End-to-end (E2E) learning has recently been proposed to jointly design the modulator and symbol detector by using deep neural networks (DNNs). However, existing schemes lack sufficient capability to cancel multi-user interference (MUI) in uplink multi-user multiple-input multiple-output (MU-MIMO) systems. In this paper, we propose a graph neural network (GNN)-based E2E learning scheme that employs a GNN-based modulator to generate learned constellation points, and a GNN-based detector to cancel MUI. They are jointly optimized to minimize the symbol error rate (SER) performance loss. Simulation results demonstrate that the proposed E2E outperforms existing schemes with a predefined modulator. Specifically, it achieves an approximate 2 dB gain in a high MUI environment and surpasses even the maximum-likelihood (ML) detector in a low MUI condition.

This paper investigates how near-field beamfocusing can be achieved using a modular linear array (MLA), composed of multiple widely spaced uniform linear arrays (ULAs). The MLA architecture extends the aperture length of a standard ULA without adding additional antennas, thereby enabling near-field beamfocusing without increasing processing complexity. Unlike conventional far-field beamforming, near-field beamfocusing enables simultaneous data transmission to multiple users at different distances in the same angular interval, offering significant multiplexing gains. We present a detailed mathematical analysis of the beamwidth and beamdepth achievable with the MLA and show that by appropriately selecting the number of antennas in each constituent ULA, ideal near-field beamfocusing can be realized. In addition, we propose a computationally efficient localization method that fuses estimates from each ULA, enabling efficient parametric channel estimation. Simulation results confirm the accuracy of the analytical expressions and that MLAs achieve near-field beamfocusing with a limited number of antennas, making them a promising solution for next-generation wireless systems.

In massive MIMO systems, fully digital precoding offers high performance but has significant implementation complexity and energy consumption, particularly at millimeter frequencies and beyond. Hybrid analog-digital architectures provide a practical alternative by reducing the number of radio frequency (RF) chains while retaining performance in spatially sparse multipath scenarios. However, most hybrid precoder designs assume ideal, infinite-resolution analog phase shifters, which are impractical in real-world scenarios. Another practical constraint is the limited fronthaul capacity between the baseband processor and array, implying that each entry of the digital precoder must be picked from a finite set of quantization labels. To minimize the sum rate degradation caused by quantized analog and digital precoders, we propose novel designs inspired by the sphere decoding (SD) algorithm. We demonstrate numerically that our proposed designs outperform traditional methods, ensuring minimal sum rate loss in hybrid precoding systems with lowresolution phase shifters and limited fronthaul capacity.

Extremely large aperture arrays (ELAAs) and reconfigurable intelligent surfaces (RISs) are candidate enablers to realize connectivity goals for the sixth-generation (6G) wireless networks. For instance, ELAAs can provide orders-of-magnitude higher area throughput compared to what massive multiple-input multiple-output (MIMO) can deliver through spatial multiplexing, while RISs can improve the propagation conditions over wireless channels but a passively reflecting RIS must be large to be effective. Active RIS with amplifiers can deal with this issue. In this paper, we analyze the distortion generated by nonlinear amplifiers in both ELAAs and active RIS. We derive analytical expressions for the angular directions and depth of nonlinear distortion in both near-field and far-field channels. These insights are then used in a distortion-aware scheduling scheme that predicts the beamforming directions of the distortion and strategically allocates users in frequency to minimize its impact. Numerical results validate our theoretical analysis and compare distortion-aware and distortion-unaware scheduling methods, highlighting the benefits of accounting for nonlinearities. We conclude that nonlinearities can both create in-band and out-of-band distortion that is beamformed in entirely new directions and distances from the transmitter.

A reconfigurable intelligent surface (RIS) alters the reflection of incoming signals based on the phase-shift configuration assigned to its elements. This feature can be used to improve the signal strength for user equipments (UEs), expand coverage, and enhance spectral efficiency in wideband communication systems. Having accurate channel state information (CSI) is indispensable to realize the full potential of RIS-aided wideband systems. Unfortunately, CSI is challenging to acquire due to the passive nature of the RIS elements, which cannot perform transmit/receive signal processing. Recently, a parametric maximum likelihood (ML) channel estimator has been developed and demonstrated excellent estimation accuracy. However, this estimator is designed for narrowband systems with no non- line-of-sight (NLOS) paths. In this paper, we develop a novel parametric ML channel estimator for RIS-assisted wideband systems, which can handle line-of-sight (LOS) paths in the base station (BS)-RIS and RIS-UE links as well as NLOS paths between the UE, BS, and RIS. We leverage the reduced subspace representation induced by the array geometry to suppress noise in unused dimensions, enabling accurate estimation of the NLOS paths. Our proposed algorithm demonstrates superior estimation performance for the BS-UE and RIS-UE channels, outperforming the existing ML channel estimator.

