Search Results (413)

The rapid evolution of fifth-generation (5G) and emerging sixth-generation (6G) wireless communication systems has considerably intensified the need for high data rates, ultra-low latency, massive connectivity, and intelligent network integration. To satisfy these requirements, millimeter-wave (mmWave) bands offer large available bandwidths; however, their severe propagation losses and integration constraints necessitate advanced antenna solutions. In this context, compact multi-port Multiple-Input–Multiple-Output (MIMO) antennas are a key solution for high-capacity and reliable mmWave communications. This review presents a comprehensive overview of recent antenna system technologies for 5G/6G applications, focusing on small mmWave MIMO antenna designs, performance improvement methods, advanced materials, and smart integration methods. Several antenna structures, such as microstrip patch, dielectric resonator, slot-based, and metamaterial-inspired designs, are critically discussed and compared. In addition, this review analyzes key design challenges involving miniaturization, mutual coupling reduction, bandwidth enhancement, gain improvement, radiation efficiency, and integration complexity, along with their impact on key performance metrics. The importance of advanced materials, artificial-intelligence-assisted optimization, hybrid antenna architectures, and smart integration strategies in future 5G/6G systems is also emphasized. Finally, we identified current challenges, emerging trends, and future research directions to provide useful design guidelines for researchers and engineers developing next-generation high-performance antenna systems for intelligent wireless communications. Full article

This paper tackles the problem of performance limitations on channel estimation accuracy in near-field massive MIMO systems resulting from the sparse reconstruction method with fixed spatial grid dictionaries. It presents a deep unfolded network with a learnable sparse dictionary (LSD-UnfoldNet) to address the grid mismatch, thereby obtaining high accuracy and low-complexity near-field channel estimation as the sparse dictionary and channel reconstruction parameters are jointly optimized using end-to-end learning. The iterative shrinking threshold algorithm is unfolded into an L-layer neural network with L learnable sparse dictionaries and linear transformation matrices in each layer of the network. Besides, to improve the correlation characteristics of the sensing matrix, an orthogonal regularization term is introduced. During training of the neural network, the Adam optimizer and cosine annealing learning rate scheduling are applied to jointly minimize the normalized mean square error and total loss of learned dictionary correlations. Experimental results demonstrate that the proposed method, at a representative signal-to-noise ratio of 20 dB, achieves normalized mean square errors of −24.5 dB. The root mean square errors for angle and distance estimation were 0.50° and 0.18 m, respectively, achieving superior performance relative to heuristic algorithms and deep learning-based algorithms. Beyond its strong robustness to different grid granularities and spatial distances, the proposed method also achieves competitive pilot overhead compared with other approaches. Full article

With the continuous evolution toward sixth-generation (6G) wireless communication systems, emerging scenarios such as terahertz transmission, integrated sensing and communication (ISAC), and ultra-massive multiple-input multiple-output (MIMO) have significantly increased the complexity, nonlinearity, and uncertainty of wireless propagation environments. The conventional model-driven paradigm, established upon Shannon information theory and precise mathematical modeling, is increasingly constrained by model-mismatch issues in real-world deployments. This paper systematically reviews recent advances in deep learning-enabled physical-layer signal processing. We examine intelligent channel estimation, signal detection, and end-to-end communication systems based on autoencoder architectures. We then analyze key technical challenges—including interpretability, data dependence, computational complexity, privacy and security in distributed learning, and system-level performance-overhead trade-offs—along with state-of-the-art solution strategies such as deep unfolding, transfer learning, model compression, federated learning, and lightweight design. Future evolutionary directions toward AI-native 6G networks, integrated sensing-communication-computing architectures, and intelligent reconfigurable wireless environments are discussed. Furthermore, emerging generative AI techniques, including diffusion models, are identified as a promising direction for addressing data scarcity and enhancing system adaptability. The study demonstrates that hybrid intelligence—integrating model-based prior knowledge with data-driven learning—will become the dominant design philosophy for next-generation intelligent physical-layer systems. Full article

