In this paper, we present a novel neural architecture for 5G channel estimation (CE), the Recurrent Equivariant UERS Estimation Network (ReQuestNet). It incorporates several practical considerations in wireless communication systems, such as ability to handle variable number of resource block (RB), dynamic number of transmit layers, physical resource block groups (PRGs) bundling size (BS), demodulation reference signal (DMRS) patterns with a single unified model, thereby, drastically simplifying the CE pipeline. Besides it addresses several limitations of the legacy linear minimum mean squared error (MMSE) solutions, for example, by being independent of other reference signals and particularly by jointly processing multiple input multiple output (MIMO) layers and differently precoded channels, unknown at the receiver. ReQuestNet comprises of two sub-units, CoarseNet followed by RefinementNet. CoarseNet performs per PRG, per transmit-receive (Tx-Rx) stream channel estimation, while RefinementNet refines the CoarseNet channel estimate by incorporating correlations across differently precoded PRGs, and correlation across MIMO channel spatial dimensions (cross-MIMO). The simulation results show that ReQuestNet outperforms genie MMSE across various channel profiles as well as unseen channel profiles during training, achieving up to 10dB gain at high signal-to-noise ration (SNR).

In the context of communication networks, digital twin technology provides a means to replicate the radio frequency (RF) propagation environment as well as the system behaviour, allowing for a way to optimize the performance of a deployed system based on simulations. One of the key challenges in the application of Digital Twin technology to mmWave systems is the prevalent channel simulators' stringent requirements on the accuracy of the 3D Digital Twin, reducing the feasibility of the technology in real applications. We propose a practical Digital Twin creation pipeline and a channel simulator, that relies only on a single mounted camera and position information. We demonstrate the performance benefits compared to methods that do not explicitly model the 3D environment, on downstream subtasks in beam acquisition, using the real-world dataset of the DeepSense6G challenge.

In terahertz (THz) massive multiple-input multiple-output (MIMO) systems, the combination of huge bandwidth and massive antennas results in severe beam split, thus making the conventional phase-shifter based hybrid precoding architecture ineffective. With the incorporation of true-time-delay (TTD) lines in the hardware implementation of the analog precoders, delay-phase precoding (DPP) emerges as a promising architecture to effectively overcome beam split. However, existing DPP approaches suffer from poor performance, high complexity, and weak robustness in practical THz channels. In this paper, we propose a novel DPP approach in wideband THz massive MIMO systems. First, the matrix decomposition optimization problem is converted into a compressive sensing (CS) form, which can be solved by the proposed extended spatially sparse precoding (SSP) algorithm. To compensate for beam split, frequency-dependent measurement matrices are designed, which can be approximately realized by feasible phase and delay codebooks. Furthermore, several efficient atom selection techniques are developed to further reduce the complexity of the extended SSP algorithm. In simulation, the proposed DPP approach achieves superior performance, complexity, and robustness by using it alone or in combination with existing DPP approaches under various settings.

Estimating path loss for a transmitter-receiver location is key to many use-cases including network planning and handover. Machine learning has become a popular tool to predict wireless channel properties based on map data. In this work, we present a transformer-based neural network architecture that enables predicting link-level properties from maps of various dimensions and from sparse measurements. The map contains information about buildings and foliage. The transformer model attends to the regions that are relevant for path loss prediction and, therefore, scales efficiently to maps of different size. Further, our approach works with continuous transmitter and receiver coordinates without relying on discretization. In experiments, we show that the proposed model is able to efficiently learn dominant path losses from sparse training data and generalizes well when tested on novel maps.