In this paper, we consider a single-anchor localization system assisted by a reconfigurable intelligent surface (RIS), where the objective is to localize multiple user equipments (UEs) placed in the radiative near-field region of the RIS by estimating their azimuth angle-of-arrival (AoA), elevation AoA, and distance to the surface. The three-dimensional (3D) locations can be accurately estimated via the conventional MUltiple SIgnal Classification (MUSIC) algorithm, albeit at the expense of tremendous complexity due to the 3D grid search. In this paper, capitalizing on the symmetric structure of the RIS, we propose a novel modified MUSIC algorithm that can efficiently decouple the AoA and distance estimation problems and drastically reduce the complexity compared to the standard 3D MUSIC algorithm. Additionally, we introduce a spatial smoothing method by partitioning the RIS into overlapping sub-RISs to address the rank-deficiency issue in the signal covariance matrix. We corroborate the effectiveness of the proposed algorithm via numerical simulations and show that it can achieve the same performance as 3D MUSIC but with much lower complexity.

Future wireless networks must provide ever higher data rates. The available bandwidth increases roughly linearly as we increase the carrier frequency, but the range shrinks drastically. This paper explores if we can instead reach massive capacities using spatial multiplexing over multiple-input multiple-output (MIMO) channels. In line-of-sight (LOS) scenarios, the rank of the MIMO channel matrix depends on the polarization and antenna arrangement. We optimize the rank and condition number by identifying the optimal antenna spacing in dual-polarized planar antenna arrays with imperfect isolation. The result is sparsely spaced antenna arrays that exploit radiative near-field properties. We further optimize the array geometry for minimum aperture length and aperture area, which leads to different configurations. Moreover, we prove analytically that for fixed-sized arrays, the MIMO rank grows quadratically with the carrier frequency in LOS scenarios, if the antennas are appropriately designed. Hence, MIMO technology contributes more to the capacity growth than the bandwidth. The numerical results show that massive data rates, far beyond 1 Tbps, can be reached both over fixed and mobile point-to-point links. It is also possible for a large base station to serve a practically-sized mobile device.

Most wireless communication systems operate in the far-field region of antennas and antenna arrays, where waves are planar and beams have infinite depth. When antenna arrays become electrically large, it is possible that the receiver is in the radiative near-field of the transmitter, and vice versa. Recent works have shown that near-field beamforming exhibits a finite depth, which enables a new depth-based spatial multiplexing paradigm. In this paper, we explore how the shape and size of an array determine the near-field beam behaviors. In particular, we investigate the 3 dB beam depth (BD), defined as the range of distances where the gain is greater than half of the peak gain. We derive analytical gain and BD expressions and prove how they depend on the aperture area and length. For non-broadside transmissions, we find that the BD increases as the transmitter approaches the end-fire direction of the array. Furthermore, it is sufficient to characterize the BD for a broadside transmitter, as the beam pattern with a non-broadside transmitter can be approximated by that of a smaller/projected array with a broadside transmitter. Our analysis demonstrates that the BD can be ordered from smallest to largest as ULA, circular, and square arrays.

Most wireless communication systems operate in the far-field region of antennas and antenna arrays, where waves are planar and beams have infinite depth. When antenna arrays become electrically large, it is possible that the receiver is in the radiative near-field of the transmitter, and vice versa. Recent works have shown that near-field beamforming exhibits a finite depth, which enables a new depth-based spatial multiplexing paradigm. In this paper, we explore how the shape and size of a rectangular array determine the near-field beam behaviors. In particular, we investigate the 3 dB beam depth (BD), defined as the range of distances where the gain is greater than half of the peak gain. We derive analytical gain and BD expressions and prove how they depend on the aperture area and length. The largest BD is obtained for a square array while the smallest BD is obtained by a uniform linear array.

