arXiv subjects

Michele Zorzi

Publications and source records attributed to Michele Zorzi.

At least 55 records · Page 3Linked to original sources

arXiv2023

A New Scheduler for URLLC in 5G NR IIoT Networks with Spatio-Temporal Traffic Correlations

This paper explores the issue of enabling Ultra-Reliable Low-Latency Communications (URLLC) in view of the spatio-temporal correlations that characterize real 5th generation (5G) Industrial Internet of Things (IIoT) networks. In this context, we consider a common Standalone Non-Public Network (SNPN) architecture as promoted by the 5G Alliance for Connected Industries and Automation (5G-ACIA), and propose a new variant of the 5G NR semi-persistent scheduler (SPS) to deal with uplink traffic correlations. A benchmark solution with a "smart" scheduler (SSPS) is compared with a more realistic adaptive approach (ASPS) that requires the scheduler to estimate some unknown network parameters. We demonstrate via simulations that the 1-ms latency requirement for URLLC is fulfilled in both solutions, at the expense of some complexity introduced in the management of the traffic. Finally, we provide numerical guidelines to dimension IIoT networks as a function of the use case, the number of machines in the factory, and considering both periodic and aperiodic traffic.

cs.NI↗

arXiv2023

Towards Decentralized Predictive Quality of Service in Next-Generation Vehicular Networks

To ensure safety in teleoperated driving scenarios, communication between vehicles and remote drivers must satisfy strict latency and reliability requirements. In this context, Predictive Quality of Service (PQoS) was investigated as a tool to predict unanticipated degradation of the Quality of Service (QoS), and allow the network to react accordingly. In this work, we design a reinforcement learning (RL) agent to implement PQoS in vehicular networks. To do so, based on data gathered at the Radio Access Network (RAN) and/or the end vehicles, as well as QoS predictions, our framework is able to identify the optimal level of compression to send automotive data under low latency and reliability constraints. We consider different learning schemes, including centralized, fully-distributed, and federated learning. We demonstrate via ns-3 simulations that, while centralized learning generally outperforms any other solution, decentralized learning, and especially federated learning, offers a good trade-off between convergence time and reliability, with positive implications in terms of privacy and complexity.

cs.NI↗

arXiv2023

Sparse Random Networks for Communication-Efficient Federated Learning

One main challenge in federated learning is the large communication cost of exchanging weight updates from clients to the server at each round. While prior work has made great progress in compressing the weight updates through gradient compression methods, we propose a radically different approach that does not update the weights at all. Instead, our method freezes the weights at their initial \emph{random} values and learns how to sparsify the random network for the best performance. To this end, the clients collaborate in training a \emph{stochastic} binary mask to find the optimal sparse random network within the original one. At the end of the training, the final model is a sparse network with random weights -- or a subnetwork inside the dense random network. We show improvements in accuracy, communication (less than $1$ bit per parameter (bpp)), convergence speed, and final model size (less than $1$ bpp) over relevant baselines on MNIST, EMNIST, CIFAR-10, and CIFAR-100 datasets, in the low bitrate regime under various system configurations.

cs.LG↗

arXiv2023

On the Optimal Beamwidth of UAV-Assisted Networks Operating at Millimeter Waves

The millimeter-wave (mm-wave) bands enable very large antenna arrays that can generate narrow beams for beamforming and spatial multiplexing. However, directionality introduces beam misalignment and leads to reduced energy efficiency. Thus, employing the narrowest possible beam in a cell may not necessarily imply maximum coverage. The objective of this work is to determine the optimal sector beamwidth for a cellular architecture served by an unmanned aerial vehicle (UAV) acting as a base station (BS). The users in a cell are assumed to be distributed according to a Poisson Point Process (PPP) with a given user density. We consider hybrid beamforming at the UAV, such that multiple concurrent beams serve all the sectors simultaneously. An optimization problem is formulated to maximize the sum rate over a given area while limiting the total power available to each sector. We observe that, for a given transmit power, the optimal sector beamwidth increases as the user density in a cell decreases, and varies based on the height of the UAV. Thus, we provide guidelines towards the optimal beamforming configurations for users in rural areas.

cs.IT↗

arXiv2023

Downlink TDMA Scheduling for IRS-aided Communications with Block-Static Constraints

