Obtaining accurate and timely channel state information (CSI) is a fundamental challenge for large MIMO systems. Mobile cellular 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.

Beam management is the defacto approach for configuring the antennas in 5G MIMO communication systems. Extending the beam management framework to larger arrays— also known as extreme MIMO systems—is challenging as the overheads grow with the array dimensions. One solution is to make use of the wealth of sensor data that is becoming available in integrated sensing and communication (ISAC) systems. In this paper, we propose a neural architecture for codebook design using environmental context derived from sensor data. In particular, we combine beamspace transformations with local occupancy grids obtained through network sensing to maximize the achievable rate in vehicular operations. Our results show significant performance gains over traditional codebooks while requiring less overhead than standard 5G beam management.

Network slicing at the radio access network (RAN) domain, called RAN slicing, requires elasticity, efficient resource sharing, and customization. In this scenario, radio resource scheduling (RRS) is responsible for dealing with scarce and limited frequency spectrum resources available at the RAN domain while fulfilling the slice intents. The wide variety of scenarios supported in 5G and beyond 5G networks makes the RRS problem in RAN slicing scenario a significant challenge. This paper proposes an intent-aware reinforcement learning method to perform the RRS function in a RAN slicing scenario. The slice's quality of service intents is described in a common intent model in a service-level agreement. The proposed method tries to prevent intent faults by making the management of radio resources available among slices. This method uses slices' and user equipment network metrics in the observation space. The proposed method is evaluated under different network conditions and outperforms different baselines considering the slices' intents fulfillment.

Beam codebooks are a recent feature to enable high dimension multiple-input multiple-output in 5G. Codebooks comprised of customizable beamforming weights can be used to transmit reference signals and aid the channel state information (CSI) acquisition process. Codebooks are also used for quantizing feedback following CSI acquisition. In this paper, we characterize the role of each codebook used during the beam management process and design a neural network to find codebooks that improve overall system performance. Evaluating a codebook requires considering the system-level dependency between the codebooks, feedback, overhead, and spectral efficiency. The proposed neural network is built on translating codebook and feedback knowledge into a consistent beamspace basis similar to a virtual channel model to generate initial access codebooks. This beamspace codebook algorithm is designed to directly integrate with current 5G beam management standards without changing the feedback format or requiring additional side information. Our simulations show that the neural network codebooks improve over traditional codebooks, even in dispersive sub-6GHz environments. We further use our framework to evaluate CSI feedback formats with regard to multi-user spectral efficiency. Our results suggest that optimizing codebook performance can provide valuable performance improvements, but optimizing the feedback configuration is also important in sub-6GHz bands.

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.

Beam management is a strategy to unify beamforming and channel state information (CSI) acquisition with large antenna arrays in 5G. Codebooks serve multiple uses in beam management including beamforming reference signals, CSI reporting, and analog beam training. In this paper, we propose and evaluate a machine learning-refined codebook design process for extremely large multiple-input multiple-output (X-MIMO) systems. We propose a neural network and beam selection strategy to design the initial access and refinement codebooks using end-to-end learning from beamspace representations. The algorithm, called Extreme-Beam Management (X-BM), can significantly improve the performance of extremely large arrays as envisioned for 6G and capture realistic wireless and physical layer aspects. Our results show an 8dB improvement in initial access and overall effective spectral efficiency improvements compared to traditional codebook methods.

Massive multiple-input multiple-output (MIMO) is an important technology in fifth generation (5G) cellular networks and beyond. To help design the beamforming at the base station, 5G has introduced new support in the form of flexible feedback and configurable antenna array geometries that allow for arbitrarily massive physical arrays. In this article, we present an overview of MIMO throughout the mobile standards, highlight the new beam-based feedback system in 5G NR, and describe how this feedback system enables massive MIMO through beam management. Finally, we conclude with challenges related to massive MIMO in 5G.

