Search

In this article, we introduce a method to optimize 5G massive multiple-input multiple-output (mMIMO) connectivity for unmanned aerial vehicles (UAVs) on aerial highways through strategic cell association. UAVs operating in 3D space encounter distinct channel conditions compared to traditional ground user equipment (gUE); under the typical line of sight (LoS) condition, UAVs perceive strong reference signal received power (RSRP) from multiple cells within the network, resulting in a large set of suitable serving cell candidates and in low signal-to-interference-plus-noise ratio (SINR) due to high interference levels. Additionally, a downside of aerial highways is to pack possibly many UAVs along a small portion of space which, when taking into account typical LoS propagation conditions, results in high channel correlation and severely limits spatial multiplexing capabilities. In this paper, we propose a solution to both problems based on the suitable selection of serving cells based on a new metric which differs from the classical terrestrial approaches based on maximum RSRP. We then introduce an algorithm for optimal planning of synchronization signal block (SSB) beams for this set of cells, ensuring maximum coverage and effective management of UAVs cell associations. Simulation results demonstrate that our approach significantly improves the rates of UAVs on aerial highways, up to four times in achievable data rates, without impacting ground user performance.

The sensing and positioning capabilities foreseen in 6G have great potential for technology advancements in various domains, such as future smart cities and industrial use cases. Channel charting has emerged as a promising technology in recent years for radio frequency-based sensing and localization. However, the accuracy of these techniques is yet far behind the numbers envisioned in 6G. To reduce this gap, in this paper, we propose a novel channel charting technique capitalizing on the time of arrival measurements from surrounding Transmission Reception Points (TRPs) along with their locations and leveraging sensor fusion in channel charting by incorporating laser scanner data during the training phase of our algorithm. The proposed algorithm remains self-supervised during training and test phases, requiring no geometrical models or user position ground truth. Simulation results validate the achievement of a sub-meter level localization accuracy using our algorithm 90% of the time, outperforming the state-of-the-art channel charting techniques and the traditional triangulation-based approaches., Comment: This paper is submitted to the Globecom 2024 conference

This work presents a new method for enhancing communication efficiency in stochastic Federated Learning that trains over-parameterized random networks. In this setting, a binary mask is optimized instead of the model weights, which are kept fixed. The mask characterizes a sparse sub-network that is able to generalize as good as a smaller target network. Importantly, sparse binary masks are exchanged rather than the floating point weights in traditional federated learning, reducing communication cost to at most 1 bit per parameter (Bpp). We show that previous state of the art stochastic methods fail to find sparse networks that can reduce the communication and storage overhead using consistent loss objectives. To address this, we propose adding a regularization term to local objectives that acts as a proxy of the transmitted masks entropy, therefore encouraging sparser solutions by eliminating redundant features across sub-networks. Extensive empirical experiments demonstrate significant improvements in communication and memory efficiency of up to five magnitudes compared to the literature, with minimal performance degradation in validation accuracy in some instances

Sixth-generation (6G) mobile communication networks are expected to have dense infrastructures, large antenna size, wide bandwidth, cost-effective hardware, diversified positioning methods, and enhanced intelligence. Such trends bring both new challenges and opportunities for the practical design of 6G. On one hand, acquiring channel state information (CSI) in real time for all wireless links becomes quite challenging in 6G. On the other hand, there would be numerous data sources in 6G containing high-quality location-tagged channel data, e.g., the estimated channels or beams between base station (BS) and user equipment (UE), making it possible to better learn the local wireless environment. By exploiting this new opportunity and for tackling the CSI acquisition challenge, there is a promising paradigm shift from the conventional environment-unaware communications to the new environment-aware communications based on the novel approach of channel knowledge map (CKM). This article aims to provide a comprehensive overview on environment-aware communications enabled by CKM to fully harness its benefits for 6G. First, the basic concept of CKM is presented, followed by the comparison of CKM with various existing channel inference techniques. Next, the main techniques for CKM construction are discussed, including both environment model-free and environment model-assisted approaches. Furthermore, a general framework is presented for the utilization of CKM to achieve environment-aware communications, followed by some typical CKM-aided communication scenarios. Finally, important open problems in CKM research are highlighted and potential solutions are discussed to inspire future work.

Deploying teams of unmanned aerial vehicles (UAVs) to harvest data from distributed Internet of Things (IoT) devices requires efficient trajectory planning and coordination algorithms. Multi-agent reinforcement learning (MARL) has emerged as a solution, but requires extensive and costly real-world training data. To tackle this challenge, we propose a novel model-aided federated MARL algorithm to coordinate multiple UAVs on a data harvesting mission with only limited knowledge about the environment. The proposed algorithm alternates between building an environment simulation model from real-world measurements, specifically learning the radio channel characteristics and estimating unknown IoT device positions, and federated QMIX training in the simulated environment. Each UAV agent trains a local QMIX model in its simulated environment and continuously consolidates it through federated learning with other agents, accelerating the learning process. A performance comparison with standard MARL algorithms demonstrates that our proposed model-aided FedQMIX algorithm reduces the need for real-world training experiences by around three magnitudes while attaining similar data collection performance.

In this paper, we investigate the problem of UAV-aided user localization in wireless networks. Unlike the existing works, we do not assume perfect knowledge of the UAV location, hence we not only need to localize the users but also to track the UAV location. To do so, we utilize the time-of-arrival along with received signal strength radio measurements collected from users using a UAV. A simultaneous localization and mapping (SLAM) framework building on the Expectation-Maximization-based least-squares method is proposed to classify measurements into line-of-sight or non-line-of-sight categories and learn the radio channel, and at the same, localize the users and track the UAV. This framework also allows us to exploit other types of measurements such as the rough estimate of the UAV location available from GPS, and the UAV velocity measured by an inertial measurement unit (IMU) on-board, to achieve better localization accuracy. Moreover, the trajectory of the UAV is optimized which brings considerable improvement to the localization performance. The simulations show the out-performance of the developed algorithm when compared to other approaches.