This study proposes a novel hardware-impairment-aware convolutional neural network (CNN)-based hybrid precoding scheme for cell-free massive multiple input multiple output (MIMO) systems operating in the terahertz (THz) band under practical constraints of imperfect channel state information (CSI) and transceiver hardware non-idealities. In a realistic THz simulation environment incorporating molecular absorption, phase noise, channel aging, and power consumption models, the proposed CNN precoder demonstrates significant performance improvements over conventional Zero-Forcing (ZF), Kalman, and Minimum Mean Square Error (MMSE) schemes. Quantitative results show that the CNN achieves spectral efficiency gains of 10.67% over Kalman, 14.67% over MMSE, and 70% over ZF for an eight-user scenario. In addition, the CNN-based precoder provides an SNR gain of 0.8 dB over MMSE and 2 dB over ZF. Complexity analysis indicates that the CNN approach is 17% less complex than ZF, 44% less complex than Kalman, and 60% less complex than MMSE. Further analysis of individual impairment effects reveals that the CNN effectively mitigates the compounded degradation caused by hardware distortions and CSI imperfections, exhibiting only a 25% performance loss compared to an ideal hardware baseline. These results establish the proposed data-driven precoder as a robust, computationally efficient, and high-performance solution for reliable and energy-sustainable ultra-high-throughput THz communication networks. Full article

Cell-free massive multiple-input multiple-output (CF-mMIMO) systems have emerged as a promising architecture for beyond-5G wireless networks because they can provide user-centric coverage, improved spectral efficiency, and reduced cell-boundary limitations. However, dynamic downlink power allocation remains challenging due to user mobility, time-varying channel conditions, interference coupling, and the need to maintain Quality of Service (QoS) under practical transmit-power constraints. This paper proposes a Deep Hybrid Intelligent (DHI) framework for dynamic downlink power allocation in CF-mMIMO systems. The proposed framework integrates Soft Actor–Critic (SAC) reinforcement learning with three power-control strategies: DHI-Max-Min, DHI-Max-Product, and DHI-Max-Sum-Rate. The SAC agent learns adaptive power-allocation policies from the network state, while L-BFGS-B refinement is applied to the Max-Product and Max-Sum-Rate strategies to improve the power-allocation decisions under bounded transmit power. The framework is evaluated using a CF-mMIMO scenario with 64 access points and 32 pieces of user equipment distributed over a 1000 × 1000 m² area. The simulation results show that DHI-Max-Sum-Rate achieves the highest sum spectral efficiency, while DHI-Max-Min provides the strongest QoS-oriented performance with a QoS satisfaction rate of 93.75%. In addition, DHI-Max-Product and DHI-Max-Sum-Rate achieve mean computational times of 0.0690 s and 0.0696 s, respectively, compared with 0.63 s for the DDPG benchmark. These results demonstrate that the proposed DHI framework provides an adaptive and computationally efficient solution for QoS-aware downlink power allocation in dynamic CF-mMIMO networks. Full article

This paper proposes a two-dimensional orthogonal pattern division multiple access (OPDMA) technique to address key challenges in massive MIMO systems, including complex channel estimation, multipath interference, Doppler effects, and inter-antenna interference. Byleveraging optimal frequency hopping patterns with ideal autocorrelation and cross-correlation properties, constructed using a two-dimensional cyclic shift method, OPDMA eliminates the need for equalizers and channel estimation, thereby simplifying receiver design and mitigating pilot contamination. A method for constructing these patterns is introduced, based on an algebraic Costas array with a two-dimensional cyclic shift approach. The simulation results show that OPDMA significantly reduces the bit error rate (BER), simplifies system architecture, and enhances communication quality. These findings highlight OPDMA’s potential to improve performance and streamline the design of massive MIMO systems compared to traditional methods, which implies that OPDMA can be a promising low-complexity interference-suppression strategy when the optimal frequency hopping patterns design parameters match the expected Doppler shift and multipath delay. Full article

To reduce the hardware cost of massive multiple-input multiple-output (MIMO) systems, low-bit analog-to-digital converters (ADCs) and sparse arrays are widely used. Compared with traditional 1-bit and 2-bit quantization techniques, 1.5-bit quantization uses two symmetric non-zero thresholds to quantize signal power into three levels, thereby balancing quantization complexity against system performance. However, the quantization loss introduced by 1.5-bit quantization is still significant and leads to degradation in DOA estimation performance. To improve the DOA estimation accuracy of 1.5-bit sparse massive MIMO systems, a covariance matrix estimation method is proposed. This method exploits the Toeplitz property of the covariance matrix of sparse arrays and the relationship between 1.5-bit quantized signals and their unquantized counterparts to transform the covariance matrix estimation problem for 1.5-bit sparse arrays into a non-convex optimization problem with equality constraints. We then further exploit the properties of 1.5-bit quantized signals to relax this problem into a convex problem and solve it via semidefinite programming. Once the covariance is estimated, the DOAs can be recovered by subspace-based methods. Numerical results show that the proposed method achieves higher estimation accuracy than 1.5B-MUSIC and 1-bit covariance-fitting baselines on 1.5-bit sparse arrays, and is competitive with structured covariance-fitting baselines applied to unquantized data, especially on coprime arrays in low-snapshot scenarios. Full article