Efficient massive/ultra-massive multiple-input multiple-output (MIMO) detection algorithms with satisfactory performance and low complexity are critical to meet the high throughput and ultra-low latency requirements in 5G and beyond communications, given the extremely large number of antennas. In this paper, we propose a low complexity graph neural network (GNN) enhanced approximate message passing (AMP) algorithm, AMP-GNN, for massive/ultra-massive MIMO detection. The structure of the neural network is customized by unfolding the AMP algorithm and introducing the GNN module for multiuser interference cancellation. Numerical results will show that the proposed AMP-GNN significantly improves the performance of the AMP detector and achieves comparable performance as the state-of-the-art deep learning-based MIMO detectors but with reduced computational complexity. Furthermore, it presents strong robustness to the change of the number of users.

In this paper, we design the joint decoding (JD) of non-orthogonal multiple access (NOMA) systems employing short block length codes. We first proposed a low-complexity soft-output ordered-statistics decoding (LC-SOSD) based on a decoding stopping condition, derived from approximations of the a-posterior probabilities of codeword estimates. Simulation results show that LC-SOSD has the similar mutual information transform property to the original SOSD with a significantly reduced complexity. Then, based on the analysis, an efficient JD receiver which combines the parallel interference cancellation (PIC) and the proposed LC-SOSD is developed for NOMA systems. Two novel techniques, namely decoding switch (DS) and decoding combiner (DC), are introduced to accelerate the convergence speed. Simulation results show that the proposed receiver can achieve a lower bit-error rate (BER) compared to the successive interference cancellation (SIC) decoding over the additive-white-Gaussian-noise (AWGN) and fading channel, with a lower complexity in terms of the number of decoding iterations.

Multiuser massive multiple-input multiple-output (MU-MIMO) systems can be used to meet high throughput requirements of 5G and beyond networks. In an uplink MU-MIMO system, a base station is serving a large number of users, leading to a strong multi-user interference (MUI). Designing a high performance detector in the presence of a strong MUI is a challenging problem. This work proposes a novel detector based on the concepts of expectation propagation (EP) and graph neural network, referred to as the GEPNet detector, addressing the limitation of the independent Gaussian approximation in EP. The simulation results show that the proposed GEPNet detector significantly outperforms the state-of-the-art MU-MIMO detectors in strong MUI scenarios with equal number of transmit and receive antennas.

IEEE 802.11ah targets long-range IoT applications where a large number of low power wireless sensor stations are connected to an access point (AP). Rate adaptation (RA) algorithm plays a prominent role in adaptively selecting an appropriate transmission rate in order to maximize throughput in that. Minstrel RA algorithm that uses a random sampling approach has been the defacto RA in industry due to its ability to adapt rate fast in a time-varying channel and non-dependency to the air-interface design used in 802.11ah as compared to other existing RA approaches. However, the throughput performance and convergence time of the Minstrel RA algorithm are still suboptimal due to its random sampling mechanism. In this paper, we propose to improve the Minstrel RA algorithm for the 802.11ah system by designing a shallow neural networks (SNNs) module that predicts a rate input for the random sampling mechanism in Minstrel. The SNNs module is implemented in the access point and consists of several SNNs. Our simulation results in the network simulator-3 (NS-3) show that our proposed algorithm is able to improve the conventional Minstrel algorithm’s convergence time and throughput by around 3.5 times and 40%.

Multi-user multiple-input multiple-output (MU-MIMO) systems can be used to meet high throughput requirements of 5G and beyond networks. A base station serves many users in an uplink MU-MIMO system, leading to a substantial multi-user interference (MUI). Designing a high-performance detector for dealing with a strong MUI is challenging. This paper analyses the performance degradation caused by the posterior distribution approximation used in the state-of-the-art message passing (MP) detectors in the presence of high MUI. We develop a graph neural network based framework to fine-tune the MP detectors’ cavity distributions and thus improve the posterior distribution approximation in the MP detectors. We then propose two novel neural network based detectors which rely on the expectation propagation (EP) and Bayesian parallel interference cancellation (BPIC), referred to as the GEPNet and GPICNet detectors, respectively. The GEPNet detector maximizes detection performance, while GPICNet detector balances the performance and complexity. We provide proof of the permutation equivariance property, allowing the detectors to be trained only once, even in the systems with dynamic changes of the number of users. The simulation results show that the proposed GEPNet detector performance approaches maximum likelihood performance in various configurations and GPICNet detector doubles the multiplexing gain of BPIC detector.