We study the problem of selecting a subset of vectors from a large set, to obtain the best signal representation over a family of functions. Although greedy methods have been widely used for tackling this problem and many of those have been analyzed under the lens of (weak) submodularity, none of these algorithms are explicitly devised using such a functional property. Here, we revisit the vector-selection problem and introduce a function which is shown to be submodular in expectation. This function does not only guarantee near-optimality through a greedy algorithm in expectation, but also alleviates the existing deficiencies in commonly used matching pursuit (MP) algorithms. We further show the relation between the single-point-estimate version of the proposed greedy algorithm and MP variants. Our theoretical results are supported by numerical experiments for the angle of arrival estimation problem, a typical signal representation task; the experiments demonstrate the benefits of the proposed method with respect to the traditional MP algorithms.

In this work, we propose an UAV-aided Integrated Access and Backhaul (IAB) system design offering 5G connectivity to ground users. UAV is integrated with a distributed unit (DU) acting as an aerial DU, which can provide 5G wireless backhaul access to a terrestrial central unit (CU). The CU-DU interface fully complies with the 3GPP defined F1 application protocol (F1AP). Such aerial DU can be instantiated and configured dynamically, tailoring to the network demands. The complete radio and access network solution is based on open-source software from OpenAirInterface (OAI) and off-the-shelf commercial 5G mobile terminals. Experimental results illustrate throughput gains and coverage extension brought by the aerial DU.

Statistical heterogeneity across clients in a Federated Learning (FL) system increases the algorithm convergence time and reduces the generalization performance, resulting in a large communication overhead in return for a poor model. To tackle the above problems without violating the privacy constraints that FL imposes, personalized FL methods have to couple statistically similar clients without directly accessing their data in order to guarantee a privacy-preserving transfer. In this work, we design user-centric aggregation rules at the parameter server (PS) that are based on readily available gradient information and are capable of producing personalized models for each FL client. The proposed aggregation rules are inspired by an upper bound of the weighted aggregate empirical risk minimizer. Secondly, we derive a communication-efficient variant based on user clustering which greatly enhances its applicability to communication-constrained systems. Our algorithm outperforms popular personalized FL baselines in terms of average accuracy, worst node performance, and training communication overhead., Comment: arXiv admin note: substantial text overlap with arXiv:2110.09869

In this article, we introduce a new metric for driving the serving cell selection process of a swarm of cellular connected unmanned aerial vehicles (CCUAVs) located on aerial highways when served by a massive multiple input multiple output (mMIMO) terrestrial network. Selecting the optimal serving cell from several suitable candidates is not straightforward. By solely relying on the traditional cell selection metric, based on reference signal received power (RSRP), it is possible to result in a scenario in which the serving cell can not multiplex an appropriate number of CCUAVs due to the high correlation in the line of sight (LoS) channels. To overcome such issue, in this work, we introduce a new cell selection metric to capture not only signal strength, but also spatial multiplexing capabilities. The proposed metric highly depends on the relative position between the aerial highways and the antennas of the base station. The numerical analysis indicates that the integration of the proposed new metric allows to have a better signal to interference plus noise ratio (SINR) performance on the aerial highways, resulting in a more reliable cellular connection for CCUAVs., Comment: To be published in IEEE International Conference on Communications Workshop 2023

In mobile networks, unmanned aerial vehicles (UAVs) acting as flying base stations (FlyBSs) can effectively improve performance. Nevertheless, such potential improvement requires an efficient positioning of the FlyBS. In this paper, we study the problem of sum downlink capacity maximization in FlyBS-assisted networks with mobile users and with a consideration of wireless backhaul with channel reuse while a minimum required capacity to every user is guaranteed. The problem is formulated under constraints on the FlyBS's flying speed, propulsion power consumption, and transmission power for both of flying and ground base stations. None of the existing solutions maximizing the sum capacity can be applied due to the combination of these practical constraints. This paper pioneers in an inclusion of all these constraints together with backhaul to derive the optimal 3D positions of the FlyBS and to optimize the transmission power allocation for the channels at both backhaul and access links as the users move over time. The proposed solution is geometrical based, and it shows via simulations a significant increase in the sum capacity (up by 19%-47%) compared with baseline schemes where one or more of the aspects of backhaul communication, transmission power allocation, and FlyBS's positioning are not taken into account., Comment: Accepted in IEEE ICC 2023 Symposium

Deployment of multi-hop network of unmanned aerial vehicles (UAVs) acting as flying base stations (FlyBSs) presents a remarkable potential to effectively enhance the performance of wireless networks. Such potential enhancement, however, relies on an efficient positioning of the FlyBSs as well as a management of resources. In this paper, we study the problem of sum capacity maximization in an extended model for mobile networks where multiple FlyBSs are deployed between the ground base station and the users. Due to an inclusion of multiple hops, the existing solutions for two-hop networks cannot be applied due to the incurred backhaul constraints for each hop. To this end, we propose an analytical approach based on an alternating optimization of the FlyBSs' 3D positions as well as the association of the users to the FlyBSs over time. The proposed optimization is provided under practical constraints on the FlyBS's flying speed and altitude as well as the constraints on the achievable capacity at the backhaul link. The proposed solution is of a low complexity and extends the sum capacity by 23%-38% comparing to state-of-the-art solutions., Comment: Accepted in IEEE GLOBECOM 2022

The use of unmanned aerial vehicles (UAVs) acting as flying base stations (FlyBSs) is considered as an effective tool to improve performance of the mobile networks. Nevertheless, such potential improvement requires an efficient positioning of the FlyBS. In this paper, we maximize the sum downlink capacity of the mobile Internet of Things devices (IoTD) served by the FlyBSs while a minimum required capacity to every device is guaranteed. To this end, we propose a geometrical approach allowing to derive the 3D positions of the FlyBS over time as the IoTDs move and we determine the transmission power allocation for the IoTDs. The problem is formulated and solved under practical constraints on the FlyBS's transmission and propulsion power consumption as well as on flying speed. The proposed solution is of a low complexity and increases the sum capacity by 15%-46% comparing to state-of-the-art works., Comment: Accepted in IEEE PIMRC Workshops 2022

In a recent work, we studied a novel precoding design for cell-free networks called team minimum mean-square error (TMMSE) precoding, which rigorously generalizes centralized MMSE precoding to distributed operations based on transmitter-specific channel state information (CSI). Despite its flexibility in handling different cooperation regimes at the CSI sharing level, TMMSE precoding assumes network-wide sharing of the data bearing signals, and hence it is inherently not scalable. In this work, inspired by recent advances on scalable cell-free architectures based on user-centric network clustering techniques, we address this issue by proposing a novel version of the TMMSE precoding design covering partial message sharing. The obtained framework is then successfully applied to derive a variety of novel, optimal, and efficient precoding schemes for a user-centric cell-free network deployed using multiple radio stripes. Numerical simulations of a typical industrial internet-of-things scenario corroborate the gains of TMMSE precoding over competing schemes in terms of spectral efficiency under different power constraints. Although presented in the context of downlink precoding, the results of this paper may be applied also on the uplink.

