Search

We detail the steps required to deploy a multi-user multiple-input multiple-output (MU-MIMO) neural receiver (NRX) in an actual cellular communication system. This raises several exciting research challenges, including the need for real-time inference and compatibility with the 5G NR standard. As the network configuration in a practical setup can change dynamically within milliseconds, we propose an adaptive NRX architecture capable of supporting dynamic modulation and coding scheme (MCS) configurations without the need for any re-training and without additional inference cost. We optimize the latency of the neural network (NN) architecture to achieve inference times of less than 1ms on an NVIDIA A100 GPU using the TensorRT inference library. These latency constraints effectively limit the size of the NN and we quantify the resulting signal-to-noise ratio (SNR) degradation as less than 0.7 dB when compared to a preliminary non-real-time NRX architecture. Finally, we explore the potential for site-specific adaptation of the receiver by investigating the required size of the training dataset and the number of fine-tuning iterations to optimize the NRX for specific radio environments using a ray tracing-based channel model. The resulting NRX is ready for deployment in a real-time 5G NR system and the source code including the TensorRT experiments is available online.

We introduce a neural network (NN)-based multiuser multiple-input multiple-output (MU-MIMO) receiver with 5G New Radio (5G NR) physical uplink shared channel (PUSCH) compatibility. The NN architecture is based on convolution layers to exploit the time and frequency correlation of the channel and a graph neural network (GNN) to handle multiple users. The proposed architecture adapts to an arbitrary number of sub-carriers and supports a varying number of multiple-input multiple-output (MIMO) layers and users without the need for any retraining. The receiver operates on an entire 5G NR slot, i.e., processes the entire received orthogonal frequency division multiplexing (OFDM) time-frequency resource grid by jointly performing channel estimation, equalization, and demapping. The proposed architecture operates less than 1 dB away from a baseline using linear minimum mean square error (LMMSE) channel estimation with K-best detection but benefits from a significantly lower computational complexity. We show the importance of a carefully designed training process such that the trained receiver is universal for a wide range of different unseen channel conditions. Finally, we demonstrate the results of a hardware-in-the-loop verification based on 3GPP compliant conformance test scenarios., Comment: 6 pages, 6 figures, presented at IEEE Globecom 2023

Sionna is a GPU-accelerated open-source library for link-level simulations based on TensorFlow. Since release v0.14 it integrates a differentiable ray tracer (RT) for the simulation of radio wave propagation. This unique feature allows for the computation of gradients of the channel impulse response and other related quantities with respect to many system and environment parameters, such as material properties, antenna patterns, array geometries, as well as transmitter and receiver orientations and positions. In this paper, we outline the key components of Sionna RT and showcase example applications such as learning radio materials and optimizing transmitter orientations by gradient descent. While classic ray tracing is a crucial tool for 6G research topics like reconfigurable intelligent surfaces, integrated sensing and communications, as well as user localization, differentiable ray tracing is a key enabler for many novel and exciting research directions, for example, digital twins., Comment: 5 pages, 5 figures, update reflects new features of Sionna RT introduced in release v0.15

In this work, we propose a fully differentiable graph neural network (GNN)-based architecture for channel decoding and showcase a competitive decoding performance for various coding schemes, such as low-density parity-check (LDPC) and BCH codes. The idea is to let a neural network (NN) learn a generalized message passing algorithm over a given graph that represents the forward error correction (FEC) code structure by replacing node and edge message updates with trainable functions. Contrary to many other deep learning-based decoding approaches, the proposed solution enjoys scalability to arbitrary block lengths and the training is not limited by the curse of dimensionality. We benchmark our proposed decoder against state-of-the-art in conventional channel decoding as well as against recent deep learning-based results. For the (63,45) BCH code, our solution outperforms weighted belief propagation (BP) decoding by approximately 0.4 dB with significantly less decoding iterations and even for 5G NR LDPC codes, we observe a competitive performance when compared to conventional BP decoding. For the BCH codes, the resulting GNN decoder can be fully parametrized with only 9640 weights., Comment: Source code is available online https://github.com/NVlabs/gnn-decoder