A coupled multi-stage learning framework is presented for joint bit error rate (BER) prediction and beam angle optimization in massive multiple-input multiple-output (MIMO) systems under a controlled simulation protocol. Unlike purely sequential benchmarking pipelines, the proposed method jointly coordinates BER prediction and beam-angle selection through a shared latent representation, an uncertainty-guided refinement mechanism, a cross-stage consistency loss and alternating optimization. Ten diverse approaches are systematically evaluated across two task-specific stages: Stage 1 examines six classical and adapted methods for BER prediction, including polynomial regression and deep unfolding networks; Stage 2 investigates four machine-learning and generative adversarial network (GAN)-based approaches for angle optimization, including conditional GANs and the proposed Direct-Angle neural network. Stage 3 couples the best-performing methods into a unified hybrid architecture through a shared encoder, explicit consistency regularization and alternating cross-stage updates, thereby producing an integrated beamforming decision strategy rather than an independent cascade. It is shown through the evaluation that the coupled hybrid framework achieves 96.0% overall angle-selection accuracy, a mean BER of $8.0\times {10}^{-5}$ and 100% BER tolerance compliance within $\pm 3$ dB. In this framework, a differentiable BER surrogate initialized from a second-degree polynomial-regression teacher is coupled with the proposed Direct-Angle-NN for angle optimization. Relative to the strongest reimplemented literature baseline under the same controlled simulation assumptions, a 33.3% reduction in mean BER is achieved. Ablation experiments show that the coupling mechanism provides a modest but consistent improvement over the decoupled sequential baseline, increasing angle-selection accuracy from 93.5% to 96.0% and reducing mean BER from $1.05\times {10}^{-4}$ to $8.0\times {10}^{-5}$; the shared encoder accounts for the largest part of this gain while the consistency loss adds 0.6 percentage points. These results indicate that the shared encoder, consistency regularization and uncertainty-guided refinement improve the final beamforming decision, although the gain should be interpreted as incremental rather than as a large architectural breakthrough. A spectral efficiency of 38.0 bps/Hz and an energy efficiency of 0.466 Gbps/W are achieved with a power consumption of only 32.6 W. The theoretical discussion is presented as an analytical characterization of BER sensitivity, complemented by a computational-complexity assessment and empirical convergence diagnostics for the alternating optimization, rather than as a formal optimality proof. The effectiveness of the framework across multiple performance metrics is supported by Monte Carlo simulations, while the limitations of the current setup, including perfect CSI, uncoded QPSK, ideal hardware assumptions and a fixed beam codebook, are explicitly discussed. The complete simulation framework, including code and trained models, can be made available by the corresponding author upon reasonable request to facilitate reproducible research in massive MIMO optimization. Full article

In massive multiple-input multiple-output (MIMO) joint communication and sensing (JCAS) systems, hybrid beamforming (HBF) has attracted much attention because it can provide a favorable tradeoff between beamforming gain and hardware cost. However, HBF design in MIMO-JCAS systems is highly challenging. The main reasons are the strong coupling between the analog and digital precoders in joint communication-sensing optimization and the high-dimensional search space caused by large-scale antenna arrays. In this paper, a state-driven adaptive deep-unfolded hybrid beamforming algorithm is proposed for MIMO-JCAS systems. Specifically, the analog precoder update is redesigned in a manifold-based form to better match the geometry of the constant-modulus constraint, while the digital precoder update is enhanced by a learnable gradient-balancing mechanism to alleviate the dynamic imbalance between the communication-rate gradient and the sensing-error gradient. Furthermore, a lightweight state-driven control network is introduced to generate scaling factors for the hyperparameters according to the current iteration state, so that the unfolded model can adapt its update behavior during optimization. Different from conventional deep-unfolded methods with static hyperparameters during inference, the proposed method provides a more effective optimization strategy for the dynamic communication-sensing tradeoff in MIMO-JCAS hybrid beamforming. Simulation results demonstrate the effectiveness of the proposed state-driven adaptive deep-unfolded method. Compared with the conventional deep-unfolded projected gradient ascent (PGA) algorithm with 20 inner iterations, the proposed method improves the joint objective, while achieving faster convergence and stronger robustness. Full article