This work takes a critical look at the application of conventional machine learning methods to wireless communication problems through the lens of reliability and robustness. Deep learning techniques adopt a frequentist framework, and are known to provide poorly calibrated decisions that do not reproduce the true uncertainty caused by limitations in the size of the training data. Bayesian learning, while in principle capable of addressing this shortcoming, is in practice impaired by model misspecification and by the presence of outliers. Both problems are pervasive in wireless communication settings, in which the capacity of machine learning models is subject to resource constraints and training data is affected by noise and interference. In this context, we explore the application of the framework of robust Bayesian learning. After a tutorial-style introduction to robust Bayesian learning, we showcase the merits of robust Bayesian learning on several important wireless communication problems in terms of accuracy, calibration, and robustness to outliers and misspecification., Comment: Submitted for publication

In this work, we investigate the problem of an online trajectory design for an Unmanned Aerial Vehicle (UAV) in a Federated Learning (FL) setting where several different communities exist, each defined by a unique task to be learned. In this setting, spatially distributed devices belonging to each community collaboratively contribute towards training their community model via wireless links provided by the UAV. Accordingly, the UAV acts as a mobile orchestrator coordinating the transmissions and the learning schedule among the devices in each community, intending to accelerate the learning process of all tasks. We propose a heuristic metric as a proxy for the training performance of the different tasks. Capitalizing on this metric, a surrogate objective is defined which enables us to jointly optimize the UAV trajectory and the scheduling of the devices by employing convex optimization techniques and graph theory. The simulations illustrate the out-performance of our solution when compared to other handpicked static and mobile UAV deployment baselines., Comment: Accepted to be presented at GLOBECOM 2022, IEEE Global Communications Conference: Selected Areas in Communications: Aerial Communications (Globecom 2022 SAC AC)", 4-8 December 2022, Rio de Janeiro, Brazil

Decentralized learning algorithms empower interconnected devices to share data and computational resources to collaboratively train a machine learning model without the aid of a central coordinator. In the case of heterogeneous data distributions at the network nodes, collaboration can yield predictors with unsatisfactory performance for a subset of the devices. For this reason, in this work, we consider the formulation of a distributionally robust decentralized learning task and we propose a decentralized single loop gradient descent/ascent algorithm (AD-GDA) to directly solve the underlying minimax optimization problem. We render our algorithm communication-efficient by employing a compressed consensus scheme and we provide convergence guarantees for smooth convex and non-convex loss functions. Finally, we corroborate the theoretical findings with empirical results that highlight AD-GDA's ability to provide unbiased predictors and to greatly improve communication efficiency compared to existing distributionally robust algorithms., Comment: Published in Transactions on Machine Learning Research (TMLR)

The use of unmanned aerial vehicles (UAV) as flying radio access network (RAN) nodes offers a promising complement to traditional fixed terrestrial deployments. More recently yet still in the context of wireless networks, drones have also been envisioned for use as radio frequency (RF) sensing and localization devices. In both cases, the advantage of using UAVs lies in their ability to navigate themselves freely in 3D and in a timely manner to locations of space where the obtained network throughput or sensing performance is optimal. In practice, the selection of a proper location or trajectory for the UAV very much depends on local terrain features, including the position of surrounding radio obstacles. Hence, the robot must be able to map the features of its radio environment as it performs its data communication or sensing services. The challenges related to this task, referred here as radio mapping, are discussed in this paper. Its promises related to efficient trajectory design for autonomous radio-aware UAVs are highlighted, along with algorithm solutions. The advantages induced by radio-mapping in terms of connectivity, sensing, and localization performance are illustrated., Comment: Accepted for publication in IEEE Wireless Communications Magazine

This paper considers the problem of ground user localization based on received signal strength (RSS) measurements obtained by an unmanned aerial vehicle (UAV). We treat UAV-user link channel model parameters and antenna radiation pattern of the UAV as unknowns that need to be estimated. A hybrid channel model is proposed that consists of a traditional path loss model combined with a neural network approximating the UAV antenna gain function. With this model and a set of offline RSS measurements, the unknown parameters are estimated. We then employ the particle swarm optimization (PSO) technique which utilizes the learned hybrid channel model along with a 3D map of the environment to accurately localize the ground users. The performance of the developed algorithm is evaluated through simulations and also real-world experiments., Comment: Accepted for publication in ICC workshop 2022

Standard Bayesian learning is known to have suboptimal generalization capabilities under misspecification and in the presence of outliers. PAC-Bayes theory demonstrates that the free energy criterion minimized by Bayesian learning is a bound on the generalization error for Gibbs predictors (i.e., for single models drawn at random from the posterior) under the assumption of sampling distributions uncontaminated by outliers. This viewpoint provides a justification for the limitations of Bayesian learning when the model is misspecified, requiring ensembling, and when data is affected by outliers. In recent work, PAC-Bayes bounds -- referred to as PAC$^m$ -- were derived to introduce free energy metrics that account for the performance of ensemble predictors, obtaining enhanced performance under misspecification. This work presents a novel robust free energy criterion that combines the generalized logarithm score function with PAC$^m$ ensemble bounds. The proposed free energy training criterion produces predictive distributions that are able to concurrently counteract the detrimental effects of misspecification -- with respect to both likelihood and prior distribution -- and outliers.

