Bridging Neural Networks and Wireless Systems with MIMO-OFDM Semantic Communications

Semantic communications aim to enhance transmission efficiency by jointly optimizing source coding, channel coding, and modulation. While prior research has demonstrated promising performance in simulations, real-world implementations often face significant challenges, including noise variability and nonlinear distortions, leading to performance gaps. This article investigates these challenges in a multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM)-based semantic communication system, focusing on the practical impacts of power amplifier (PA) nonlinearity and peak-to-average power ratio (PAPR) variations. Our analysis identifies frequency selectivity of the actual channel as a critical factor in performance degradation and demonstrates that targeted mitigation strategies can enable semantic systems to approach theoretical performance. By addressing key limitations in existing designs, we provide actionable insights for advancing semantic communications in practical wireless environments. This work establishes a foundation for bridging the gap between theoretical models and real-world deployment, highlighting essential considerations for system design and optimization.

Precoding Design for Limited-Feedback MISO Systems via Character-Polynomial Codes

We consider the problem of Multiple-Input Single- Output (MISO) communication with limited feedback, where the transmitter relies on a limited number of bits associated with the channel state information (CSI), available at the receiver (CSIR) but not at the transmitter (no CSIT), sent via the feedback link. We demonstrate how character-polynomial (CP) codes, a class of analog subspace codes (also, referred to as Grassmann codes) can be used for the corresponding quantization problem in the Grassmann space. The proposed CP codebook-based precoding design allows for a smooth trade-off between the number of feedback bits and the beamforming gain, by simply adjusting the rate of the underlying CP code. We present a theoretical upper bound on the mean squared quantization error of the CP codebook, and utilize it to upper bound the resulting distortion as the normalized gap between the CP codebook beamforming gain and the baseline equal gain transmission (EGT) with perfect CSIT. We further show that the distortion vanishes asymptotically. The results are also confirmed via simulations for different types of fading models in the MISO system and various parameters.

Frequency-selective beamforming and single-shot beam training with dynamic metasurface antennas

Dynamic metasurface antennas (DMAs) beamform through low-powered components that enable reconfiguration of each radiating element. Previous research on a single-user multiple-input-single-output (MISO) system with a dynamic metasurface antenna at the transmitter has focused on maximizing the beamforming gain at a fixed operating frequency. The DMA, however, has a frequency-selective response that leads to magnitude degradation for frequencies away from the resonant frequency of each element. This causes reduction in beamforming gain if the DMA only operates at a fixed frequency. We exploit the frequency reconfigurability of the DMA to dynamically optimize both the operating frequency and the element configuration, maximizing the beamforming gain. We leverage this approach to develop a single-shot beam training procedure using a DMA sub-array architecture that estimates the receiver's angular direction with a single OFDM pilot signal. We evaluate the beamforming gain performance of the DMA array using the receiver's angular direction estimate obtained from beam training. Our results show that it is sufficient to use a limited number of resonant frequency states to do both beam training and beamforming instead of using an infinite resolution DMA beamformer.

Pilot Contamination Aware Transformer for Downlink Power Control in Cell-Free Massive MIMO Networks

Learning-based downlink power control in cell-free massive multiple-input multiple-output (CFmMIMO) systems offers a promising alternative to conventional iterative optimization algorithms, which are computationally intensive due to online iterative steps. Existing learning-based methods, however, often fail to exploit the intrinsic structure of channel data and neglect pilot allocation information, leading to suboptimal performance, especially in large-scale networks with many users. This paper introduces the pilot contamination-aware power control (PAPC) transformer neural network, a novel approach that integrates pilot allocation data into the network, effectively handling pilot contamination scenarios. PAPC employs the attention mechanism with a custom masking technique to utilize structural information and pilot data. The architecture includes tailored preprocessing and post-processing stages for efficient feature extraction and adherence to power constraints. Trained in an unsupervised learning framework, PAPC is evaluated against the accelerated proximal gradient (APG) algorithm, showing comparable spectral efficiency fairness performance while significantly improving computational efficiency. Simulations demonstrate PAPC's superior performance over fully connected networks (FCNs) that lack pilot information, its scalability to large-scale CFmMIMO networks, and its computational efficiency improvement over APG. Additionally, by employing padding techniques, PAPC adapts to the dynamically varying number of users without retraining.

Harnessing Multimodal Sensing for Multi-user Beamforming in mmWave Systems

Sensor-aided beamforming reduces the overheads associated with beam training in millimeter-wave (mmWave) multi-input-multi-output (MIMO) communication systems. Most prior work, though, neglects the challenges associated with establishing multi-user (MU) communication links in mmWave MIMO systems. In this paper, we propose a new framework for sensor-aided beam training in MU mmWave MIMO system. We leverage the beamspace representation of the channel that contains only the angles-of-departure (AoDs) of the channel's significant multipath components. We show that a deep neural network (DNN)-based multimodal sensor fusion framework can estimate the beamspace representation of the channel using sensor data. To aid the DNN training, we introduce a novel supervised soft-contrastive loss (SSCL) function that leverages the inherent similarity between channels to extract similar features from the sensor data for similar channels. Finally, we design an MU beamforming strategy that uses the estimated beamspaces of the channels to select analog precoders for all users in a way that prevents transmission to multiple users over the same directions. Compared to the baseline, our approach achieves more than 4$\times$ improvement in the median sum-spectral efficiency (SE) at 42 dBm equivalent isotropic radiated power (EIRP) with 4 active users. This demonstrates that sensor data can provide more channel information than previously explored, with significant implications for machine learning (ML)-based communication and sensing systems.