We propose a neural network (NN)-based algorithm for device detection and time of arrival (ToA) and carrier frequency offset (CFO) estimation for the narrowband physical random-access channel (NPRACH) of narrowband internet of things (NB-IoT). The introduced NN architecture leverages residual convolutional networks as well as knowledge of the preamble structure of the 5G New Radio (5G NR) specifications. Benchmarking on a 3rd Generation Partnership Project (3GPP) urban microcell (UMi) channel model with random drops of users against a state-of-the-art baseline shows that the proposed method enables up to 8 dB gains in false negative rate (FNR) as well as significant gains in false positive rate (FPR) and ToA and CFO estimation accuracy. Moreover, our simulations indicate that the proposed algorithm enables gains over a wide range of channel conditions, CFOs, and transmission probabilities. The introduced synchronization method operates at the base station (BS) and, therefore, introduces no additional complexity on the user devices. It could lead to an extension of battery lifetime by reducing the preamble length or the transmit power. Our code is available at: https://github.com/NVlabs/nprach_synch/., Comment: Our code is available at: https://github.com/NVlabs/nprach_synch/

Sionna is a GPU-accelerated open-source library for link-level simulations based on TensorFlow. It enables the rapid prototyping of complex communication system architectures and provides native support for the integration of neural networks. Sionna implements a wide breadth of carefully tested state-of-the-art algorithms that can be used for benchmarking and end-to-end performance evaluation. This allows researchers to focus on their research, making it more impactful and reproducible, while saving time implementing components outside their area of expertise. This white paper provides a brief introduction to Sionna, explains its design principles and features, as well as future extensions, such as integrated ray tracing and custom CUDA kernels. We believe that Sionna is a valuable tool for research on next-generation communication systems, such as 6G, and we welcome contributions from our community., Comment: 5 pages, 1 figure, 4 code listings

In orthogonal frequency division multiplexing (OFDM)-based wireless communication systems, the bit error rate (BER) performance is heavily dependent on the accuracy of channel estimation. It is important for a good channel estimator to be capable of handling the changes in the wireless channel conditions that occur due to the mobility of the users. In recent years, the focus has been on developing complex neural network (NN)- based channel estimators that enable an error performance close to that of a genie-aided channel estimator. This work considers the other alternative which is to have a simple channel estimator but a more complex NN-based demapper for the generation of soft information for each transmitted bit. In particular, the problem of reversing the adverse effects of an imperfect channel estimator is addressed, and a convolutional self-attention-based neural demapper that significantly outperforms the baseline is proposed.

Machine learning (ML) has shown great promise in optimizing various aspects of the physical layer processing in wireless communication systems. In this paper, we use ML to learn jointly the transmit waveform and the frequency-domain receiver. In particular, we consider a scenario where the transmitter power amplifier is operating in a nonlinear manner, and ML is used to optimize the waveform to minimize the out-of-band emissions. The system also learns a constellation shape that facilitates pilotless detection by the simultaneously learned receiver. The simulation results show that such an end-to-end optimized system can communicate data more accurately and with less out-of-band emissions than conventional systems, thereby demonstrating the potential of ML in optimizing the air interface. To the best of our knowledge, there are no prior works considering the power amplifier induced emissions in an end-to-end learned system. These findings pave the way towards an ML-native air interface, which could be one of the building blocks of 6G.

An attractive research direction for future communication systems is the design of new waveforms that can both support high throughputs and present advantageous signal characteristics. Although most modern systems use orthogonal frequency-division multiplexing (OFDM) for its efficient equalization, this waveform suffers from multiple limitations such as a high adjacent channel leakage ratio (ACLR) and high peak-to-average power ratio (PAPR). In this paper, we propose a learning-based method to design OFDM-based waveforms that satisfy selected constraints while maximizing an achievable information rate. To that aim, we model the transmitter and the receiver as convolutional neural networks (CNNs) that respectively implement a high-dimensional modulation scheme and perform the detection of the transmitted bits. This leads to an optimization problem that is solved using the augmented Lagrangian method. Evaluation results show that the end-to-end system is able to satisfy target PAPR and ACLR constraints and allows significant throughput gains compared to a tone reservation (TR) baseline. An additional advantage is that no dedicated pilots are needed.

