independent network branches, the DDNet detector performs sample-wise dynamic routing to adaptively select a better one between the IDetNet and the OAMPNet detectors for every samples under different system conditions. To avoid the prohibitive transmission overhead of dataset collection in centralized learning (CL), we propose the federated averaging (FedAve)-DDNet detector, where all raw data are kept at local clients and only locally trained model parameters are transmitted to the central server for aggregation. To further reduce the transmission overhead, we develop the federated gradient sparsification (FedGS)-DDNet detector by randomly sampling gradients with elaborately calculated probability when uploading gradients to the central server. Based on simulation results, the proposed DDNet detector consistently outperforms other detectors under all system conditions thanks to the sample-wise dynamic routing. Moreover, the federated DDNet detectors, especially the FedGS-DDNet detector, can reduce the transmission overhead by at least 25.7% while maintaining satisfactory detection accuracy.

This paper proposes a unified mathematical frame-work for intelligent transceiver design. It mainly includes three most important modules in the communication system, namely, beamforming, channel estimation and Multiple-Input Multiple-Output (MIMO) detection. Firstly, the mathematical correlation behind different algorithms of a single communication module is analyzed, the purpose is to realize the unification between different algorithms of a specific communication module. Next, a cross-module unified mathematical framework is proposed. Finally, an AI architecture for the unified mathematical framework is designed, which shows that the intelligent transceiver based on the mathematical framework has higher performance.

Achieving adequate precision in deep learning based communications often requires large network architectures, which results into unacceptable time delay and power consumption. This paper introduces the dynamic neural network (DyNN) into the design of wireless communications systems. DyNN allocates different samples with computation resources on demand by preforming dynamic inferences, thereby reducing the redundant computational cost and enhancing the network efficiency. We design a dynamic depth architecture that allows samples to adaptively skip layers with various dynamic strategies, from which we further develop aconfidence criterion baseddynamicimproved DetNet (CD-IDetNet) and apolicy network baseddynamicimproved DetNet (PD-IDetNet) for multiple-input multiple-output (MIMO) detection. Specifically, in CD-IDetNet, a confidence criterion is adopted to control samples exiting early, while in PD-IDetNet, policy networks are trained by reinforcement learning to selectively skip layers for varying samples. Simulation results demonstrate that CD-IDetNet and PD-IDetNet detectors can respectively reduce 17.4% and 31.1% computational costs while preserving the full accuracy of IDetNet. Desirable tradeoffs between accuracy and computational complexity can be further achieved by fine-tuning the hyper-parameters of CD-IDetNet and PD-IDetNet. Moreover, over-the-air (OTA) tests are conducted to validate the effectiveness of the proposed detectors in practical systems.

In massive multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, a challenging problem is how to predict channel state information (CSI) (i.e., channel prediction) accurately in mobility scenarios. However, a practical obstacle is caused by CSI non-stationary and nonlinear dynamics in temporal domain. In this paper, we propose a spatio-temporal neural network (STNN) to achieve better performance by carefully taking into account the spatio-temporal characteristics of CSI. Specifically, STNN uses its encoder and decoder modules to capture the spatial correlation and temporal dependence of CSI. Further, the differencing-attention module is designed to deal with the non-stationary and nonlinear temporal dynamics and realize adaptive feature refinement for more accurate multi-step prediction. Additionally, an advanced training scheme is adopted to reduce the discrepancy between STNN training and testing. Evaluated on a realistic channel model with enhanced mobility and spherical waves, experimental results show that STNN can effectively improve the accuracy of prediction and perform well with respect to different signal to noise ratios (SNRs). Visualization and testing for unit root illustrate STNN is able to learn CSI time-varying patterns by alleviating series non-stationarity.