Large MIMO arrays can improve network performance when configured with accurate channel state information. 5G supports two formats, or types, for feeding back channel state information to the transmitter based on codebooks. Type-I is a direct codebook format containing a small set of predefined codewords, while type-II feedback is a construction-based feedback format where the channel state information is represented as a sum of multipath components with complex gains. Type-II feedback involves more overhead than type-I feedback, but it is more computationally expensive and neither format is sufficiently rich enough for low- and mid-band deployments. Type-II feedback can be extended to support richer feedback, but the computational complexity grows exponentially. In this paper, we propose two new methods for calculating type-II precoding matrix indicator (PMI) feedback using the inherent structure of oversampled DFT codebooks. The first method is based on iteratively decomposing the PMI, while the second method uses a codebook-of-codebooks to integrate the correlation of oversampled DFT codebooks into the beam selection process. We show in simulation that the proposed codebook-of-codebooks method can increase the effective spectral efficiency by up to 25% in multi-user settings with the same computational cost.

The detection and estimation of sinusoids is a fundamental signal processing task for many applications related to sensing and communications. While algorithms have been proposed for this setting, quantization is a critical, but often ignored modeling effect. In wireless communications, estimation with low resolution data converters is relevant for reduced power consumption in wideband receivers. Similarly, low resolution sampling in imaging and spectrum sensing allows for efficient data collection. In this work, we propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples. We incorporate signal reconstruction internally as domain knowledge within the network to enhance learning and surpass traditional algorithms in mean squared error and Chamfer error. We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions. This threshold provides insight into why neural networks tend to outperform traditional methods and into the learned relationships between the input and output distributions. In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data. We use the learning threshold to explain, in the one-bit case, how our estimators learn to minimize the distributional loss, rather than learn features from the data.

Fifth-generation (5G) cellular communication systems have embraced massive multiple-input-multiple-output (MIMO) in the low- and mid-band frequencies. In a multiband system, the base station can serve different users in each band, while the user equipment can operate only in a single band simultaneously. This paper considers a massive MIMO system where channels are dynamically allocated in different frequency bands. We treat multiband massive MIMO as a scheduling and resource allocation problem and propose deep reinforcement learning (DRL) agents to perform user scheduling. The DRL agents use buffer and channel information to compose their observation space, and the agent's reward function maximizes the transmitted throughput and minimizes the packet loss rate. We compare the proposed DRL algorithms with traditional baselines, such as maximum throughput and proportional fairness. The results show that the DRL models outperformed baselines obtaining a 20% higher network sum rate and an 84% smaller packet loss rate. Moreover, we compare different DRL algorithms focusing on training time to assess the online implementation of the DRL agents, showing that the best agent needs about 50K training steps to converge.

Beam codebooks are a new feature of massive multiple-input multiple-output (M-MIMO) in 5G new radio (NR). Codebooks comprised of beamforming vectors are used to transmit reference signals and obtain limited channel state information (CSI) from receivers via the codeword index. This enables large arrays that cannot otherwise obtain sufficient CSI. The performance, however, is limited by the codebook design. In this paper, we show that machine learning can be used to train site-specific codebooks for initial access. We design a neural network based on an autoencoder architecture that uses a beamspace observation in combination with RF environment characteristics to improve the synchronization signal (SS) burst codebook. We test our algorithm using a flexible dataset of channels generated from QuaDRiGa. The results show that our model outperforms the industry standard (DFT beams) and approaches the optimal performance (perfect CSI and singular value decomposition (SVD)-based beamforming), using only a few bits of feedback.

Cellular networks continue to trend rapidly towards more bands and carrier frequencies, along with higher base station density, requiring complex decisions to be made when associating a mobile user with a band and cell. This paper develops a novel approach to optimizing frequency band and cell selection while taking into account user mobility and handovers. This is a complex problem because of the uncertain link failure events, handover related overheads, and the significant difference in the propagation characteristics between different frequency bands. The network dynamics due to user mobility are modeled as a Markov decision process, and we develop a recurrent Q-learning framework to exploit the relationship between user trajectories and the history of SINR measurements. The effective cell boundaries are therefore based on user trajectories and velocities rather than just position and signal strength. Detailed system-level simulations show that the proposed learning-based approach improves the throughput of the edge users by 54% and the median throughput by 34% compared to traditional SINR-based association and achieves a superior rate/coverage tradeoff (quantified as sum-log-rate) compared to SINR or signal-strength-based associations.