Hybrid analog-digital (HAD) architecture is widely adopted in practical millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems to reduce hardware cost and energy consumption. However, channel estimation in the context of HAD is challenging due to only limited radio frequency (RF) chains at transceivers. Although various compressive sensing (CS) algorithms have been developed to solve this problem by exploiting inherent channel sparsity and sparsity structures, practical effects, such as power leakage and beam squint, can still make the real channel features deviate from the assumed models and result in performance degradation. Besides, the high complexity of CS algorithms caused by a large number of iterations hinders their applications in practice. To tackle these issues, we develop a deep learning (DL)-based channel estimation approach where the sparse Bayesian learning (SBL) algorithm is unfolded into a deep neural network (DNN). In each SBL layer, Gaussian variance parameters of the sparse angular domain channel are updated by a tailored DNN, which is able to capture complicated channel sparsity structures in various domains effectively and efficiently. The measurement matrix is jointly optimized for performance improvement. Then, the proposed approach is extended to the multi-block case where channel correlation in time is further exploited to adaptively predict the measurement matrix and facilitate the update of variance parameters. Simulation results show that the proposed approaches outperform existing approaches in terms of both performance and complexity.

Analog beamforming is the predominant approach for millimeter wave (mmWave) communication given its favor-able characteristics for limited-resource devices. In this work, we aim at reducing the spectral efficiency gap between analog and digital beamforming methods. We propose a method for refined beam selection based on the estimated raw channel. The channel estimation, an underdetermined problem, is solved using compressed sensing (CS) methods leveraging angular domain sparsity of the channel. To reduce the complexity of CS methods, we propose dictionary learning iterative soft-thresholding algorithm, which jointly learns the sparsifying dictionary and signal reconstruction. We evaluate the proposed method on a realistic mm Wave setup and show considerable performance improvement with respect to code-book based analog beamforming approaches.

The highly directional nature of mmWave channels results in a mutlipath incoming signal, often with varying power levels. To exploit the complete diversity of this channel, beamformer design should incorporate this multipath. This increases pilot overhead for initial access. However, low latency mmWave signalling protocols require minimal pilot transmission. Additionally, practical system implementations of beamformers use low-complexity phase-shifter (PS) beamformers. Balancing performance, latency and hardware constraints, active learning has proven to be an extremely effective strategy for initial channel access. However, modern active learning algorithms are tailored to line-of-sight (LoS) angular estimation and tracking. We address multipath beamformer design via deep learning, which is increasingly used for channel estimation and end-to-end communication. We develop two novel deep neural networks (DNN) for multipath beamformer learning: (i) Deep Unfolded Beamformer Learning and (ii) Deep Recurrent Beamformer Learning. Our approach improves on active learning for LoS paths by utilizing multipath diversity for increased reference signal received power (RSRP).

We present a neural network architecture for jointly learning user locations and environment mapping up to isometry, in an unsupervised way, from channel state information (CSI) values with no location information. The model is based on an encoder-decoder architecture. The encoder network maps CSI values to the user location. The decoder network models the physics of propagation by parametrizing the environment using virtual anchors. It aims at reconstructing, from the encoder output and virtual anchor location, the set of time of flights (ToFs) that are extracted from CSI using super-resolution methods. The neural network task is set prediction and is accordingly trained end-to-end. The proposed model learns an interpretable latent, i.e., user location, by just enforcing a physics-based decoder. It is shown that the proposed model achieves sub-meter accuracy on synthetic ray tracing based datasets with single anchor SISO setup while recovering the environment map up to 4cm median error in a 2D environment and 15cm in a 3D environment.

We propose generative channel modeling to learn statistical channel models from channel input-output measurements. Generative channel models can learn more complicated distributions and represent the field data more faithfully. They are tractable and easy to sample from, which can potentially speed up the simulation rounds. To achieve this, we leverage advances in generative adversarial network (GAN), which helps us learn an implicit distribution over stochastic MIMO channels from observed measurements. In particular, our approach MIMO-GAN implicitly models the wireless channel as a distribution of time-domain band-limited impulse responses. We evaluate MIMO-GAN on 3GPP TDL MIMO channels and observe high-consistency in capturing power, delay and spatial correlation statistics of the underlying channel. In particular, we observe MIMO-GAN achieve errors of under 3.57 ns average delay and -18.7 dB power.