The increasing complexity of next-generation wireless systems challenges the scalability and generalization capabilities of traditional model-driven physical layer (PHY) design, which relies on analytically derived channel models and optimization frameworks. This paper presents a comprehensive survey and critical review of deep learning (DL) architectures enabling the transition toward AI-native PHY design. A unified optimization perspective is developed in which all PHY tasks—including channel estimation, channel state information (CSI) feedback, massive MIMO processing, signal detection, channel coding, beamforming, resource allocation, and semantic-aware transmission—are formulated under a common empirical risk minimization (ERM) framework. Neural architectures such as autoencoders, convolutional and recurrent networks, transformers, and reinforcement learning models are examined through their underlying optimization formulations, loss functions, training methodologies, and representation learning mechanisms. The review compares model-driven and AI-native approaches in terms of performance metrics, computational complexity, robustness, generalization capability, and practical deployment constraints, including hardware limitations, energy efficiency, and real-time feasibility. The analysis highlights the conditions under which AI-native architectures provide adaptability and performance improvements while identifying trade-offs in complexity, latency, and interpretability. The study concludes by outlining prioritized research directions toward fully adaptive and self-optimizing wireless communication systems. Full article

The evolution toward prospective sixth-generation (6G) wireless networks is expected to significantly increase user density, bandwidth demand, and architectural complexity, reinforcing the need for scalable multiple-input multiple-output (MIMO) deployments. In this context, two fundamentally different design strategies have emerged: scaling up centralized antenna arrays and scaling out distributed cooperative infrastructures. This paper presents a system-level comparative benchmark of scale-up and scale-out MIMO architectures under identical operating conditions of three representative downlink deployments: centralized Massive MIMO, centralized XL-Massive MIMO, and distributed Cell-Free MIMO. All architectures are assessed under identical urban channel conditions, transmit power, bandwidth, and traffic assumptions, considering sub-6 GHz (3.5 GHz) and millimeter-wave (28 GHz) frequency bands as proxies for 5G and prospective 6G operation. A unified Monte Carlo simulation framework is employed to jointly evaluate aggregate throughput, spectral efficiency, coverage performance, interference behavior, and energy efficiency over a wide range of user densities and service radii. The results highlight the distinct architectural trade-offs between centralized and distributed deployments: XL-Massive MIMO maximizes aggregate throughput and spatial reuse in dense hotspot scenarios, whereas Cell-Free MIMO provides superior coverage uniformity and improved energy efficiency in wide-area deployments. By isolating the impact of architectural scaling under consistent assumptions, the presented benchmark offers quantitative guidance for 6G network design and deployment planning. Full article

The rapid growth of 5G necessitates wireless receivers capable of high-speed, low-latency communication under complex channel conditions. Traditional receivers struggle with the performance–complexity trade-off in massive MIMO systems, where linear detectors underperform and maximum likelihood (ML) detection becomes computationally prohibitive. Deep-learning-based model-driven approaches have demonstrated a favorable balance between detection performance and computational cost. However, despite their algorithmic promise, the transition of these learned detectors into practical, real-time systems is critically hampered by inefficient hardware mapping, resulting in suboptimal throughput, high resource overhead, and limited scalability. To bridge this gap, this paper presents LwAMP-Net, a dedicated FPGA accelerator for a lightweight learned AMP detector. We propose a modular and multi-mode hardware architecture for LwAMP-Net, featuring an outer-product-based dataflow that mitigates pipeline stalls and multi-mode processing elements that adapt to diverse computation patterns. These innovations jointly enhance computational parallelism and resource utilization on the FPGA. Implemented on a Xilinx XC7VX690T FPGA for a 128 × 8 MIMO system with 16QAM, the accelerator achieves a 49.2% higher normalized throughput per iteration, an 85.4% improvement in throughput per LUT slice, and a 12.7% improvement in throughput per DSP compared to the state-of-the-art methods. This work provides a complete architectural solution for deploying high-performance, hardware-efficient learned MIMO detectors in real-world systems. Full article