Channel state information (CSI) estimation is one of the key techniques for improving the performance of wireless communication systems. Meanwhile, the fifth generation wireless communication systems require higher accuracy and lower latency for CSI estimation. In this paper, the methods of noise modeling and online learning are combined to improve the accuracy and reduce the latency. The complex noise environment (considering noise and interference together) is modeled as a specific mixture of Gaussian (MoG) distribution because of its widely approximation capability to any continuous distribution. The MoG CSI estimation (MoG-CE) model and expectation maximization (EM) algorithm are introduced as one of the baseline methods. Further, the parameters of the model can be updated in real time based on the prior knowledge of historical information. Therefore, the online MoG CSI estimation (O-MoG-CE) model and online MoG dynamic CSI estimation (O-MoG-D-CE) model are proposed for time-invariant and time-varying CSI estimations, respectively. The above models can not only self-adapt to various complex communication scenarios robustly but also achieve online and dynamic CSI estimation to improve the accuracy and reduce the latency significantly. In addition, the proposed models can be formulated as standard maximum a posteriori estimations and efficient online expectation maximization (OEM) algorithms are applied for the estimations in a pure machine learning fashion. Comparing with baseline methods, the simulation results demonstrate the superiority of the proposed methods in terms of the accuracy, latency and computation consumption.

In this paper, we study the channel state information (CSI) estimation by utilizing maximum entropy principle (MEP) and noise modeling method. The new model can not only represent the characters of the complex communication environment, but can also adjust itself according to the environment by using machine learning. In addition, a new iteration algorithm is presented to derive numerical results. Adaptive parameters learning and features choosing capability make the proposed method outperform the existing methods. The accuracy of estimation is verified by the Monte Carlo simulations.

This paper proposes a novel learning to learn method, called learning to learn iterative search algorithm (LISA), for signal detection in a multi-input multi-output (MIMO) system. The idea is to regard the signal detection problem as a decision making problem over tree. The goal is to learn the optimal decision policy. In LISA, deep neural networks are used as parameterized policy function. Through training, optimal parameters of the neural networks are learned and thus optimal policy can be approximated. Different neural network-based architectures are used for fixed and varying channel models, respectively. LISA provides soft decisions and does not require any information about the additive white Gaussian noise. Simulation results show that LISA 1) obtains near maximum likelihood detection performance in both fixed and varying channel models under QPSK modulation; 2) achieves significantly better bit error rate (BER) performance than classical detectors and recently proposed deep/machine learning based detectors at various modulations and signal to noise (SNR) ratios both under i.i.d and correlated Rayleigh fading channels in the simulation experiments; 3) is robust to MIMO detection problems with imperfect channel state information; and 4) generalizes very well against channel correlation and SNRs.

Channel estimation is the critical and fundamental problem in wireless communication techniques, however, the complexity environment, including interference and noise, post a fundamental limit on the accuracy of channel estimation on practical applications. Most existing channel estimation techniques are based on the simple assumption of Gaussian white noise, which makes the performance poorly within real communication environment. To address this problem, we propose a new channel estimation method by assuming the environment as Mixture of Gaussian (MoG) distributions and penalized MoG (PMoG) model by combining the penalized likelihood method with MoG distributions. This model is proposed by the first time in the research of wireless communication, and the superiority of this method lies on its approximation capability to wide range of scenarios of complex communication environments adaptively and analyzing the environment by learning the proper number of statistical components. Moreover, we design an Expectation Maximization (EM) algorithm to estimate the parameters of the PMoG model. The advantage of our method is demonstrated by simulation experiments.

In this paper, we investigate the energy harvesting (EH) technique and accordingly design transceivers for a K link multiple-input multiple-output interference channel. Each link consists of two full-duplex (FD) Internet of Things (IoT) nodes exchanging information simultaneously in a bi-directional communication channel. All the nodes suffer from interference, in particular strong self-interference and inter-node interference, due to operating in FD mode and simultaneous transmission at each link, respectively. Further, we divide the received signal at each node into two parts. While one part of the signal is used for information decoding, the other part is used for EH. We jointly design the transmit and receive beamforming vectors and receiver power splitting ratios by minimizing the total transmission power of the system, subject to both signal-to-interference-plus-noise ratio and EH threshold constraints. Furthermore, the case of multiple-input single-output interference channel is also included for the sake of comparison. We also revisit the above problems for the case when the available channel state information (CSI) at the transmitters is imperfect, where the errors of the CSI are assumed to be norm bounded. Simulation results show that the EH technique can harvest enough energy to support power consumption limited IoT devices by aiding in recharging their respective batteries.