Decentralized learning empowers wireless network devices to collaboratively train a machine learning (ML) model relying solely on device-to-device (D2D) communication. It is known that the convergence speed of decentralized optimization algorithms severely depends on the degree of the network connectivity, with denser network topologies leading to shorter convergence time. Consequently, the local connectivity of real world mesh networks, due to the limited communication range of its wireless nodes, undermines the efficiency of decentralized learning protocols, rendering them potentially impracticable. In this work we investigate the role of an unmanned aerial vehicle (UAV), used as flying relay, in facilitating decentralized learning procedures in such challenging conditions. We propose an optimized UAV trajectory, that is defined as a sequence of waypoints that the UAV visits sequentially in order to transfer intelligence across sparsely connected group of users. We then provide a series of experiments highlighting the essential role of UAVs in the context of decentralized learning over mesh networks., Comment: Accepted to the 30th European Signal Processing Conference, EUSIPCO 2022

Massive multiple-input multiple-output (MIMO) is believed to deliver unrepresented spectral efficiency gains for 5G and beyond. However, a practical challenge arises during its commercial deployment, which is known as the ``curse of mobility''. The performance of massive MIMO drops alarmingly when the velocity level of user increases. In this paper, we tackle the problem in frequency division duplex (FDD) massive MIMO with a novel Channel State Information (CSI) acquisition framework. A joint angle-delay-Doppler (JADD) wideband precoder is proposed for channel training. Our idea consists in the exploitation of the partial channel reciprocity of FDD and the angle-delay-Doppler channel structure. More precisely, the base station (BS) estimates the angle-delay-Doppler information of the UL channel based on UL pilots using Matrix Pencil (MP) method. It then computes the wideband JADD precoders according to the extracted parameters. Afterwards, the user estimates and feeds back some scalar coefficients for the BS to reconstruct the predicted DL channel. Asymptotic analysis shows that the CSI prediction error converges to zero when the number of BS antennas and the bandwidth increases. Numerical results with industrial channel model demonstrate that our framework can well adapt to high speed (350 km/h), large CSI delay (10 ms) and channel sample noise., Comment: 9 figures, 15 pages, to appear in IEEE Transactions on Wireless Communications

This paper addresses high-resolution vehicle positioning and tracking. In recent work, it was shown that a fleet of independent but neighboring vehicles can cooperate for the task of localization by capitalizing on the existence of common surrounding reflectors, using the concept of Team Channel-SLAM. This approach exploits an initial (e.g. GPS-based) vehicle position information and allows subsequent tracking of vehicles by exploiting the shared nature of virtual transmitters associated to the reflecting surfaces. In this paper, we show that the localization can be greatly enhanced by joint sensing and mapping of reflecting surfaces. To this end, we propose a combined approach coined Team Channel-SLAM Evolution (TCSE) which exploits the intertwined relation between (i) the position of virtual transmitters, (ii) the shape of reflecting surfaces, and (iii) the paths described by the radio propagation rays, in order to achieve high-resolution vehicle localization. Overall, TCSE yields a complete picture of the trajectories followed by dominant paths together with a mapping of reflecting surfaces. While joint localization and mapping is a well researched topic within robotics using inputs such as radar and vision, this paper is first to demonstrate such an approach within mobile networking framework based on radio data.

The acquisition of channel state information (CSI) in Frequency Division Duplex (FDD) massive MIMO has been a formidable challenge. In this paper, we address this problem with a novel CSI feedback framework enabled by the partial reciprocity of uplink and downlink channels in the wideband regime. We first derive the closed-form expression of the rank of the wideband massive MIMO channel covariance matrix for a given angle-delay distribution. A low-rankness property is identified, which generalizes the well-known result of the narrow-band uniform linear array setting. Then we propose a partial channel reciprocity (PCR) codebook, inspired by the low-rankness behavior and the fact that the uplink and downlink channels have similar angle-delay distributions. Compared to the latest codebook in 5G, the proposed PCR codebook scheme achieves higher performance, lower complexity at the user side, and requires a smaller amount of feedback. We derive the feedback overhead necessary to achieve asymptotically error-free CSI feedback. Two low-complexity alternatives are also proposed to further reduce the complexity at the base station side. Simulations with the practical 3GPP channel model show the significant gains over the latest 5G codebook, which prove that our proposed methods are practical solutions for 5G and beyond., Comment: 15 pages, 8 figures, submitted to IEEE Transactions on Wireless Communications

Data heterogeneity across participating devices poses one of the main challenges in federated learning as it has been shown to greatly hamper its convergence time and generalization capabilities. In this work, we address this limitation by enabling personalization using multiple user-centric aggregation rules at the parameter server. Our approach potentially produces a personalized model for each user at the cost of some extra downlink communication overhead. To strike a trade-off between personalization and communication efficiency, we propose a broadcast protocol that limits the number of personalized streams while retaining the essential advantages of our learning scheme. Through simulation results, our approach is shown to enjoy higher personalization capabilities, faster convergence, and better communication efficiency compared to other competing baseline solutions., Comment: Accepted in Workshop on Wireless Communications For Distributed Intelligence, GLOBECOM 2021

Reliable pedestrian crash avoidance mitigation (PCAM) systems are crucial components of safe autonomous vehicles (AVs). The nature of the vehicle-pedestrian interaction where decisions of one agent directly affect the other agent's optimal behavior, and vice versa, is a challenging yet often neglected aspect of such systems. We address this issue by modeling a Markov decision process (MDP) for a simulated AV-pedestrian interaction at an unmarked crosswalk. The AV's PCAM decision policy is learned through deep reinforcement learning (DRL). Since modeling pedestrians realistically is challenging, we compare two levels of intelligent pedestrian behavior. While the baseline model follows a predefined strategy, our advanced pedestrian model is defined as a second DRL agent. This model captures continuous learning and the uncertainty inherent in human behavior, making the AV-pedestrian interaction a deep multi-agent reinforcement learning (DMARL) problem. We benchmark the developed PCAM systems according to the collision rate and the resulting traffic flow efficiency with a focus on the influence of observation uncertainty on the decision-making of the agents. The results show that the AV is able to completely mitigate collisions under the majority of the investigated conditions and that the DRL pedestrian model learns an intelligent crossing behavior., Comment: IEEE Intelligent Vehicles Symposium 2022