We propose Hypernetwork Kalman Filter (HKF) for tracking applications with multiple different dynamics. The HKF combines generalization power of Kalman filters with expressive power of neural networks. Instead of keeping a bank of Kalman filters and choosing one based on approximating the actual dynamics, HKF adapts itself to each dynamics based on the observed sequence. Through extensive experiments on CDL-B channel model, we show that the HKF can be used for tracking the channel over a wide range of Doppler values, matching Kalman filter performance with genie Doppler information. At high Doppler values, it achieves around 2dB gain over genie Kalman filter. The HKF generalizes well to unseen Doppler, SNR values and pilot patterns unlike LSTM, which suffers from severe performance degradation.

We consider the problem of training User Verification (UV) models in federated setup, where each user has access to the data of only one class and user embeddings cannot be shared with the server or other users. To address this problem, we propose Federated User Verification (FedUV), a framework in which users jointly learn a set of vectors and maximize the correlation of their instance embeddings with a secret linear combination of those vectors. We show that choosing the linear combinations from the codewords of an error-correcting code allows users to collaboratively train the model without revealing their embedding vectors. We present the experimental results for user verification with voice, face, and handwriting data and show that FedUV is on par with existing approaches, while not sharing the embeddings with other users or the server.

Among the three 5G scenarios identified by ITU-R, massive MTC poses very challenging uplink design target which requires the simultaneous support of enhanced coverage, long battery life and massive connection density. During the 5G Release 14 study phase in 3GPP, the working group studied the Non-Orthogonal Multiple Access (NOMA) scheme which can improve link budget and increase user density with the cost of complex user detection scheme. Among all the candidates, Resource Spread Multiple Access (RSMA) scheme shows promising performance gain without introducing too much complexity on the receiver design. In this paper, we briefly review the RSMA scheme. For the link level performance analysis, we firstly analyze and compare the link budget among RSMA, TDMA, and FDMA to find where the gain for RSMA comes from. Meanwhile, we provide preliminary results to justify the gains compared with OMA scheme. On system design, we review the whole procedure and propose to use user centric mobility and grant free to improve the system efficiency along with NOMA.

For an existing macro-cell wireless network deployment, it is shown how distributed antenna systems (DAS) can be added to improve the capacity. This is demonstrated through a set of experiments using a cdma2000 1xEV-DO outdoor test network on licensed spectrum with commercial reference devices and infrastructure equipment. DAS was used to add small cell sites at locations consistent with right-of-way deployments (e.g., light poles, traffic lights), and cell sites were added within both the interior and handoff regions of the existing macro network. For the case where the small cells were enabled as pico-cells, significant gains in capacity were found as a result of the cell- splitting and offloading of traffic demand onto the DAS sites, as well as the improved coverage within nearby buildings. Furthermore, when the smalls cells were configured to allow for centralized processing, additional performance gains were measured (1) when the downlink admits simultaneous transmission of pilot and data across remote sites, as well as for (2) when the uplink allows soft combining and interference cancellation across remote sites. These results were achieved using commercially available equipment at the DAS hub.

In this paper, we study the potential benefit of base-station (BS) cooperation for downlink transmission in a modified Wyner-type multicell model. Besides the dirty-paper-coding (DPC) precoder, we also analyze several linear precoding schemes, including co-phasing, zero-forcing (ZF) and MMSE precoders. For the nonfading case, analytical sum rate expression is obtained for each scheme. In networks of a large number N of cells, a high signal-to-noise-ratio (SNR) asymptotic gap is shown between the sum rate performances of DPC and ZF precoders. Moreover, the MMSE precoder sum rate expression in large networks indicates different behaviors of MMSE precoder in different SNR regimes: in the SNR > N2regime, it coincides with the ZF precoder, while, in the SNR2regime, it coincides with the co-phasing precoder. For the Rayleigh fading case, Monte-Carlo simulations demonstrate the effectiveness of linear precoding schemes with the proposed user selection criterion.