In this work, the performance of a dual‐hop amplify‐and‐forward (AF) multi‐antenna relaying system over Rayleigh fading channels with random co‐channel interference (CCI) is investigated. Three receiving strategies such as the maximal‐ratio combining (MRC), zero‐forcing (ZF) and minimum mean square error (MMSE) are employed in the relay to mitigate the impact of CCI which follows a Poisson point process. In second hop, the relay forwards the signal to the destination by using maximum ratio transmission (MRT). Specifically, we derive the asymptotic expressions of the capacities for this system. The simulation and analytical results show that the MMSE/MRT scheme always provides significant improvement on capacity compared with MRC/MRT and ZF/MRT schemes. Furthermore, the MRC/MRT scheme gives almost the same performance as the MMSE/MRT scheme when the density of CCI sources is high.

In this paper, we analyse the performance of a millimeter wave (mmWave) cloud radio access network (CRAN), where remote radio heads (RRHs) are modelled as a homogeneous Poisson point process (PPP) and blockages are randomly distributed. In contrast to the previous works on CRAN that operate below 6GHz, we consider CRAN operating in mmWave range (30-300 GHz). Since blockages have a significant impact on mmWave communications, we adopt a distance-dependent line-of-sight (LOS) probability function and model the locations of the LOS and non-line-of-sight (NLOS) RRHs as two independent non-homogeneous PPP. The outage performance and ergodic capacity of the LOS and NLOS RRHs are analysed and compared. When the RRH with the best channel is selected for transmission, the expressions of outage probability and throughput are provided. The presented results show that due to the severe path loss in NLOS links, in low transmitted power regime, the best RRH (BR) is always LOS. However, in high transmitted power regime, NLOS RRHs can be BR.

In this paper, the performance of a cloud radio access network (CRAN) is analysed, which consists of multiple randomly distributed remote radio heads (RRHs) and a macro base station (MBS). Different from previous works on CRAN where Poisson Point Process (PPP) is used to model spatial distribution of RRHs, a more realistic Matern Hard-core point process (MHCPP) model is adopted in this work. To compare system performance of CRAN when different transmission strategies are used, two RRH selection schemes are adopted including 1) the best RRH selection (BRS) and 2) all RRHs participation (ARP). Considering downlink transmission, the outage probability and system throughput of CRAN are analytically characterized. The presented results demonstrate that compared to PPP model, the presence of hard-core distance will increase outage probability. Furthermore, the BRS scheme is more energy-efficient than the ARP scheme. Moreover, it is shown that the hard-core distance has a more significant impact on systems with higher intensity of PPP distributed candidate points and in large hard-core distance regime increasing the intensity of candidate points can only provide a small improvement in outage performance.

The potential benefits of deploying relays in outdoor millimeter-wave (mmWave) networks are investigated. We derive the coverage probability from sources to a typical destination for such systems aided by relays. The sources and the relays are modeled as independent homogeneous Poisson point processes. We present a relay modeling technique for mmWave networks considering blockages and compute the density of active relays that aid the transmission. Closed form expressions for end-to-end signal to noise ratio for two relay selection techniques, namely best path selection and best relay selection are derived. Finally, we analyze the coverage probability and transmission capacity of the network and validate them with simulation results. Our results show that the coverage probability and transmission capacity of mmWave systems, which are often affected by extensive blockages can be increased considerably with the aid of relays.

This paper studies the energy efficiency (EE) of the cloud radio access network (C-RAN), consisting of multiple remote radio heads (RRHs) equipped with electronically steerable parasitic array radiator (ESPAR) antennas, which provide multiple antenna functionality with a single radio frequency (RF) chain. An EE optimization problem is formulated to obtain the configuration of ESPAR and the closed-form expressions of the voltage feeding and the loadings are derived for signal transmission at each RRH. Specifically, we obtain the closed-form expressions for precoder and power allocation that are applicable not only for the ESPAR based system but also for standard MIMO antenna (SMA) system with multiple RF chains. It is shown that EA system can be configured with less complexity compared with SMA system in block fading channel. Furthermore, symbol error rate (SER) and EE performances are compared for EA and SMA based systems. It is shown that the system with EA provides better EE performance while providing similar SER performance. From our results, it is proved that EA system can provide better performance to satisfy the requirement of 5G wireless communication networks.