Taking advantage of the rich information provided by Wi-Fi measurement setups, Wi-Fi-based human behavior sensing leveraging Channel State Information (CSI) measurements has received a lot of research attention in recent years. The CSI-based human sensing algorithms typically either rely on an explicit channel propagation model or, more recently, adopt machine learning so as to robustify feature extraction. In most related work, the considered CSI is extracted from a single dedicated Access Point (AP) communication setup. In this paper, we consider a more realistic setting where a legacy network of multiple APs is already deployed for communications purposes and leveraged for sensing benefits using machine learning. The use of legacy network presents challenges and opportunities as many Wi-Fi links can present with richer yet unequally useful data sets. In order to break the curse of dimensionality associated with training over a too large dimensional CSI, we propose a link selection mechanism based on Reinforcement Learning (RL) which allows for dimension reduction while preserving the data that is most relevant for human behavior sensing. The method is based on a sequential state decision-making process in which the CSI is modeled as a part of the state. From actual experiment results, our method is shown to perform better than state-of-the-art approaches in a scenario with multiple available Wi-Fi links.

This paper tackles the problem of downlink data transmission in massive multiple-input multiple-output (MIMO) systems where user equipments (UEs) exhibit high spatial correlation and channel estimation is limited by strong pilot contamination. Signal subspace separation among UEs is, in fact, rarely realized in practice and is generally beyond the control of the network designer (as it is dictated by the physical scattering environment). In this context, we propose a novel statistical beamforming technique, referred to as MIMO covariance shaping, that exploits multiple antennas at the UEs and leverages the realistic non-Kronecker structure of massive MIMO channels to target a suitable shaping of the channel statistics performed at the UE-side. To optimize the covariance shaping strategies, we propose a low-complexity block coordinate descent algorithm that is proved to converge to a limit point of the original nonconvex problem. For the two-UE case, this is shown to converge to a stationary point of the original problem. Numerical results illustrate the sum-rate performance gains of the proposed method with respect to spatial multiplexing in scenarios where the spatial selectivity of the base station is not sufficient to separate closely spaced UEs., Comment: Accepted for publication in IEEE Transactions on Wireless Communications

The idea of using a Reconfigurable Intelligent Surface (RIS) consisting of a large array of passive scattering elements to assist wireless communication systems has recently attracted much attention from academia and industry. A central issue with RIS is how much power they can effectively convey to the target radio nodes. Regarding this question, several power level models exist in the literature but few have been validated through experiments. In this paper, we propose a radar cross section-based received power model for an RIS-aided wireless communication system that is rooted in the physical properties of RIS. Our proposed model follows the intuition that the received power is related to the distances from the transmitter/receiver to the RIS, the angles in the TX-RIS-RX triangle, the effective area of each element, and the reflection coefficient of each element. To the best of our knowledge, this paper is the first to model the angle-dependent phase shift of the reflection coefficient, which is typically ignored in existing literature. We further measure the received power with our experimental platform in different scenarios to validate our model. The measurement results show that our model is appropriate both in near field and far field and can characterize the impact of angles well., Comment: 5 pages, 6 figures, submitted

This article studies a novel distributed precoding design, coined team minimum mean-square error (TMMSE) precoding, which rigorously generalizes classical centralized MMSE precoding to distributed operations based on transmitter-specific channel state information (CSIT). Building on the so-called theory of teams, we derive a set of necessary and sufficient conditions for optimal TMMSE precoding, in the form of an infinite dimensional linear system of equations. These optimality conditions are further specialized to cell-free massive MIMO networks, and explicitly solved for two important examples, i.e., the classical case of local CSIT and the case of unidirectional CSIT sharing along a serial fronthaul. The latter case is relevant, e.g., for the recently proposed radio stripe concept and the related advances on sequential processing exploiting serial connections. In both cases, our optimal design outperforms the heuristic methods that are known from the previous literature. Duality arguments and numerical simulations validate the effectiveness of the proposed team theoretical approach in terms of ergodic achievable rates under a sum-power constraint.

Efficient millimeter wave (mmWave) beam selection in vehicle-to-infrastructure (V2I) communication is a crucial yet challenging task due to the narrow mmWave beamwidth and high user mobility. To reduce the search overhead of iterative beam discovery procedures, contextual information from light detection and ranging (LIDAR) sensors mounted on vehicles has been leveraged by data-driven methods to produce useful side information. In this paper, we propose a lightweight neural network (NN) architecture along with the corresponding LIDAR preprocessing, which significantly outperforms previous works. Our solution comprises multiple novelties that improve both the convergence speed and the final accuracy of the model. In particular, we define a novel loss function inspired by the knowledge distillation idea, introduce a curriculum training approach exploiting line-of-sight (LOS)/non-line-of-sight (NLOS) information, and we propose a non-local attention module to improve the performance for the more challenging NLOS cases. Simulation results on benchmark datasets show that, utilizing solely LIDAR data and the receiver position, our NN-based beam selection scheme can achieve 79.9% throughput of an exhaustive beam sweeping approach without any beam search overhead and 95% by searching among as few as 6 beams. In a typical mmWave V2I scenario, our proposed method considerably reduces the beam search time required to achieve a desired throughput, in comparison with the inverse fingerprinting and hierarchical beam selection schemes., Comment: Submitted for publication

Deep Reinforcement Learning (DRL) is gaining attention as a potential approach to design trajectories for autonomous unmanned aerial vehicles (UAV) used as flying access points in the context of cellular or Internet of Things (IoT) connectivity. DRL solutions offer the advantage of on-the-go learning hence relying on very little prior contextual information. A corresponding drawback however lies in the need for many learning episodes which severely restricts the applicability of such approach in real-world time- and energy-constrained missions. Here, we propose a model-aided deep Q-learning approach that, in contrast to previous work, considerably reduces the need for extensive training data samples, while still achieving the overarching goal of DRL, i.e to guide a battery-limited UAV on an efficient data harvesting trajectory, without prior knowledge of wireless channel characteristics and limited knowledge of wireless node locations. The key idea consists in using a small subset of nodes as anchors (i.e. with known location) and learning a model of the propagation environment while implicitly estimating the positions of regular nodes. Interaction with the model allows us to train a deep Q-network (DQN) to approximate the optimal UAV control policy. We show that in comparison with standard DRL approaches, the proposed model-aided approach requires at least one order of magnitude less training data samples to reach identical data collection performance, hence offering a first step towards making DRL a viable solution to the problem., Comment: 6 pages, 2 figures, Accepted in GLOBECOM 2021