Beam Training in mmWave Vehicular Systems: Machine Learning for Decoupling Beam Selection

Codebook-based beam selection is one approach for configuring millimeter wave communication links. The overhead required to reconfigure the transmit and receive beam pair, though, increases in highly dynamic vehicular communication systems. Location information coupled with machine learning (ML) beam recommendation is one way to reduce the overhead of beam pair selection. In this paper, we develop ML-based location-aided approaches to decouple the beam selection between the user equipment (UE) and the base station (BS). We quantify the performance gaps due to decoupling beam selection and also disaggregating the UE's location information from the BS. Our simulation results show that decoupling beam selection with available location information at the BS performs comparable to joint beam pair selection at the BS. Moreover, decoupled beam selection without location closely approaches the performance of beam pair selection at the BS when sufficient beam pairs are swept.

Neural Codebook Design for Network Beam Management

Obtaining accurate and timely channel state information (CSI) is a fundamental challenge for large antenna systems. Mobile systems like 5G use a beam management framework that joins the initial access, beamforming, CSI acquisition, and data transmission. The design of codebooks for these stages, however, is challenging due to their interrelationships, varying array sizes, and site-specific channel and user distributions. Furthermore, beam management is often focused on single-sector operations while ignoring the overarching network- and system-level optimization. In this paper, we proposed an end-to-end learned codebook design algorithm, network beamspace learning (NBL), that captures and optimizes codebooks to mitigate interference while maximizing the achievable performance with extremely large hybrid arrays. The proposed algorithm requires limited shared information yet designs codebooks that outperform traditional codebooks by over 10dB in beam alignment and achieve more than 25% improvements in network spectral efficiency.

AdaBoost-Based Efficient Channel Estimation and Data Detection in One-Bit Massive MIMO

The use of one-bit analog-to-digital converter (ADC) has been considered as a viable alternative to high resolution counterparts in realizing and commercializing massive multiple-input multiple-output (MIMO) systems. However, the issue of discarding the amplitude information by one-bit quantizers has to be compensated. Thus, carefully tailored methods need to be developed for one-bit channel estimation and data detection as the conventional ones cannot be used. To address these issues, the problems of one-bit channel estimation and data detection for MIMO orthogonal frequency division multiplexing (OFDM) system that operates over uncorrelated frequency selective channels are investigated here. We first develop channel estimators that exploit Gaussian discriminant analysis (GDA) classifier and approximated versions of it as the so-called weak classifiers in an adaptive boosting (AdaBoost) approach. Particularly, the combination of the approximated GDA classifiers with AdaBoost offers the benefit of scalability with the linear order of computations, which is critical in massive MIMO-OFDM systems. We then take advantage of the same idea for proposing the data detectors. Numerical results validate the efficiency of the proposed channel estimators and data detectors compared to other methods. They show comparable/better performance to that of the state-of-the-art methods, but require dramatically lower computational complexities and run times.

Successive Bayesian Reconstructor for FAS Channel Estimation

Fluid antenna systems (FASs) can reconfigure their locations freely within a spatially continuous space. To keep favorable antenna positions, the channel state information (CSI) acquisition for FASs is essential. While some techniques have been proposed, most existing FAS channel estimators require several channel assumptions, such as slow variation and angular-domain sparsity. When these assumptions are not reasonable, the model mismatch may lead to unpredictable performance loss. In this paper, we propose the successive Bayesian reconstructor (S-BAR) as a general solution to estimate FAS channels. Unlike model-based estimators, the proposed S-BAR is prior-aided, which builds the experiential kernel for CSI acquisition. Inspired by Bayesian regression, the key idea of S-BAR is to model the FAS channels as a stochastic process, whose uncertainty can be successively eliminated by kernel-based sampling and regression. In this way, the predictive mean of the regressed stochastic process can be viewed as the maximum a posterior (MAP) estimator of FAS channels. Simulation results verify that, in both model-mismatched and model-matched cases, the proposed S-BAR can achieve higher estimation accuracy than the existing schemes.

Successive Bayesian Reconstructor for Channel Estimation in Flexible Antenna Systems

Flexible antenna systems (FASs) can reconfigure their locations freely within a spatially continuous space. To keep favorable antenna positions, the channel state information (CSI) acquisition for FASs is essential. While some techniques have been proposed, most existing FAS channel estimators require several channel assumptions, such as slow variation and angular-domain sparsity. When these assumptions are not reasonable, the model mismatch may lead to unpredictable performance loss. In this paper, we propose the successive Bayesian reconstructor (S-BAR) as a general solution to estimate FAS channels. Unlike model-based estimators, the proposed S-BAR is prior-aided, which builds the experiential kernel for CSI acquisition. Inspired by Bayesian regression, the key idea of S-BAR is to model the FAS channels as a stochastic process, whose uncertainty can be successively eliminated by kernel-based sampling and regression. In this way, the predictive mean of the regressed stochastic process can be viewed as the maximum a posterior (MAP) estimator of FAS channels. Simulation results verify that, in both model-mismatched and model-matched cases, the proposed S-BAR can achieve higher estimation accuracy than the existing schemes.