In this paper, we analyze the performance of a cloud radio access network (CRAN), consisting of multiple randomly distributed remote radio heads (RRHs) and a macro base station (MBS), each equipped with multiple antennas. To model the spatial distribution of RRHs and analyze its performance, we use stochastic geometry tools. In contrast to previous works on CRAN that consider Poisson Point Process (PPP) model for the spatial distribution of RRHs, we consider a more realistic Matérn hard-core point process (MHCPP) model that imposes a certain minimal distance (referred to as hard-core distance) between the two RRHs so that the RRHs are not too close to each other. To compare system performance of CRAN when different transmission strategies are used, three RRH selection schemes are adopted including 1) the best RRH selection (BRS); 2) all RRHs participation (ARP); and 3) nearest RRH selection (NRS). Considering downlink transmission, the ergodic capacity, outage probability, and system throughput of CRAN are analytically characterized for different RRH selection schemes. The presented results demonstrate that compared to PPP model, the increase in hard-core distance will result in a higher outage probability and cause a negative impact on ergodic capacity. Furthermore, when the same total transmit power is consumed, BRS scheme provides the best outage performance while ARP scheme is the best RRH selection scheme when the same transmit SNR at each RRH is assumed. Moreover, it is shown that the hard-core distance has a more significant impact on systems with higher intensity of PPP distributed candidate points and in large hard-core distance regime increasing the intensity of candidate points can only provide a small improvement in outage performance. We extend our work to multiuser case with zero-forcing (ZF) precoding where it is proven that the results in multiuser case reduce to the derived results in this work by substituting K=1 for single-user.

In this paper, we use stochastic geometry to characterize spatially distributed multi-antenna users within a cell that consists of a single multiple-input multiple-output (MIMO) base station (BS) equipped with a large antenna array. We also use large dimensional random matrix theory (RMT) to achieve deterministic approximations of the sum rate of this system. In particular, we consider the users inside the cell to follow a Poisson point process (PPP). The sum rate of this system is analyzed with respect to (i) the different number of antennas at the BS as well as (ii) the intensity of the users within the coverage area of the cell. We obtained closed-form approximations for the deterministic rate at low signal-to-noise ratio (SNR) and high SNR regimes, which have very low computational complexity. We also derive the deterministic rate corresponding to a general user who is chosen from a set of users ordered in accordance with PPP.

This paper investigates the optimization of the generalized likelihood ratio test (GLRT) eigenvalue-based spectrum sensing detector in terms of decision thresholds and sensing time. In order to guarantee the interests of primary and secondary users simultaneously, the sensing performance is assessed using the total error rate, i.e., the summation of probabilities of false alarm and missed detection. Therefore, the generalized statistical distributions of the test statistic are derived under the absence and presence of primary users, assuming an arbitrary number of receive antennas. These distributions are necessary for the analyses of the total error rate performance and the optimization. The optimization consists of two parts. Firstly, the optimal decision threshold is numerically obtained, which can minimize the total error rate under the constraints of target probabilities of false alarm and missed detection. Secondly, the optimal sensing time is obtained when a target total error rate is guaranteed, so that the spectrum sensing process can be accelerated without the loss of sensing accuracy. Furthermore, the simulation and theoretical results reveal that the chosen optimal decision thresholds benefit the primary and secondary users simultaneously and the chosen optimal sensing time improves the speed of spectrum sensing.

In this study, the authors investigate the Gallager's error exponents of dual‐hop amplify‐and‐forward systems over generalised η ‐ μ and κ ‐ μ fading channels, two versatile channel models which encompass a number of popular fading channels such as Rayleigh, Rician, Nakagami‐ m , Hoyt and one‐sided Gaussian fading channels. The authors present new analytical expressions for the probability density function of the end‐to‐end signal‐to‐noise‐ratio (SNR) of the system. These analytical expressions are then applied to analyse the system performance through the study of Gallager's exponents, which are classical tight bounds of error exponents and present the tradeoff between practical information rate and the reliability of communication. Two types of Gallager's exponents, namely, random coding error exponent and expurgated error exponent, are studied. Based on the newly derived analytical expressions, the authors provide an efficient method to compute the required codeword length to achieve a predefined upper bound of error probability. In addition, the analytical expressions are derived for the cutoff rate and ergodic capacity of the system. Moreover, simplified expressions are presented at the high SNR regime. All the analytical results are verified via Monte–Carlo simulations.

