Integrated sensing and communication have drawn great research attention in recent years. Specifically, 5G mmWave has demonstrated its capabilities not only in high-speed communications but also in perceiving the physical environment. Apart from providing locationing services for user equipment (UE), 5G mmWave can also estimate the position of target objects that does not carry any equipment (i.e., device-free). Existing works of device-free wireless localization often employs a single monostatic radar or a few transceivers in fixed positions. In this work, we examine a cooperative sensing case, where multiple UEs cooperate with the infrastructure of transmit/receive points (TRPs) to jointly locate device-free objects. This new setting brings in new challenges for existing locationing algorithms as the number and the locations of the UEs and sensing targets are all dynamic. Our work proposes a novel procedure that uses visualization methods to jointly represent the information in the mmWave channel impulse responses and the locations of UEs and TRPs. We then introduce an end-to-end deep learning transformer architecture inspired by popular models in the computer vision domain to estimate the target objects’ locations from the visualizations. On a dataset generated using 3D ray-tracing simulations, our system can locate multiple device-free objects with an average error of 0.47 meters within a 20 meterby-40 meter experiment area.

Ray tracing is one of the de-facto standard method-ologies for radio channel modelling, given the geographical map of the layout. However, the channel generated by ray-tracing cannot be adapted to incorporate knowledge from real-world channel measurements. Several recent papers have proposed training a deep neural network (DNN) to compute the radio map for a given input layout. Such techniques typically require a large number of measurements, transmitters and receivers to generate the dataset needed for training the DNN, and hence can only be trained on simulated data from ray tracing. We propose an extension to these techniques, whereby we first train our DNN on simulated data, and then use a small number of measurements from a given setting to predict the path loss at all locations of interest, borrowing from a generative modelling technique called Deep Image Prior. Our simulations show that Radio DIP can achieve a RMSE of 5 dB in predicting the path loss of 50k outdoor locations, given less than 100 measurements.

Radio signals are well suited for user localization because they are ubiquitous, can operate in the dark and maintain privacy. Many prior works learn mappings between channel state information (CSI) and position fully-supervised. However, that approach relies on position labels which are very expensive to acquire. In this work, this requirement is relaxed by using pseudo-labels during deployment, which are calculated from an inertial measurement unit (IMU). We propose practical algorithms for IMU double integration and training of the localization system. We show decimeter-level accuracy on simulated and challenging real data of 5G measurements. Our IMU-supervised method performs similarly to fully-supervised, but requires much less effort to deploy.

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.

The evolution of massive multiple-input multiple-output (MIMO), such as holographic MIMO and reconfigurable intelligent surface (RIS), is one of the hottest topics in the sixth generation (6G) mobile communication systems. In this area, the network node may be equipped with much more antenna elements and/or transmit-receive units (TxRUs) than its presence in current deployment. To obtain accurate channel estimation for these nodes, using high-density pilot may result in tremendous downlink overhead, so pilot reduction is a key area to investigate. In this work, we design a low-density frequency-aware antenna selection pattern and a transformer (TF)-based channel estimator that is deployed at the user equipment (UE) side to recover the channel. Compared to the two-sided model where the pilot transmission is based on a neural network (NN) that is jointly optimized with the UE side channel estimator, the proposed design is more convenient for practical implementation. The simulation results suggest that our proposed pattern can achieve similar channel estimation performance as the two-sided model and can save 50% pilot overhead compared to the conventional method. Moreover, we demonstrate that our proposed design is robust against different antenna selection patterns.