We propose a learning-based method for the joint design of a transmit and receive filter, the constellation geometry and associated bit labeling, as well as a neural network (NN)-based detector. The method maximizes an achievable information rate, while simultaneously satisfying constraints on the adjacent channel leakage ratio (ACLR) and peak-to-average power ratio (PAPR). This allows control of the tradeoff between spectral containment, peak power, and communication rate. Evaluation on an additive white Gaussian noise (AWGN) channel shows significant reduction of ACLR and PAPR compared to a conventional baseline relying on quadrature amplitude modulation (QAM) and root-raised-cosine (RRC), without significant loss of information rate. When considering a 3rd Generation Partnership Project (3GPP) multipath channel, the learned waveform and neural receiver enable competitive or higher rates than an orthogonal frequency division multiplexing (OFDM) baseline, while reducing the ACLR by 10 dB and the PAPR by 2 dB. The proposed method incurs no additional complexity on the transmitter side and might be an attractive tool for waveform design of beyond-5G systems.

Machine learning (ML) can be used in various ways to improve multi-user multiple-input multiple-output (MU-MIMO) receive processing. Typical approaches either augment a single processing step, such as symbol detection, or replace multiple steps jointly by a single neural network (NN). These techniques demonstrate promising results but often assume perfect channel state information (CSI) or fail to satisfy the interpretability and scalability constraints imposed by practical systems. In this paper, we propose a new strategy which preserves the benefits of a conventional receiver, but enhances specific parts with ML components. The key idea is to exploit the orthogonal frequency-division multiplexing (OFDM) signal structure to improve both the demapping and the computation of the channel estimation error statistics. Evaluation results show that the proposed ML-enhanced receiver beats practical baselines on all considered scenarios, with significant gains at high speeds.

Orthogonal frequency-division multiplexing (OFDM) is widely used in modern wireless networks thanks to its efficient handling of multipath environment. However, it suffers from a poor peak-to-average power ratio (PAPR) which requires a large power backoff, degrading the power amplifier (PA) efficiency. In this work, we propose to use a neural network (NN) at the transmitter to learn a high-dimensional modulation scheme allowing to control the PAPR and adjacent channel leakage ratio (ACLR). On the receiver side, a NN-based receiver is implemented to carry out demapping of the transmitted bits. The two NNs operate on top of OFDM, and are jointly optimized in and end-to-end manner using a training algorithm that enforces constraints on the PAPR and ACLR. Simulation results show that the learned waveforms enable higher information rates than a tone reservation baseline, while satisfying predefined PAPR and ACLR targets.

As communication systems are foreseen to enable new services such as joint communication and sensing and utilize parts of the sub-THz spectrum, the design of novel waveforms that can support these emerging applications becomes increasingly challenging. We present in this work an end-to-end learning approach to design waveforms through joint learning of pulse shaping and constellation geometry, together with a neural network (NN)-based receiver. Optimization is performed to maximize an achievable information rate, while satisfying constraints on out-of-band emission and power envelope. Our results show that the proposed approach enables up to orders of magnitude smaller adjacent channel leakage ratios (ACLRs) with peak-to-average power ratios (PAPRs) competitive with traditional filters, without significant loss of information rate on an additive white Gaussian noise (AWGN) channel, and no additional complexity at the transmitter.