Intelligent reflecting surfaces (IRSs) are being studied as possible low-cost energy-efficient alternatives to active relays, with the goal of solving the coverage issues of millimeter wave (mmWave) and terahertz (THz) network deployments. In the literature, these surfaces are often studied by idealizing their characteristics. Notably, it is often assumed that IRSs can tune with arbitrary frequency the phase-shifts induced by their elements, thanks to a wire-like control channel to the next generation node base (gNB). Instead, in this work we investigate an IRS-aided time division multiple access (TDMA) cellular network, where the reconfiguration of the IRS may entail an energy or communication cost, and we aim at limiting the number of reconfigurations over time. We develop a clustering-based heuristic scheduling, which optimizes the system sum-rate subject to a given number of reconfigurations within the TDMA frame. To such end, we first cluster user equipments (UEs) with a similar optimal IRS configuration. Then, we compute an overall IRS cluster configuration, which can be thus kept constant while scheduling the whole UEs cluster. Numerical results show that our approach is effective in supporting IRSs-aided systems with practical constraints, achieving up to 85% of the throughput obtained by an ideal deployment, while providing a 50% reduction in the number of IRS reconfigurations.

eess.SP↗

arXiv2023

Real-Time HAP-Assisted Vehicular Edge Computing for Rural Areas

Non-Terrestrial Networks (NTNs) are expected to be a key component of 6th generation (6G) networks to support broadband seamless Internet connectivity and expand the coverage even in rural and remote areas. In this context, High Altitude Platforms (HAPs) can act as edge servers to process computational tasks offloaded by energy-constrained terrestrial devices such as Internet of Things (IoT) sensors and ground vehicles (GVs). In this paper, we analyze the opportunity to support Vehicular Edge Computing (VEC) via HAP in a rural scenario where GVs can decide whether to process data onboard or offload them to a HAP. We characterize the system as a set of queues in which computational tasks arrive according to a Poisson arrival process. Then, we assess the optimal VEC offloading factor to maximize the probability of real-time service, given latency and computational capacity constraints.

cs.NI↗

arXiv2023

Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression

The coordination of robotic swarms and the remote wireless control of industrial systems are among the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that needs to be shared over the wireless medium can overload even high-capacity connections. Consequently, solving the effective communication problem by optimizing the transmission strategy to discard irrelevant information can provide a significant advantage, but is often a very complex task. In this work, we consider a prototypal system in which an observer must communicate its sensory data to an actor controlling a task (e.g., a mobile robot in a factory). We then model it as a remote Partially Observable Markov Decision Process (POMDP), considering the effect of adopting semantic and effective communication-oriented solutions on the overall system performance. We split the communication problem by considering an ensemble Vector Quantized Variational Autoencoder (VQ-VAE) encoding, and train a Deep Reinforcement Learning (DRL) agent to dynamically adapt the quantization level, considering both the current state of the environment and the memory of past messages. We tested the proposed approach on the well-known CartPole reference control problem, obtaining a significant performance increase over traditional approaches

cs.LG↗

arXiv2023

Safehaul: Risk-Averse Learning for Reliable mmWave Self-Backhauling in 6G Networks

Wireless backhauling at millimeter-wave frequencies (mmWave) in static scenarios is a well-established practice in cellular networks. However, highly directional and adaptive beamforming in today's mmWave systems have opened new possibilities for self-backhauling. Tapping into this potential, 3GPP has standardized Integrated Access and Backhaul (IAB) allowing the same base station serve both access and backhaul traffic. Although much more cost-effective and flexible, resource allocation and path selection in IAB mmWave networks is a formidable task. To date, prior works have addressed this challenge through a plethora of classic optimization and learning methods, generally optimizing a Key Performance Indicator (KPI) such as throughput, latency, and fairness, and little attention has been paid to the reliability of the KPI. We propose Safehaul, a risk-averse learning-based solution for IAB mmWave networks. In addition to optimizing average performance, Safehaul ensures reliability by minimizing the losses in the tail of the performance distribution. We develop a novel simulator and show via extensive simulations that Safehaul not only reduces the latency by up to 43.2% compared to the benchmarks but also exhibits significantly more reliable performance (e.g., 71.4% less variance in achieved latency).

cs.NI↗

arXiv2023

5G NR-Light at Millimeter Waves: Design Guidelines for Mid-Market IoT Use Cases

5th generation (5G) systems have been designed with three main objectives in mind: increasing throughput, reducing latency, and enabling reliable communications. To meet these (often conflicting) constraints, the 3GPP released a set of specifications for 5G NR, one of the main innovations being the support for communications in the millimeter wave (mmWave) bands. However, how to implement lower complexity, energy efficient, mid-market Internet of Things (IoT) applications is still an on-going investigation, currently led by the 3GPP which is extending the NR standard with NR-Light specifications to support devices with reduced capabilities (REDCAP). While REDCAP devices may also operate at mmWaves to improve the network performance, hardware/software simplifications are needed to support balanced and mixed requirements compared to 5G NR systems. In this context, the contributions of this paper are threefold. First, we present some NR-Light use cases for which the support of the mmWave bands is desirable. Second, we describe how 5G NR can be simplified to achieve NR-Light requirements and expectations. Finally, we evaluate via simulation the performance of NR-Light devices operating at mmWaves in an industrial IoT setup, in terms of cost and complexity, throughput, and latency.