Intelligent integrated sensing and communication is one of key aspects of future wireless networks in which sensing can be leveraged to enhance communications and vice-versa. In this paper, we propose a novel sensing solution that can be used to represent an RF-environment. The proposed solution accounts for practical challenges such as limited time resolution due to limited bandwidth with no angle measurements while providing robustness to wireless propagation phenomena such as diffraction. Our proposed method leverages offline data collection during RF-mapping, and finds the location of virtual anchors (VAs), i.e., mirror images of a physical anchor w.r.t reflectors, through an iterative process called successive tap removal (STR). Afterwards, machine learning (ML) models are trained to predict dominant multipath components of the received wireless channel at a given location. Found VAs and their associated ML models stand for intermediate entities that represent an RF-environment. As an application, we use the developed models in the context of multipath assisted positioning to improve positioning accuracy in challenging indoor environments with heavy non-line-of-sight (NLoS) conditions. Finally, we extend our ideas to systems with multi-antenna transmitters and show that VA detection accuracy can be improved, bringing higher accuracy to the downstream positioning applications.

Artificial intelligence (AI) or machine learning (ML) based beam prediction is currently studied in the 3rd Generation Partnership Project (3GPP) fifth generation (5G)-Advanced new ratio (NR) standardization for future commercialization and standard evolution towards sixth generation (6G) communications, wherein time domain (TD) beam prediction is an important use case. The targets for such 3GPP studies and standardization are to lower power consumed at user equipment (UE) and reference signal (RS) overhead that are currently needed by frequent beam measurements due to UE rotation and mobility. To meet such targets, in this paper, we investigate AI/ML based algorithms facilitating TD beam prediction suitable for 5G-Advanced beam management (BM), including RS receive power (RSRP) prediction and beam change prediction. The proposed AI/ML algorithms are first evaluated through computer simulations with new UE mobility models based on recent standard evolutions in 3GPP. Then we further present over-the-air test results achieved by such AI/ML algorithms, using based station (BS) and UE compliant with 3GPP standards. Evaluation results show that the proposed schemes can accurately predict future beams and reduce large amount of the power consumed at the UE for BM, which also demonstrate feasibility of AI/ML based BM for 5G-Advanced and future 6G communications.

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.

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 present our study results on the neural network based approaches to the transmitter/receiver design over nonlinear channel. In the first part, we discuss the transmitter design for the peak-to-average power (PAPR) reduction. The algorithm unrolling is applied to a well-known PAPR reduction algorithm. The learning-based approach achieves the performance on par with the classical approach, but at the smaller computational complexity. The second part discusses the joint transmitter/receiver design for the mitigation of the transmitter nonlinearity. It is shown that by combining the neural network with the unfolded algorithm for PAPR reduction at the transmitter and employing the receiver neural network, sizable gain is achieved when the emission criterion is relaxed.

The increasing number of wireless devices operating in unlicensed spectrum motivates the development of intelligent adaptive approaches to spectrum access. We consider decentralized contention-based medium access for base stations (BSs) operating on unlicensed shared spectrum, where each BS autonomously decides whether or not to transmit on a given resource. The contention decision attempts to maximize not its own downlink throughput, but rather a network-wide objective. We formulate this problem as a decentralized partially observable Markov decision process with a novel reward structure that provides long term proportional fairness in terms of throughput. We then introduce a two-stage Markov decision process in each time slot that uses information from spectrum sensing and reception quality to make a medium access decision. Finally, we incorporate these features into a distributed reinforcement learning framework for contention-based spectrum access. Our formulation provides decentralized inference, online adaptability and also caters to partial observability of the environment through recurrent Q-learning. Empirically, we find its maximization of the proportional fairness metric to be competitive with a genie-aided adaptive energy detection threshold, while being robust to channel fading and small contention windows.

Precise positioning in 5G that can enable a wide variety of new use cases. We investigate the problem of accurate line-of-sight (LOS) delay estimation of an observed wireless channel using deep neural networks (NN). These delay estimates are the primary building block for deriving accurate position estimates. Our work proposes a custom super-resolution NN that exploits the properties of the wireless channel to guide the NN design. We compare against traditional algorithms used for LOS detection and show that the proposed NN shows excellent performance in the presence of weak LOS signals and dense multipath; scenarios that are challenging for traditional signal processing algorithms.