Orthogonal frequency division multiplexing (OFDM) is one of the dominant waveforms in wireless communication systems due to its efficient implementation. However, it suffers from a loss of spectral efficiency as it requires a cyclic prefix (CP) to mitigate inter-symbol interference (ISI) and pilots to estimate the channel. We propose in this work to address these drawbacks by learning a neural network (NN)-based receiver jointly with a constellation geometry and bit labeling at the transmitter, that allows CP-less and pilotless communication on top of OFDM without a significant loss in bit error rate (BER). Our approach enables at least 18% throughput gains compared to a pilot and CP-based baseline, and at least 4% gains compared to a system that uses a neural receiver with pilots but no CP., Comment: arXiv admin note: substantial text overlap with arXiv:2009.05261

Machine learning (ML) starts to be widely used to enhance the performance of multi-user multiple-input multiple-output (MU-MIMO) receivers. However, it is still unclear if such methods are truly competitive with respect to conventional methods in realistic scenarios and under practical constraints. In addition to enabling accurate signal reconstruction on realistic channel models, MU-MIMO receive algorithms must allow for easy adaptation to a varying number of users without the need for retraining. In contrast to existing work, we propose an ML-enhanced MU-MIMO receiver that builds on top of a conventional linear minimum mean squared error (LMMSE) architecture. It preserves the interpretability and scalability of the LMMSE receiver, while improving its accuracy in two ways. First, convolutional neural networks (CNNs) are used to compute an approximation of the second-order statistics of the channel estimation error which are required for accurate equalization. Second, a CNN-based demapper jointly processes a large number of orthogonal frequency-division multiplexing (OFDM) symbols and subcarriers, which allows it to compute better log likelihood ratios (LLRs) by compensating for channel aging. The resulting architecture can be used in the up- and downlink and is trained in an end-to-end manner, removing the need for hard-to-get perfect channel state information (CSI) during the training phase. Simulation results demonstrate consistent performance improvements over the baseline which are especially pronounced in high mobility scenarios., Comment: 15 pages

Each generation of cellular communication systems is marked by a defining disruptive technology of its time, such as orthogonal frequency division multiplexing (OFDM) for 4G or Massive multiple-input multiple-output (MIMO) for 5G. Since artificial intelligence (AI) is the defining technology of our time, it is natural to ask what role it could play for 6G. While it is clear that 6G must cater to the needs of large distributed learning systems, it is less certain if AI will play a defining role in the design of 6G itself. The goal of this article is to paint a vision of a new air interface which is partially designed by AI to enable optimized communication schemes for any hardware, radio environment, and application., Comment: 7 pages, 6 figures, accepted for publication in the IEEE Communications Magazine

Previous studies have demonstrated that end-to-end learning enables significant shaping gains over additive white Gaussian noise (AWGN) channels. However, its benefits have not yet been quantified over realistic wireless channel models. This work aims to fill this gap by exploring the gains of end-to-end learning over a frequency- and time-selective fading channel using orthogonal frequency division multiplexing (OFDM). With imperfect channel knowledge at the receiver, the shaping gains observed on AWGN channels vanish. Nonetheless, we identify two other sources of performance improvements. The first comes from a neural network (NN)-based receiver operating over a large number of subcarriers and OFDM symbols which allows to significantly reduce the number of orthogonal pilots without loss of bit error rate (BER). The second comes from entirely eliminating orthognal pilots by jointly learning a neural receiver together with either superimposed pilots (SIPs), linearly combined with conventional quadrature amplitude modulation (QAM), or an optimized constellation geometry. The learned geometry works for a wide range of signal-to-noise ratios (SNRs), Doppler and delay spreads, has zero mean and does hence not contain any form of superimposed pilots. Both schemes achieve the same BER as the pilot-based baseline with around 7% higher throughput. Thus, we believe that a jointly learned transmitter and receiver are a very interesting component for beyond-5G communication systems which could remove the need and associated control overhead for demodulation reference signals (DMRSs).