This paper presents a performance evaluation of a long short-term memory (LSTM)-based precoder for cell-free (CF) massive multiple-input multiple-output (MIMO) systems in 6G networks operating under hardware impairments and imperfect channel state information (CSI). It also compares the proposed method with traditional Kalman, minimum mean square error (MMSE), and zero forcing (ZF) precoders. Simulations conducted at 2.4 GHz show that the LSTM-based scheme offers improved spectral efficiency (SE) and energy efficiency (EE) while remaining computationally feasible. Specifically, the LSTM precoder achieves an average per-user SE of 1.74 bps/Hz, representing gains of about 1.15% over Kalman, 3.45% over MMSE, 4.6% over ZF, and 5.75% over MRT. Under severe hardware impairments, it provides a 2.94% improvement over Kalman and a 5.88% improvement over MMSE. The total SE reaches 17.4 bps/Hz, increasing the overall system capacity by approximately 2.87% over Kalman, 4.02% over MMSE, 6.32% over ZF, and 8.05% over MRT when the number of users (K) is 10. The LSTM-based precoder also achieves the highest peak EE, indicating that its learning-driven adaptability yields higher SE for comparable power usage. Despite a slight increase in power consumption, its inference time remains shorter than both MMSE and ZF, offering a favorable balance between performance and computational complexity. Overall, the results demonstrate that a learning-driven, impairment-aware precoding approach provides significant advantages in terms of robustness and scalability for next-generation 6G CF massive MIMO networks, particularly in non-ideal hardware environments. Full article

Extremely Large-Scale Multiple-Input Multiple-Output (XL-MIMO) is positioned as a transformative technology for sixth-generation (6G) networks, effectively turning base stations into high-resolution sensing and communication hubs. However, the practical deployment of XL-MIMO is hindered by the “curse of dimensionality,” specifically the prohibitive overhead associated with Channel State Information (CSI) sensing and feedback, alongside the computational latency of massive antenna arrays. To resolve the conflict between high-resolution sensing requirements and limited bandwidth resources, this paper proposes a novel two-stage beamforming architecture that synergizes physics-aware dimensionality reduction with deep learning. First, by exploiting the inherent sparsity of XL-MIMO channels in the angle-delay domain, we design a Spatial–Frequency Concentration Block (SFCB). This module functions as a hard-attention sensing mechanism, performing efficient source-end dimensionality reduction on raw CSI at the User Equipment (UE) via precise feature extraction and adaptive energy truncation. Second, we develop a highly adaptable Direct Integrated Precoding Network (DIP-I). Departing from the conventional “sense-reconstruct-then-precode” paradigm, DIP-I learns end-to-end mapping to directly regress the optimal precoding matrix at the Base Station (BS). Comprehensive simulations utilizing the COST 2100 and QuaDRiGa hybrid channel models demonstrate that, under a massive 512-antenna configuration, the proposed framework achieves exceptional beamforming gain. Furthermore, it significantly reduces sensing data overhead and inference latency, offering a superior trade-off between spectral efficiency and hardware resource consumption for future 6G sensing-communication integrated systems. Full article

In frequency division duplex (FDD) massive multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, the sub-array multi-user (MU) hybrid beamforming architecture is highly attractive because of its low hardware cost and high energy efficiency. However, downlink channel state information (CSI) acquisition and hybrid beamformer optimization remain challenging due to the large feedback overhead and the non-convexity of the beamforming design. To address these issues, we propose an end-to-end deep learning (DL) framework that jointly optimizes pilot training, CSI feedback, and hybrid beamforming, overcoming the limitations of conventional independently designed modules. At the core of the network, we introduce the star efficient location attention (StarELA) module, which combines the implicit high-dimensional representation capability of star operations (element-wise multiplication) with the fine-grained feature localization of efficient location attention (ELA). In addition, for wideband digital beamformer generation, we exploit inter-subcarrier correlation and design a frequency–domain seed generation and interpolation upsampling strategy, which significantly reduces network parameters. Experimental results show that the proposed method approaches the upper-bound performance of conventional hybrid beamforming with ideal CSI, while consistently outperforming existing benchmark methods. Full article