This paper addresses vehicle positioning, a topic whose importance has risen dramatically in the context of future autonomous driving systems. While classical methods that use GPS and/or beacon signals from network infrastructure for triangulation tend to be sensitive to multi-paths and signal obstruction, our method exhibits robustness with respect to such phenomena. Our approach builds on the recently proposed Channel-SLAM method which first enabled leveraging of multi-path so as to improve (single) vehicle positioning. Here, we propose a cooperative mapping approach which builds upon the Channel-SLAM concept, referred to here as Team Channel-SLAM. Team Channel-SLAM not only exploits the stationary nature of many reflecting objects around the vehicle, but also capitalizes on the multi-vehicle nature of road traffic. The key intuition behind our method is the exploitation for the first time of the correlation between reflectors around multiple neighboring vehicles. An algorithm is derived for reflector selection and estimation, combined with a team particle filter (TPF) so as to achieve high precision simultaneous multiple vehicle positioning. We obtain large improvement over the single-vehicle positioning scenario, with gains being already noticeable for moderate vehicle densities, such as over 40% improvement for a vehicle density as low as 4 vehicles in 132 meters' length road.

Multicasting, where a base station (BS) wishes to convey the same message to several user equipments (UEs), represents a common yet highly challenging wireless scenario. In fact, guaranteeing decodability by the whole UE population proves to be a major performance bottleneck since the UEs in poor channel conditions ultimately determine the achievable rate. To overcome this issue, two-phase cooperative multicasting schemes, which use conventional multicasting in a first phase and leverage device-to-device (D2D) communications in a second phase to effectively spread the message, have been extensively studied. However, most works are limited either to the simple case of single-antenna BS or to a specific channel state information at the transmitter (CSIT) setup. This paper proposes a general two-phase framework that is applicable to the cases of perfect, statistical, and topological CSIT in the presence of multiple antennas at the BS. The proposed method exploits the precoding capabilities at the BS, which enable targeting specific UEs that can effectively serve as D2D relays towards the remaining UEs, and maximize the multicast rate under some outage constraint. Numerical results show that our schemes bring substantial gains over traditional single-phase multicasting and overcome the worst-UE bottleneck behavior in all the considered CSIT configurations., Comment: Submitted to IEEE Transactions on Wireless Communications

Massive multiple-input multiple-output (mMIMO) communications are one of the enabling technologies of 5G and beyond networks. While prior work indicates that mMIMO networks employing time division duplexing have a significant capacity growth potential, deploying mMIMO in frequency division duplexing (FDD) networks remains problematic. The two main difficulties in FDD networks are the scalability of the downlink reference signals and the overhead associated with the required uplink feedback for channel state information (CSI) acquisition. To address these difficulties, most existing methods utilize assumptions on the radio environment such as channel sparsity or angular reciprocity. In this work, we propose a novel cooperative method for a scalable and low-overhead approach to FDD mMIMO under the so-called grid-of-beams architecture. The key idea behind our scheme lies in the exploitation of the near-common signal propagation paths that are often found across several mobile users located in nearby regions, through a coordination mechanism. In doing so, we leverage the recently specified device-to-device communications capability in 5G networks. Specifically, we design beam selection algorithms capable of striking a balance between CSI acquisition overhead and multi-user interference mitigation. The selection exploits statistical information, through so-called covariance shaping. Simulation results demonstrate the effectiveness of the proposed algorithms, which prove particularly well-suited to rapidly-varying channels with short coherence time., Comment: 33 pages, 10 figures. Accepted for publication in IEEE Transactions on Wireless Communications

Harvesting data from distributed Internet of Things (IoT) devices with multiple autonomous unmanned aerial vehicles (UAVs) is a challenging problem requiring flexible path planning methods. We propose a multi-agent reinforcement learning (MARL) approach that, in contrast to previous work, can adapt to profound changes in the scenario parameters defining the data harvesting mission, such as the number of deployed UAVs, number, position and data amount of IoT devices, or the maximum flying time, without the need to perform expensive recomputations or relearn control policies. We formulate the path planning problem for a cooperative, non-communicating, and homogeneous team of UAVs tasked with maximizing collected data from distributed IoT sensor nodes subject to flying time and collision avoidance constraints. The path planning problem is translated into a decentralized partially observable Markov decision process (Dec-POMDP), which we solve through a deep reinforcement learning (DRL) approach, approximating the optimal UAV control policy without prior knowledge of the challenging wireless channel characteristics in dense urban environments. By exploiting a combination of centered global and local map representations of the environment that are fed into convolutional layers of the agents, we show that our proposed network architecture enables the agents to cooperate effectively by carefully dividing the data collection task among themselves, adapt to large complex environments and state spaces, and make movement decisions that balance data collection goals, flight-time efficiency, and navigation constraints. Finally, learning a control policy that generalizes over the scenario parameter space enables us to analyze the influence of individual parameters on collection performance and provide some intuition about system-level benefits., Comment: Modifications: final formatting; Code available under https://github.com/hbayerlein/uav_data_harvesting, article extends on arXiv:2007.00544

Path planning methods for autonomous unmanned aerial vehicles (UAVs) are typically designed for one specific type of mission. This work presents a method for autonomous UAV path planning based on deep reinforcement learning (DRL) that can be applied to a wide range of mission scenarios. Specifically, we compare coverage path planning (CPP), where the UAV's goal is to survey an area of interest to data harvesting (DH), where the UAV collects data from distributed Internet of Things (IoT) sensor devices. By exploiting structured map information of the environment, we train double deep Q-networks (DDQNs) with identical architectures on both distinctly different mission scenarios to make movement decisions that balance the respective mission goal with navigation constraints. By introducing a novel approach exploiting a compressed global map of the environment combined with a cropped but uncompressed local map showing the vicinity of the UAV agent, we demonstrate that the proposed method can efficiently scale to large environments. We also extend previous results for generalizing control policies that require no retraining when scenario parameters change and offer a detailed analysis of crucial map processing parameters' effects on path planning performance., Comment: ICAR 2021, code available at https://github.com/theilem/uavSim