We introduce a trainable coded modulation scheme that enables joint optimization of the bit-wise mutual information (BMI) through probabilistic shaping, geometric shaping, bit labeling, and demapping for a specific channel model and for a wide range of signal-to-noise ratios (SNRs). Compared to probabilistic amplitude shaping (PAS), the proposed approach is not restricted to symmetric probability distributions, can be optimized for any channel model, and works with any code rate $k/m$, $m$ being the number of bits per channel use and $k$ an integer within the range from $1$ to $m-1$. The proposed scheme enables learning of a continuum of constellation geometries and probability distributions determined by the SNR. Additionally, the PAS architecture with Maxwell-Boltzmann (MB) as shaping distribution was extended with a neural network (NN) that controls the MB shaping of a quadrature amplitude modulation (QAM) constellation according to the SNR, enabling learning of a continuum of MB distributions for QAM. Simulations were performed to benchmark the performance of the proposed joint probabilistic and geometric shaping scheme on additive white Gaussian noise (AWGN) and mismatched Rayleigh block fading (RBF) channels.

Optimal symbol detection for multiple-input multiple-output (MIMO) systems is known to be an NP-hard problem. Conventional heuristic algorithms are either too complex to be practical or suffer from poor performance. Recently, several approaches tried to address those challenges by implementing the detector as a deep neural network. However, they either still achieve unsatisfying performance on practical spatially correlated channels, or are computationally demanding since they require retraining for each channel realization. In this work, we address both issues by training an additional neural network (NN), referred to as the hypernetwork, which takes as input the channel matrix and generates the weights of the neural NN-based detector. Results show that the proposed approach achieves near state-of-the-art performance without the need for re-training.

We consider a trainable point-to-point communication system, where both transmitter and receiver are implemented as neural networks (NNs), and demonstrate that training on the bit-wise mutual information (BMI) allows seamless integration with practical bit-metric decoding (BMD) receivers, as well as joint optimization of constellation shaping and labeling. Moreover, we present a fully differentiable neural iterative demapping and decoding (IDD) structure which achieves significant gains on additive white Gaussian noise (AWGN) channels using a standard 802.11n low-density parity-check (LDPC) code. The strength of this approach is that it can be applied to arbitrary channels without any modifications. Going one step further, we show that careful code design can lead to further performance improvements. Lastly, we show the viability of the proposed system through implementation on software-defined radios (SDRs) and training of the end-to-end system on the actual wireless channel. Experimental results reveal that the proposed method enables significant gains compared to conventional techniques., Comment: submitted to IEEE TCOM

The choice of constellations largely affects the performance of communication systems. When designing constellations, both the locations and probability of occurrence of the points can be optimized. These approaches are referred to as geometric and probabilistic shaping, respectively. Usually, the geometry of the constellation is fixed, e.g., quadrature amplitude modulation (QAM) is used. In such cases, the achievable information rate can still be improved by probabilistic shaping. In this work, we show how autoencoders can be leveraged to perform probabilistic shaping of constellations. We devise an information-theoretical description of autoencoders, which allows learning of capacity-achieving symbol distributions and constellations. Recently, machine learning techniques to perform geometric shaping were proposed. However, probabilistic shaping is more challenging as it requires the optimization of discrete distributions. Furthermore, the proposed method enables joint probabilistic and geometric shaping of constellations over any channel model. Simulation results show that the learned constellations achieve information rates very close to capacity on an additive white Gaussian noise (AWGN) channel and outperform existing approaches on both AWGN and fading channels., Comment: Accepted for presentation at the IEEE GLOBECOM 2019

There is a recent interest in neural network (NN)-based communication algorithms which have shown to achieve (beyond) state-of-the-art performance for a variety of problems or lead to reduced implementation complexity. However, most work on this topic is simulation based and implementation on specialized hardware for fast inference, such as field-programmable gate arrays (FPGAs), is widely ignored. In particular for practical uses, NN weights should be quantized and inference carried out by a fixed-point instead of floating-point system, widely used in consumer class computers and graphics processing units (GPUs). Moving to such representations enables higher inference rates and complexity reductions, at the cost of precision loss. We demonstrate that it is possible to implement NN-based algorithms in fixed-point arithmetic with quantized weights at negligible performance loss and with hardware complexity compatible with practical systems, such as FPGAs and application-specific integrated circuits (ASICs).