Recently, the orthogonal time frequency space (OTFS) modulation is proposed for 6G wireless system to deal with high Doppler spread. The high Doppler spread happens when the transmitted signal is reflected towards the receiver by fast moving objects (e.g. high speed cars), which causes inter-carrier interference (ICI). Recent state-of-the-art OTFS detectors fail to achieve an acceptable bit-error-rate (BER) performance as the number of mobile reflectors increases which in turn, results in high inter-carrier-interference (ICI). In this paper, we propose a novel detector for OTFS systems, referred to as the Bayesian based parallel interference and decision statistics combining (B-PIC-DSC) OTFS detector that can achieve a high BER performance, under high ICI environments. The B-PIC-DSC OTFS detector employs the PIC and DSC schemes to iteratively cancel the interference, and the Bayesian concept to take the probability measure into the consideration when refining the transmitted symbols. Our simulation results show that in contrast to the state-of-the-art OTFS detectors, the proposed detector is able to achieve a BER of less than 10−5, when SNR is over 14 dB, under high ICI environments.

Cell-free (CF) massive multiple-input multiple-output (M-MIMO) technology plays a prominent role in the beyond fifth-generation (5G) networks. However, designing a high performance CF M-MIMO detector is a challenging task due to the presence of pilot contamination which appears when the number of pilot sequences is smaller than the number of users. This work proposes a CF M-MIMO detector referred to as CF expectation propagation (CF-EP) that incorporates the pilot contamination when calculating the posterior belief. The simulation results show that the proposed detector achieves significant improvements in terms of the bit-error rate and sum spectral efficiency performances as compared to the ones of the state-of-the-art CF detectors.

The stringent requirements on reliability and processing delay in the fifth-generation (5G) cellular networks introduce considerable challenges in the design of massive multiple-input-multiple-output (M-MIMO) receivers. The two main components of an M-MIMO receiver are a detector and a decoder. To improve the trade-off between reliability and complexity, a Bayesian concept has been considered as a promising approach that enhances classical detectors, e.g. minimum-mean-square-error detector. This work proposes an iterative M-MIMO detector based on a Bayesian framework, a parallel interference cancellation scheme, and a decision statistics combining concept. We then develop a high performance M-MIMO receiver, integrating the proposed detector with a low complexity sequential decoding for polar codes. Simulation results of the proposed detector show a significant performance gain compared to other low complexity detectors. Furthermore, the proposed M-MIMO receiver with sequential decoding ensures one order magnitude lower complexity compared to a receiver with stack successive cancellation decoding for polar codes from the 5G New Radio standard.

Much stringent reliability and processing latency requirements in ultra-reliable-low-latency-communication (URLLC) traffic make the design of linear massive multiple-input-multiple-output (M-MIMO) receivers becomes very challenging. Recently, Bayesian concept has been used to increase the detection reliability in minimum-mean-square-error (MMSE) linear receivers. However, the latency processing time is a major concern due to the exponential complexity of matrix inversion operations in MMSE schemes. This paper proposes an iterative M-MIMO receiver that is developed by using a Bayesian concept and a parallel interference cancellation (PIC) scheme, referred to as a linear Bayesian learning (LBL) receiver. PIC has a linear complexity as it uses a combination of maximum ratio combining (MRC) and decision statistic combining (DSC) schemes to avoid matrix inversion operations. Simulation results show that the bit-error-rate (BER) and latency processing performances of the proposed receiver outperform the ones of MMSE and best Bayesian-based receivers by minimum 2 dB and 19 times for various M-MIMO system configurations.

The order-of-magnitude increase in the dimension of antenna arrays, which forms extra-large-scale massive multiple-input-multiple-output (MIMO) systems, enables substantial improvement in spectral efficiency, energy efficiency, and spatial resolution. However, practical challenges, such as excessive computational complexity and excess of baseband data to be transferred and processed, prohibit the use of centralized processing. A promising solution is to distribute baseband data from disjoint subsets of antennas into parallel processing procedures coordinated by a central processing unit. This solution is called subarray-based architecture. In this work, we extend the application of expectation propagation (EP) principle, which effectively balances performance and practical feasibility in conventional centralized MIMO detector design, to fit the subarray-based architecture. Analytical results confirm the convergence of the proposed iterative procedure and that the proposed detector asymptotically approximates Bayesian optimal performance under certain conditions. The proposed subarray-based EP detector is reduced to centralized EP detector when only one subarray exists. In addition, we propose additional strategies for further reducing the complexity and overhead of the information exchange between parallel subarrays and the central processing unit to facilitate the practical implementation of the proposed detector. Simulation results demonstrate that the proposed detector achieves numerical stability within few iterations and outperforms its counterparts.