In this paper, the multi-way relaying scenario is considered with M users who want to exchange their information with each other with the help of N relays (N ≫ M) among them. There are no direct transmission channels between any two users. Particularly, all users transmit their signals to all relays in the first time slot and M - 1 relays are selected later to broadcast their mixture signals during the following M - 1 time slots to all users. Compared to the transmission with the help of single relay, the multi-way relaying scenario reduces the transmit time significantly from 2M to M time slots. Random and semiorthogonal relays selections are applied. Rician fading channels are considered between the users and relays, and analytical expressions for the outage probability and ergodic sum rate for the proposed relaying protocol are developed by first characterizing the statistical property of the effective channel gain based on random relays selection. Also, the approximation of ergodic sum rate at high signal-to-noise ratio regime is derived. In addition, the diversity order of the system is investigated for both random and semiorthogonal relay selections. Meanwhile, it is shown that when the relays are randomly separated into L groups of M - 1 relays, the group with maximum average channel gain can achieve the diversity order L, which will increase when more relays considered in the scheme. Furthermore, when semiorthogonal selection (SS) algorithm is applied to select the relays with semiorthogonal channels, it is shown that the system will guarantee that all the users can decode the others information successfully. Moreover, the maximum of channel gain after semiorthogonal relays selection is investigated by using extreme value theory, and tight lower and upper bounds are derived. Simulation results demonstrate that the derived expressions are accurate.

This paper investigates optimization of the sensing threshold that minimizes the total error rate (i.e., the sum of the probabilities of false alarm and missed detection) of eigenvalue-based spectrum sensing techniques for multiple-antenna cognitive radio networks. Four techniques are investigated, which are maximum eigenvalue detection (MED), maximum minimum eigenvalue (MME) detection, energy with minimum eigenvalue (EME) detection, and the generalized likelihood ratio test (GLRT) detection. The contribution of this paper is of four parts. Firstly, we present the derivative of the matrix-variate confluent hypergeometric function, which is required for the MED case. Secondly, we derive the probabilities of false alarm for both cases MME and EME detection. Thirdly, we derive the probability of missed detection for the GLRT detector. Finally, we provide the exact expressions required to obtain the optimal sensing thresholds for all cases. The simulation results reveal that for all the investigated cases the chosen optimal sensing thresholds achieve the minimum total error rate.

In this paper, we investigate the error exponents of dual-hop amplify-and-forward (AF) system for η-μ fading channel. Channel capacity of a wireless communication system gives only the knowledge of maximum achievable rate. Therefore, it is necessary to analyse the decoding complexity of the code that achieves a certain level of reliable communication. In fact, a measure of reliability called error exponent exists which sets ultimate bounds on the performance of communication systems employing codes of finite complexity. Assuming the receiver has full channel state information (CSI) and the transmitter has no CSI, we derive the novel exact expressions of Random coding error exponent (RCEE) and expurgated error exponent which provide insight into an elementary tradeoff between the communication reliability and information rate. Moreover, the necessary codeword length can be computed easily without the extensive Monte-Carlo simulation to achieve predefined error probability at a given rate. Meanwhile, simplified approximate expressions in the high signal-to-noise ratio (SNR) regime are also obtained. In addition, we derive the exact closed-form expressions for the ergodic capacity and cutoff rate.

Along with the channel capacity, the error exponent is one of the most important information-theoretic measures of reliability, as it sets ultimate bounds on the performance of communication systems employing codes of finite complexity. In this paper, we derive the closed-form expressions for the Gallager's random coding and expurgated error exponents for Rayleigh fading multi-keyhole multiple-input multiple-output (MIMO) channels, which provides insight into an elementary tradeoff between the communication reliability and information rate. Moreover, we can easily compute the necessary codeword length without the extensive Monte-Carlo simulation to achieve predefined error probability at a given rate. In addition, we derive the exact closed-form expressions for the ergodic capacity and cutoff rate based on the easily computable Meijer G-function. We also quantify the effects of the number of antennas, channel coherence time and the number of keyholes on the required codeword length to achieve a certain decoding error probability.

In this paper, we investigate the ergodic sum rate of K fading MIMO channels with linear MMSE receiver, which is an analytically friendly fading model to describe both the small scale fading and shadowing. The exact closed-form expression of the ergodic sum rate was derived, which is applicable for arbitrary number of transmit and receive antennas and any signal to noise ratio (SNR) range. Moreover, simple expressions were derived for the ergodic sum rate in the high and low SNR regimes. The analytical results enable us to gain insights on how the key system parameters affect the ergodic sum rate of the system. Numerical results are presented and verified via Monte Carlo simulations.