In the context of wireless networking, it was recently shown that multiple DNNs can be jointly trained to offer a desired collaborative behaviour capable of coping with a broad range of sensing uncertainties. In particular, it was established that DNNs can be used to derive policies that are robust with respect to the information noise statistic affecting the local information (e.g. CSI in a wireless network) used by each agent (e.g. transmitter) to make its decision. While promising, a major challenge in the implementation of such method is that information noise statistics may differ from agent to agent and, more importantly, that such statistics may not be available at the time of training or may evolve over time, making burdensome retraining necessary. This situation makes it desirable to devise a "universal" machine learning model, which can be trained once for all so as to allow for decentralized cooperation in any future feedback noise environment. With this goal in mind, we propose an architecture inspired from the well-known Mixture of Experts (MoE) model, which was previously used for non-linear regression and classification tasks in various contexts, such as computer vision and speech recognition. We consider the decentralized power control problem as an example to showcase the validity of the proposed model and to compare it against other power control algorithms. We show the ability of the so called Team-DMoE model to efficiently track time-varying statistical scenarios.

Autonomous deployment of unmanned aerial vehicles (UAVs) supporting next-generation communication networks requires efficient trajectory planning methods. We propose a new end-to-end reinforcement learning (RL) approach to UAV-enabled data collection from Internet of Things (IoT) devices in an urban environment. An autonomous drone is tasked with gathering data from distributed sensor nodes subject to limited flying time and obstacle avoidance. While previous approaches, learning and non-learning based, must perform expensive recomputations or relearn a behavior when important scenario parameters such as the number of sensors, sensor positions, or maximum flying time, change, we train a double deep Q-network (DDQN) with combined experience replay to learn a UAV control policy that generalizes over changing scenario parameters. By exploiting a multi-layer map of the environment fed through convolutional network layers to the agent, we show that our proposed network architecture enables the agent to make movement decisions for a variety of scenario parameters that balance the data collection goal with flight time efficiency and safety constraints. Considerable advantages in learning efficiency from using a map centered on the UAV's position over a non-centered map are also illustrated., Comment: Code available under https://github.com/hbayerlein/uav_data_harvesting, IEEE Global Communications Conference (GLOBECOM) 2020

Submodularity is a discrete domain functional property that can be interpreted as mimicking the role of the well-known convexity/concavity properties in the continuous domain. Submodular functions exhibit strong structure that lead to efficient optimization algorithms with provable near-optimality guarantees. These characteristics, namely, efficiency and provable performance bounds, are of particular interest for signal processing (SP) and machine learning (ML) practitioners as a variety of discrete optimization problems are encountered in a wide range of applications. Conventionally, two general approaches exist to solve discrete problems: $(i)$ relaxation into the continuous domain to obtain an approximate solution, or $(ii)$ development of a tailored algorithm that applies directly in the discrete domain. In both approaches, worst-case performance guarantees are often hard to establish. Furthermore, they are often complex, thus not practical for large-scale problems. In this paper, we show how certain scenarios lend themselves to exploiting submodularity so as to construct scalable solutions with provable worst-case performance guarantees. We introduce a variety of submodular-friendly applications, and elucidate the relation of submodularity to convexity and concavity which enables efficient optimization. With a mixture of theory and practice, we present different flavors of submodularity accompanying illustrative real-world case studies from modern SP and ML. In all cases, optimization algorithms are presented, along with hints on how optimality guarantees can be established.

We address the problem of resource allocation (RA) in a cognitive radio (CR) communication system with multiple secondary operators sharing spectrum with an incumbent primary operator. The key challenge of the RA problem is the inter-operator coordination arising in the optimization problem so that the aggregated interference at the primary users (PUs) does not exceed the target threshold. While this problem is easily solvable if a centralized unit could access information of all secondary operators, it becomes challenging in a realistic scenario. In this paper, considering a satellite setting, we alleviate this problem by proposing two approaches to reduce the information exchange level among the secondary operators. In the first approach, we formulate an RA scheme based on a partial information sharing method which enables distributed optimization across secondary operators. In the second approach, instead of exchanging secondary users (SUs) information, the operators only exchange their contributions of the interference-level and RA is performed locally across secondary operators. These two approaches, for the first time in this context, provide a trade-off between performance and level of inter-operator information exchange. Through the numerical simulations, we explain this trade-off and illustrate the penalty resulting from partial information exchange., Comment: arXiv admin note: text overlap with arXiv:2005.02746

We address the problem of resource allocation (RA) for spectrum underlay in a cognitive radio (CR) communication system with multiple secondary operators sharing resource with an incumbent primary operator. The multiple secondary operator RA problem is well known to be especially challenging because of the inter-operator coupling constraints arising in the optimization problem, which render impractical inter-operator information exchange necessary. In this paper, we consider a satellite setting for multi-operator CR. In the CR maturation regime, i.e., the period in which the secondary subscriber density is growing yet remains much below that of incumbent users, we show that in fact the inter-operator mutual constraints can be neglected, thus making distributed (across secondary operators) optimization possible. Furthermore, we establish analytically that the mutual constraints asymptotically vanish with the primary user density.

We analyze the high-SNR regime of the MxK Network MISO channel in which each transmitter has access to a different channel estimate, possibly with different precision. It has been recently shown that, for some regimes, this setting attains the same Degrees-of-Freedom as the ideal centralized setting with perfect CSI sharing, in which all the transmitters are endowed with the best estimate available at any transmitter. This result is restricted by the limitations of the DoF metric, as it only provides information about the slope of growth of the capacity as a function of the SNR, without any insight about the possible performance at a given SNR. To overcome this limitation, we analyze the affine approximation of the rate on the high-SNR regime for this decentralized Network MISO setting for the antenna configurations in which it achieves the DoF of the centralized setting. We show that, for a regime of antenna configurations, it is possible to asymptotically attain the same achievable rate as in the ideal centralized scenario. Consequently, it is possible to achieve the beamforming gain of the ideal perfect-CSI-sharing setting even if only a subset of transmitters is endowed with precise CSI, which can be exploited in scenarios such as distributed massive MIMO where the number of transmit antennas is much bigger than the number of served users. This outcome is a consequence of the synergistic compromise between CSI precision at the transmitters and consistency between the locally-computed precoders, which is an inherent trade-off of decentralized settings that does not exist in a centralized CSI configuration. We propose a precoding scheme achieving the previous result, which is built on an uneven structure in which some transmitters reduce the precision of their own precoding for the sake of using transmission parameters that can be more easily predicted by the other transmitters.