We consider a flat fading multiantenna downlink system with a large number of users where the objective is to deliver equal rates to nonoutage users with a low complexity. We show that in the limit of a large number of users, a zero-forcing beamforming strategy combined with a low complexity user grouping algorithm based on a semi-orthogonal user selection achieves asymptotically optimal performance, with respect to an upper bound that can be achieved when no interference is present among users.

In this paper we quantify 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) Release 8 downlink system performance for a macro cell hexagonal grid scenario. The system performance is analyzed for a closed loop Single User Multi-Input Multi Output (SU-MIMO) mode and compared with Single Input Multiple Output (SIMO) and Multi-User (MU) MIMO modes, for a full buffer scenario and static users. In addition to the full buffer scenario, traffic models are considered for SIMO mode to evaluate impact of partial loading and handover. Voice over Internet Protocol (VoIP) system performance is quantified for static users. Mobility simulations are performed for Video Telephony (VT) users and compared to the static case.

We analyze the sum-rate performance of a multi- antenna downlink system carrying more users than transmit antennas, with partial channel knowledge at the transmitter due to finite rate feedback. In order to exploit multiuser diversity, we show that the transmitter must have, in addition to directional information, information regarding the quality of each channel. Such information should reflect both the channel magnitude and the quantization error. Expressions for the SINR distribution and the sum-rate are derived, and tradeoffs between the number of feedback bits, the number of users, and the SNR are observed. In particular, for a target performance, having more users reduces feedback load.

Coverage spectral efficiency (CSE) characterizes the tradeoff between efficient channel reuse and the achievable rates per cell, under the assumption of detection by a single base station and intra-cell FDMA. It is well known that intra-cell FDMA is not in general optimal. In this paper we study an alternative intra- cell wide-band scheme as well as the base station cooperation in detection, which has demonstrated potential capacity gain. The effect on CSE of different schemes are then compared and the optimal reuse distance is determined for each scheme.

We analyze the sum-rate performance of a multi-antenna downlink system carrying more users than transmit antennas, with partial channel knowledge at the transmitter due to finite rate feedback. In order to exploit multiuser diversity, we show that the transmitter must have, in addition to directional information, information regarding the quality of each channel. Such information should reflect both the channel magnitude and the quantization error. Expressions for the SINR distribution and the sum-rate are derived, and tradeoffs between the number of feedback bits, the number of users, and the SNR are observed. In particular, for a target performance, having more users reduces feedback load

Although the capacity of multiple-input/multiple-output (MIMO) broadcast channels (BCs) can be achieved by dirty paper coding (DPC), it is difficult to implement in practical systems. This paper investigates if, for a large number of users, simpler schemes can achieve the same performance. Specifically, we show that a zero-forcing beamforming (ZFBF) strategy, while generally suboptimal, can achieve the same asymptotic sum capacity as that of DPC, as the number of users goes to infinity. In proving this asymptotic result, we provide an algorithm for determining which users should be active under ZFBF. These users are semiorthogonal to one another and can be grouped for simultaneous transmission to enhance the throughput of scheduling algorithms. Based on the user grouping, we propose and compare two fair scheduling schemes in round-robin ZFBF and proportional-fair ZFBF. We provide numerical results to confirm the optimality of ZFBF and to compare the performance of ZFBF and proposed fair scheduling schemes with that of various MIMO BC strategies.

In this correspondence, we investigate the effect of channel estimation error on the capacity of multiple-input-multiple-output (MIMO) fading channels. We study lower and upper bounds of mutual information under channel estimation error, and show that the two bounds are tight for Gaussian inputs. Assuming Gaussian inputs we also derive tight lower bounds of ergodic and outage capacities and optimal transmitter power allocation strategies that achieve the bounds under perfect feedback. For the ergodic capacity, the optimal strategy is a modified waterfilling over the spatial (antenna) and temporal (fading) domains. This strategy is close to optimum under small feedback delays, but when the delay is large, equal powers should be allocated across spatial dimensions. For the outage capacity, the optimal scheme is a spatial waterfilling and temporal truncated channel inversion. Numerical results show that some capacity gain is obtained by spatial power allocation. Temporal power adaptation, on the other hand, gives negligible gain in terms of ergodic capacity, but greatly enhances outage performance.