The performance of ad‐hoc networks is greatly affected by interference, particularly interference from nearby nodes. Based on stochastic geometry, this work studies a form of multiple‐input–multiple‐output (interference alignment (IA) that eliminates interference from transmitters within a range and treats the remaining interference as a shot noise process. Adapting to the bursty nature of ad‐hoc network traffic, the authors introduce a novel distributed ad‐hoc network with renewal process, whereby cooperation between interferer and receiver is implemented in one‐way process, which results from the difficulties for the node to change the beamforming or receiving matrix whereas communicating with a proposed transmitter. In addition, this scheme takes advantage of IA, leaving the desired signal with higher degree of freedom (DoF) compared with the partially zero‐forcing method. Outage probability and transmission capacity are derived with and without Rayleigh fading. Simulation results show the effect of IA in ad‐hoc network, including the incremental in the DoF of the desired signal as time goes by. Monte Carlo simulations are implemented and show that IA outperforms successive interference cancellation by at least 10 dB in terms of the signal‐to‐interference ratio with large path‐loss exponent.

Along with the channel capacity, the error exponent is one of the most important information theoretic measures of reliability, as it sets ultimate bounds on the performance of communication systems employing codes of finite complexity. In this paper, we derive the closed-form expressions of Gallager's random coding and expurgated error exponents for Nakagami-m fading keyhole multiple-input multiple-output (MIMO) channels under the assumption that there is no channel-state information (CSI) at the transmitter and perfect CSI at the receiver. From the derived analytical expressions, we get insight into an elementary tradeoff between the communication reliability and information rate of the Nakagami-m fading keyhole MIMO channels. Moreover, we can easily compute the necessary codeword length without the extensive Monte-carlo simulation to achieve predefined error probability at a given rate below the channel capacity. In addition, we derive the exact closed-form expressions for the cutoff rate, critical rate and expurgation rate based on easily computable Meijer G-function. Numerical results are presented and verified via Monte Carlo simulation.

Along with the channel capacity, the error exponent is one of the most important information theoretic measures of reliability, as it sets ultimate bounds on the performance of communication systems employing codes of finite complexity. In this paper, we derive the closed-form expressions for the Gallager's random coding and expurgated error exponents for Rayleigh fading product multiple-input multiple-output (MIMO) channels under the assumption that there is no channel-state information (CSI) at the transmitter and perfect CSI at the receiver. From the derived analytical expressions, we get insight into an elementary tradeoff between the communication reliability and information rate for the Rayleigh fading product MIMO channels. Moreover, we can easily compute the necessary codeword length without the extensive Monte-carlo simulation to achieve predefined error probability at a given rate below the channel capacity. In addition, we derive the exact closed-form expressions for the ergodic capacity and cutoff rate based on easily computable Meijer G-function. The closed-form expressions for the error exponents, ergodic capacity and cutoff rate have also been derived for Rayleigh fading keyhole MIMO channels as the example of special case.

In this paper, we study the error exponent of generalized-K fading multiple-input multiple-output (MIMO) channels over Orthogonal Space-Time Block Codes (OSTBC). Error exponent sets ultimate bounds on the performance of communication systems employing codes of finite complexity and has been seen as one of the most significant information theoretic measures of reliability. In this paper, closed-form expressions of Gallager's random coding and expurgated error exponents for generalized-K fading MIMO channels over OSTBC are derived, assuming that there is no channel-state information (CSI) at the transmitter and perfect CSI at the receiver. Based on which, we gain valuable insight into the fundamental tradeoff between the communication reliability and information rate of the channel. The necessary codeword length to achieve predefined error probability at a given rate below the capacity of channel is identified. Moreover, we derive closed-form expressions for the cutoff rate, critical rate and expurgation rate.

In this paper, we derive the closed-form Gallager's random coding error exponent expression for Orthogonal Space-Time Block Coded (OSTBC) Nakagami-m fading multiple-input multiple-output (MIMO) channels. We assume that the transmitter has no channel-state information (CSI) and perfect CSI at the receiver. We get the knowledge of an elementary tradeoff between the communication reliability and information rate of the OSTBC Nakagami-m fading MIMO channels by this measure. At a given rate below the channel capacity, it enables us to find the necessary codeword length to achieve predefined error probability. We derive the expression for the cutoff rate and ergodic capacity based on easily computable Meijer G-function. Numerical results are presented and verified via Monte-Carlo simulation.