Wireless cellular networks have many parameters that are normally tuned upon deployment and re-tuned as the network changes. Many operational parameters affect reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-interference-plus-noise-ratio (SINR), and, ultimately, throughput. In this paper, we develop and compare two approaches for maximizing coverage and minimizing interference by jointly optimizing the transmit power and downtilt (elevation tilt) settings across sectors. To evaluate different parameter configurations offline, we construct a realistic simulation model that captures geographic correlations. Using this model, we evaluate two optimization methods: deep deterministic policy gradient (DDPG), a reinforcement learning (RL) algorithm, and multi-objective Bayesian optimization (BO). Our simulations show that both approaches significantly outperform random search and converge to comparable Pareto frontiers, but that BO converges with two orders of magnitude fewer evaluations than DDPG. Our results suggest that data-driven techniques can effectively self-optimize coverage and capacity in cellular networks.

Low resolution architectures are a power efficient solution for high bandwidth communication at millimeter wave and terahertz frequencies. In such systems, carrier synchronization is important yet has not received much attention. In this paper, we develop and analyze deep learning architectures for estimating the carrier frequency of a complex sinusoid in noise from the 1-bit samples of the in-phase and quadrature components. Carrier frequency offset estimation from a sinusoid is used in GSM and is a first step towards developing a more comprehensive solution with other kinds of signals. We train four different deep learning architectures each on eight datasets which represent possible training considerations. Specifically, we consider how training with various signal to noise ratios (SNR), quantization, and sequence lengths affects estimation error. Further, we analyze each architecture in terms of scalability for MIMO receivers. In simulations, we compare execution time and mean squared error (MSE) versus classic signal processing techniques. We demonstrate that training with quantized data, drawn from signals with SNRs between 0-10dB tends to improve deep learning estimator performance across the entire SNR range of interest. We conclude that convolutional models have the best performance, while also requiring shorter execution time than FFT methods. Our approach is able to accurately estimate carrier frequencies from 1-bit quantized data with fewer pilots and lower signal to noise ratios (SNRs) than traditional signal processing methods.

This paper presents a novel method for classifying radio frequency (RF) devices from their transmission signals. Given a collection of signals from identical devices, we accurately classify both the distance of the transmission and the specific device identity. We develop a multiple classifier system that accurately discriminates between channels and classifies devices using normalized in-phase and quadrature (IQ) samples. Our network uses residual connections for both distance and device classification, reaching 88.33% accuracy classifying 16 unique devices over 11 different distances and two different times, on a task that was previously unlearnable. Furthermore, we demonstrate the efficacy for pre-training neural networks for massive data domains and subtle classification differences.

Low resolution data converters can enable power efficient high bandwidth communication at millimeter-wave and terahertz frequencies. Synchronization of such systems is a critical step in accurate decoding, yet current approaches require long block lengths or fail to reach the Cramer Rao Bound (CRB).´ Prior solutions have traditionally been divided into two distinct focuses: algorithms and designed sequences for synchronization. In this paper, we develop a jointly optimized neural architecture for frequency synchronization from configurable sequences and estimators. Our proposed technique uses two neural networks to generate sequences and determine the carrier frequency offset of the sequence after propagating through a channel and applying one-bit quantization. Our simulations show that we can improve estimation performance at low signal to noise ratio (SNR) by up to 8dB at little cost compared to the same estimator without the sequence generator. Our proposed system is fast, efficient, and easily updated, allowing it to handle time-varying systems. In conclusion, we believe further investigation in jointly optimized pilot sequences and estimators will be fundamental to handling signal processing techniques with low resolution data converters.