Vehicle positioning is considered a key element in autonomous driving systems. While conventional positioning requires the use of GPS and/or beacon signals from network infrastructure for triangulation, they are sensitive to multi-path and signal obstruction. However, recent proposals like the Channel-SLAM method showed it was possible in principle to in fact leverage multi-path to improve positioning of a single vehicle. In this paper, we derive a cooperative Channel-SLAM framework, which is referred as Team Channel-SLAM. Different from the previous work, Team Channel-SLAM not only exploits the stationary nature of reflecting objects around the receiver to characterize the location of a single vehicle through multi-path signals, but also capitalizes on the multi-vehicle aspects of road traffic to further improve positioning.Specifically, Team Channel-SLAM exploits the correlation between reflectors around multiple neighboring vehicles to achieve high precision multiple vehicle positioning. Our method uses affinity propagation clustering and cooperative particle filter. The new framework is shown to give substantial improvement over the single vehicle positioning situation.

Coverage path planning (CPP) is the task of designing a trajectory that enables a mobile agent to travel over every point of an area of interest. We propose a new method to control an unmanned aerial vehicle (UAV) carrying a camera on a CPP mission with random start positions and multiple options for landing positions in an environment containing no-fly zones. While numerous approaches have been proposed to solve similar CPP problems, we leverage end-to-end reinforcement learning (RL) to learn a control policy that generalizes over varying power constraints for the UAV. Despite recent improvements in battery technology, the maximum flying range of small UAVs is still a severe constraint, which is exacerbated by variations in the UAV's power consumption that are hard to predict. By using map-like input channels to feed spatial information through convolutional network layers to the agent, we are able to train a double deep Q-network (DDQN) to make control decisions for the UAV, balancing limited power budget and coverage goal. The proposed method can be applied to a wide variety of environments and harmonizes complex goal structures with system constraints., Comment: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

In this work, we study the impact of imperfect sharing of the Channel State Information (CSI) available at the transmitters on a Network MIMO setting in which a set of $M$ transmit antennas, possibly not co-located, jointly serve two multi-antenna users endowed with $N_1$ and $N_2$ antennas, respectively. We consider the case where only a subset of $k$ transmit antennas have access to perfect CSI, whereas the other $M-k$ transmit antennas have only access to finite precision CSI. The analysis of this configuration aims to answer the question of how much an extra informed antenna can help. We model this scenario as a Decentralized MIMO Broadcast Channel (BC) and characterize the Degrees-of-Freedom (DoF) region, showing that only $k=\max(N_1,N_2)$ antennas with perfect CSI are needed to achieve the DoF of the conventional BC with ubiquitous perfect CSI. Furthermore, we identify the increase of DoF obtained by providing CSI to an extra transmit antenna.

Massive MIMO is widely touted as an enabling technology for 5th generation (5G) mobile communications and beyond. On paper, the large excess of base station (BS) antennas promises unprecedented spectral efficiency gains. Unfortunately, during the initial phase of industrial testing, a practical challenge arose which threatens to undermine the actual deployment of massive MIMO: user mobility-induced channel Doppler. In fact, testing teams reported that in moderate-mobility scenarios, e.g., 30 km/h of user equipment (UE) speed, the performance drops up to 50% compared to the low-mobility scenario, a problem rooted in the acute sensitivity of massive MIMO to this channel Doppler, and not foreseen by many theoretical papers on the subject. In order to deal with this "curse of mobility", we propose a novel form of channel prediction method, named Prony-based angular-delay domain (PAD) prediction, which is built on exploiting the specific angle-delay-Doppler structure of the multipath. In particular, our method relies on the high angular-delay resolution which arises in the context of 5G. Our theoretical analysis shows that when the number of base station antennas and the bandwidth are large, the prediction error of our PAD algorithm converges to zero for any UE velocity level, provided that only two accurate enough previous channel samples are available. Moreover, when the channel samples are inaccurate, we propose to combine the PAD algorithm with a denoising method for channel estimation phase based on the subspace structure and the long-term statistics of the channel observations. Simulation results show that under a realistic channel model of 3GPP in rich scattering environment, our proposed method is able to overcome this challenge and even approaches the performance of stationary scenarios where the channels do not vary at all., Comment: 15 pages, 7 figures, to appear in IEEE Journal on Selected Areas in Communications

This paper studies a memoryless state-dependent multiple access channel (MAC) where two transmitters wish to convey a message to a receiver under the assumption of causal and imperfect channel state information at transmitters (CSIT) and imperfect channel state information at receiver (CSIR). In order to emphasize the limitation of transmitter cooperation between physically distributed nodes, we focus on the so-called distributed CSIT assumption, i.e. where each transmitter has its individual channel knowledge, while the message can be assumed to be partially or entirely shared a priori between transmitters by exploiting some on-board memory. Under this setup, the first part of the paper characterizes the common message capacity of the channel at hand for arbitrary CSIT and CSIR structure. The optimal scheme builds on Shannon strategies, i.e. optimal codes are constructed by letting the channel inputs be a function of current CSIT only. For a special case when CSIT is a deterministic function of CSIR, the considered scheme also achieves the capacity region of a common message and two private messages. The second part addresses an important instance of the previous general result in a context of a cooperative multi-antenna Gaussian channel under i.i.d. fading operating in frequency-division duplex mode, such that CSIT is acquired via an explicit feedback of perfect CSIR. The capacity of the channel at hand is achieved by distributed linear precoding applied to Gaussian codes. Surprisingly, we demonstrate that it is suboptimal to send a number of data streams bounded by the number of transmit antennas as typically considered in a centralized CSIT setup. Finally, numerical examples are provided to evaluate the sum capacity of the binary MAC with binary states as well as the Gaussian MAC with i.i.d. fading.