By examining the achievable rates of a multistage decoding system on stationary ergodic channels, we derive lower bounds on the mutual information rate corresponding to independent and uniformly distributed (i.u.d.) inputs, also referred to as the i.u.d. information rate. For binary intersymbol interference (ISI) channels, we show that these bounds become tight as the number of decoding stages increases. Our analysis, which focuses on the marginal conditional output densities at each stage of decoding, provides an information rate corresponding to each stage. These rates underlie the design of multilevel coding schemes, based upon low-density parity-check (LDPC) codes and message passing, that in combination with multistage decoding approach the i.u.d. information rate for binary ISI channels. We give example constructions for channel models that have been commonly used in magnetic recording. These examples demonstrate that the technique is very effective even for a small number of decoding stages

A general framework is provided to characterize the link level performance of CDMA systems with interference cancellation. This closed-form residual power analysis accounts for the impact of channel estimation errors due to SNR, channel variation, chip asynchronism, and filter mismatch. Simulations further quantify the link level cancellation performance on more realistic sub-chip multipath channels. This work demonstrates that properly designed channel estimation and signal reconstruction techniques achieve high cancellation efficiency over a variety of multipath fading channels.

This paper addresses the network level aspects of incorporating interference cancellation into the CDMA2000 1xEV-DO Revision A reverse link. We illustrate how a physical layer analysis of interference cancellation can be applied to an extensive network simulation environment that models inter-cell interference, hybrid-ARQ, multipath fading channels and the MAC-layer dynamics of power control, rate allocation, and rise- over-thermal control. An investigation of reverse link pilot channel performance and rise-over-thermal distribution shows that interference cancellation can be added to the base station processing without modifying the overall network operation or system stability. Network simulation results demonstrate how interference cancellation increases the data rate of each user to significantly improve the throughput achieved with both 2 and 4 receiver antennas per sector.

The achievable information rates for multilevel coding (MLC) systems with multistage decoding (MSD) are examined on two-dimensional binary-input intersymbol interference (ISI) channels. One MSD scheme employs trellis-based detection, while another involves zero-forcing equalization and linear noise prediction. Information rates are determined by examining the output statistics at each stage of MSD. The first scheme is shown to achieve rates very close to known information-theoretic limits. Systems with low-density parity-check codes are then optimized to approach these rates

We present a near-capacity coding system for higher-order partial-response channels, consisting of an outer set of interleaved low-density parity-check codes, an inner rate-1 shaping code, and a multistage decoder. The inner shaping code, which may be noninvertible, is designed to generate an output process similar to a binary Markov process that maximizes the mutual information for a given order. On the EPR4 channel, our system exhibits an iterative decoding threshold and a simulation BER of 10/sup -5/ within 0.19 and 0.33 dB, respectively, of the information-theoretic limit for a third-order input process.

For a discrete-time, binary-input, Gaussian channel with finite intersymbol interference, we prove that reliable communication can be achieved if, and only if, E/sub b//N/sub 0/>log2/G/sub opt/, for some constant G/sub opt/ that depends on the channel. To determine this constant, we consider the finite-state machine which represents the output sequences of the channel filter when driven by binary inputs. We then define G/sub opt/ as the maximum output power achieved by a simple cycle in this graph, and show that no other cycle or asymptotically long sequence can achieve an output power greater than this. We provide examples where the binary input constraint leads to a suboptimality, and other cases where binary signaling is just as effective as real signaling at very low signal-to-noise ratios.

In this paper, we present two simple Monte Carlo methods for estimating the achievable information rates of general finite state channels. Both methods require only the ability to simulate the channel with an a posteriori probability (APP) detector matched to the channel. The first method estimates the mutual information rate between the input random process and the output random process, provided that both processes are stationary and ergodic. When the inputs are iid equiprobable, this rate is known as the Symmetric Information Rate (SIR). The second method estimates the achievable information rate of an explicit coding system which interleaves m independent codes onto the channel and employs multistage decoding. For practical values of m, numerical results show that this system nearly achieves the SIR. Both methods are applied to the class of partial response channels commonly used in magnetic recording.