Millimeter wave (mmWave) communication is a key component of 5G systems and beyond. Such systems provide high bandwidth and high data rate but are sensitive to blockages. A sudden blockage in the line of sight (LOS) link leads to abrupt disconnection. Thus addressing blockage problems is essential for enhancing the reliability and latency of mmWave communication networks. In this paper, we propose a novel solution that relies only on in-band mmWave wireless measurements to proactively predict future dynamic line-of-sight (LOS) link blockages. The proposed solution utilizes deep neural networks and special patterns of received signal power, which we call pre-blockage wireless signatures, to infer future blockages. Specifically, the machine learning models attempt to predict: (i) Whether a blockage will occur in the next few seconds? (ii) At what time instance will this blockage occur? To evaluate our proposed approach, we build a mmWave communication setup with moving blockage in an indoor scenario and collect received power sequences. Simulation results on a real dataset show that blockage occurrence can be predicted with more than 85% accuracy, and the exact time instance of blockage occurrence can be obtained with less than 2 time instances (1.66s) error for prediction interval of 10 time instances (8.8s). This demonstrates the potential of the proposed solution for dynamic blockage prediction and proactive hand-off.

Millimeter wave (mmWave) and massive MIMO systems are intrinsic components of 5G and beyond. These systems rely on using beamforming codebooks for both initial access and data transmission. Current beam codebooks, however, generally consist of a large number of narrow beams that scan all possible directions, leading to large training overhead. Further, these codebooks do not normally account for hardware impairments or possible non-uniform array geometries, and their calibration process is expensive. To overcome these limitations, this paper develops an efficient online machine learning framework that learns how to adapt the codebook beam patterns to the specific deployment, surrounding environment, user distribution, and hardware characteristics. This is done by designing a novelcomplex-valued neural networkarchitecture in which the neuron weights directly model the beamforming weights of the analog phase shifters, accounting for the key hardware constraints. This model learns the codebook beams through online and self-supervised training avoiding the need for explicit channel state information. This respects the practical situations where the channel is imperfect or hard to obtain. Simulation results highlight the capability of the proposed solution in learning environment and hardware aware beam codebooks, which reduce the training overhead and improve the robustness against possible hardware impairments.

Millimeter wave (mmWave) and terahertz MIMO systems rely on pre-defined beamforming codebooks for both initial access and data transmission. These pre-defined codebooks, however, are commonly not optimized for specific environments, user distributions, and/or possible hardware impairments. This leads to large codebook sizes with high beam training overhead which makes it hard for these systems to support highly mobile applications. To overcome these limitations, this paper develops a deep reinforcement learning framework that learns how to optimize the codebook beam patterns relying only on the receive power measurements. The developed model learns how to adapt the beam patterns based on the surrounding environment, user distribution, hardware impairments, and array geometry. Further, this approach does not require any knowledge about the channel, RF hardware, or user positions. To reduce the learning time, the proposed model designs a novelWolpertinger-variant architecture that is capable of efficiently searching the large discrete action space. The proposed learning framework respects the RF hardware constraints such as the constant-modulus and quantized phase shifter constraints. Simulation results confirm the ability of the developed framework to learn near-optimal beam patterns for line-of-sight (LOS), non-LOS (NLOS), mixed LOS/NLOS scenarios and for arrays with hardware impairments without requiring any channel knowledge.

This paper investigates a novel research direction that leverages vision to help overcome the critical wireless communication challenges. In particular, this paper considers millimeter wave (mmWave) communication systems, which are principal components of 5G and beyond. These systems face two important challenges: (i) the large training overhead associated with selecting the optimal beam and (ii) the reliability challenge due to the high sensitivity to link blockages. Interestingly, most of the devices that employ mmWave arrays will likely also use cameras, such as 5G phones, self-driving vehicles, and virtual/augmented reality headsets. Therefore, we investigate the potential gains of employing cameras at the mmWave base stations and leveraging their visual data to help overcome the beam selection and blockage prediction challenges. To do that, this paper exploits computer vision and deep learning tools to predict mmWave beams and blockages directly from the camera RGB images and the sub-6GHz channels. The experimental results reveal interesting insights into the effectiveness of such solutions. For example, the deep learning model is capable of achieving over 90% beam prediction accuracy, which only requires snapping a shot of the scene and zero overhead.

The growing role artificial intelligence and specifically machine learning is playing in shaping the future of wireless communications has opened up many new and intriguing research directions. This paper motivates the research in the novel direction of vision-aided wireless communications, which aims at leveraging visual sensory information in tackling wireless communication problems. Like any new research direction driven by machine learning, obtaining a development dataset poses the first and most important challenge to vision-aided wireless communications. This paper addresses this issue by introducing the Vision-Wireless (ViWi) dataset framework. It is developed to be a parametric, systematic, and scalable data generation framework. It utilizes advanced 3D-modeling and ray-tracing softwares to generate high-fidelity synthetic wireless and vision data samples for the same scenes. The result is a framework that does not only offer a way to generate training and testing datasets but helps provide a common ground on which the quality of different machine learning-powered solutions could be assessed.

Predicting the millimeter wave (mmWave) beams and blockages using sub-6 GHz channels has the potential of enabling mobility and reliability in scalable mmWave systems. Prior work has focused on extracting spatial channel characteristics at the sub-6 GHz band and then use them to reduce the mmWave beam training overhead. This approach still requires beam refinement at mmWave and does not normally account for the different dielectric properties at the different bands. In this paper, we first prove that under certain conditions, there exist mapping functions that can predict the optimal mmWave beam and blockage status directly from the sub-6 GHz channel. These mapping functions, however, are hard to characterize analytically which motivates exploiting deep neural network models to learn them. For that, we prove that a large enough neural network can predict mmWave beams and blockages with success probabilities that can be made arbitrarily close to one. Then, we develop a deep learning model and empirically evaluate its beam/blockage prediction performance using a publicly available dataset. The results show that the proposed solution can predict the mmWave blockages with more than 90% success probability and can predict the optimal mmWave beams to approach the upper bounds while requiring no beam training overhead.

As a promising candidate for future wireless systems, large intelligent surfaces (LISs) recently emerged to serve considerate improvements in both spectral and energy efficiencies. These surfaces consist of large numbers of passive elements capable of intelligently reflecting the incident signals. Since the LIS employs passive elements, critical challenges are inherent in the channel training/estimation process in order to properly design the LIS reflection matrices. One challenge particularly is how to acquire the channel knowledge with low training overhead and power consumption solutions. In this paper, we first propose an energy-efficient novel LIS architecture where all the LIS elements are passive except few non-uniformly distributed active elements (connected to the baseband). Then, we develop an efficient solution to design the LIS reflection matrices, with negligible training overhead, leveraging deep learning tools. Given what we call environment descriptors, the LIS has the ability to learn the optimal LIS reflection matrices. The simulation results show that the developed solution can approach the optimal upper bound, when only a small fraction of the LIS elements are active, yielding a promising solution for LIS systems from both energy efficiency and training overhead perspectives.

A simple convolutional neural network is proposed in this letter and is trained end-to-end to restore clear images from hazy inputs. The proposed network is generic and agnostic in the sense that it is not designed specifically for image dehazing and, in particular, it has no knowledge of the atmosphere scattering model. Remarkably, this network achieves record-breaking dehazing performance on several standard data sets that are synthesized using the atmosphere scattering model. This surprising finding suggests that there might be a need to rethink the predominant plug-in approach to image dehazing.