We consider a multi-user MIMO downlink system employing zero-forcing beamforming (ZFBF) as a spatial multiplexing strategy, and propose low-complexity user subset selection methods based on a clique (fully connected subgraph) search. The proposed algorithms, maximum weighted clique (MWC)-ZFBF and greedy weighted clique (GWC)-ZFBF, are shown to achieve the asymptotic sum-capacity of MIMO downlink channels as the number of users goes to infinity. Thus, clique search based ZFBF is an appealing strategy in MIMO downlink systems with a large number of users.

In MIMO downlink channels, the capacity is achieved by dirty paper coding (DPQ). However, DPC is difficult to implement in practical systems. This work investigates if, for a large number of users, simpler schemes can achieve the same performance. Specifically, we show that a zero-forcing beamforming (ZFBF) strategy, while generally suboptimal, can achieve the same asymptotic sum-rate capacity as that of DPC, as the number of users goes to infinity. In proving this asymptotic result, we propose an algorithm for determining which users should be active in ZFBF transmission. These users are semi-orthogonal to one another, and when fairness among users is required, can be grouped for simultaneous transmissions to enhance the throughput of fair schedulers. We provide numerical results to confirm the optimality of ZFBF and to compare its performance with that of various MIMO downlink strategies.

We investigate ergodic capacities and optimal transmitter strategies in Rayleigh fading multiple input multiple output (MIMO) channels with spatial correlation, when there exist channel uncertainties arising from the combined effect of channel estimation error and limited feedback. We consider both covariance feedback and instantaneous feedback, and formulate optimization problems that determine the capacities and optimal transmitter designs for both cases. In the high SNR regime, the optimal solutions have simple closed form formulas that involve inverting the channel covariance and waterfilling over instantaneous channel gains. Numerical results show that instantaneous feedback gives large capacity gain at low SNR and is also helpful at high SNR. Covariance feedback, on the other hand, seems to give little gain at mid SNR, but is almost as good as instantaneous feedback at high SNR under a reasonable channel estimation quality.

In this paper, we investigate the effect of channel estimation error on the capacity of multiple input multiple output (MIMO) systems in i.i.d. Rayleigh flat-fading channels. We study lower and upper bounds of mutual information under channel estimation error, and show that the two bounds are tight for Gaussian inputs. It is seen that the mutual information increases with the. number of antennas, but is limited by channel estimation error at high SNR. We also derive tight lower bounds of ergodic and outage capacities and optimal transmitter power allocation strategies that achieve the bounds. For the ergodic capacity, the optimal strategy is a modified waterfilling over the spatial (subchannel) and temporal (fading) domain. For the outage capacity, it is a spatial waterfilling and temporal truncated channel inversion. Numerical results show that some capacity gain is obtained by spatial power allocation. Temporal power adaptation, on the other hand, gives negligible gain in terms of ergodic capacity, but greatly enhances outage performance.

We propose a cross-layer design framework for supporting delay-critical traffic over ad hoc wireless networks and analyze its benefits for video streaming. In this framework, link capacities and traffic flows are jointly allocated to minimize the congestion experienced by video packets. The optimal solution, calculated via time sharing among different transmission schemes, concentrates resources only on active links. Experimental results on a simulated network illustrate the advantages of cross-layer design over another method based on oblivious layers. With one path, the cross-layer approach yields a 10-fold gain in supported data rate or equivalently 8.5 dB improvement in PSNR of achievable received video quality. Using 3 paths, the gain is 3-fold in rate or 5 dB in video quality. While multipath routing is essential to high data rate in oblivious-layered design, cross-layer design achieves efficient resource utilization regardless of the number of routes.