cs.NI↗

arXiv2022

Pilot Reuse in Cell-Free Massive MIMO Systems: A Diverse Clustering Approach

Distributed or Cell-free (CF) massive Multiple-Input, Multiple-Output (mMIMO), has been recently proposed as an answer to the limitations of the current network-centric systems in providing high-rate ubiquitous transmission. The capability of providing uniform service level makes CF mMIMO a potential technology for beyond-5G and 6G networks. The acquisition of accurate Channel State Information (CSI) is critical for different CF mMIMO operations. Hence, an uplink pilot training phase is used to efficiently estimate transmission channels. The number of available orthogonal pilot signals is limited, and reusing these pilots will increase co-pilot interference. This causes an undesirable effect known as pilot contamination that could reduce the system performance. Hence, a proper pilot reuse strategy is needed to mitigate the effects of pilot contamination. In this paper, we formulate pilot assignment in CF mMIMO as a diverse clustering problem and propose an iterative maxima search scheme to solve it. In this approach, we first form the clusters of User Equipments (UEs) so that the intra-cluster diversity maximizes and then assign the same pilots for all UEs in the same cluster. The numerical results show the proposed techniques' superiority over other methods concerning the achieved uplink and downlink average and per-user data rate.

cs.IT↗

arXiv2022

On the Performance of Non-Terrestrial Networks to Support the Internet of Things

The advent of the Internet of Things (IoT) era, where billions of devices and sensors are becoming more and more connected and ubiquitous, is putting a strain on traditional terrestrial networks, that may no longer be able to fulfill service requirements efficiently. This issue is further complicated in rural and remote areas with scarce and low-quality cellular coverage. To fill this gap, the research community is focusing on non-terrestrial networks (NTNs), where Unmanned Aerial Vehicles (UAVs), High Altitude Platforms (HAPs) and satellites can serve as aerial/space gateways to aggregate, process, and relay the IoT traffic. In this paper we demonstrate this paradigm, and evaluate how common Low-Power Wide Area Network (LPWAN) technologies, designed and developed to operate for IoT systems, work in NTNs. We then formalize an optimization problem to decide whether and how IoT traffic can be offloaded to LEO satellites to reduce the burden on terrestrial gateways.

cs.NI↗

arXiv2022

Distributed Resource Allocation for URLLC in IIoT Scenarios: A Multi-Armed Bandit Approach

This paper addresses the problem of enabling inter-machine Ultra-Reliable Low-Latency Communication (URLLC) in future 6G Industrial Internet of Things (IIoT) networks. As far as the Radio Access Network (RAN) is concerned, centralized pre-configured resource allocation requires scheduling grants to be disseminated to the User Equipments (UEs) before uplink transmissions, which is not efficient for URLLC, especially in case of flexible/unpredictable traffic. To alleviate this burden, we study a distributed, user-centric scheme based on machine learning in which UEs autonomously select their uplink radio resources without the need to wait for scheduling grants or preconfiguration of connections. Using simulation, we demonstrate that a Multi-Armed Bandit (MAB) approach represents a desirable solution to allocate resources with URLLC in mind in an IIoT environment, in case of both periodic and aperiodic traffic, even considering highly populated networks and aggressive traffic.

cs.NI↗

arXiv2022

System Architecture and Communication Infrastructure for the RoboVaaS project

Current advancements in waterborne autonomous systems, together with the development of cloud-based service-oriented architectures and the recent availability of low-cost underwater acoustic modems and long-range above water wireless devices, enabled the development of new applications to support ships and port activities. Unmanned Surface Vehicle (USV) can, for instance, be used to perform bathymetry and environmental data collection tasks to ensure under-keel clearance and to monitor the quality of the water. Similarly, Remotely Operated Vehicles (ROVs) can be deployed to inspect ship hulls and typical port infrastructure elements, such as quay and sheet pilling walls. In this paper we present the complete system deployed for the small-scale demonstrations of the Robotic Vessels as-a-Service (RoboVaaS) project, which introduces an on-demand service-based cloud system that dispatches Unmanned Vehicles (UVs) capable of performing the required service either autonomously or piloted. These vessels are able to interact with sensors deployed in the port and with the shore station through an integrated underwater and above water network. The developed system has been validated through sea trials and showcased through an underwater sensor data collection service. The results of the test presented in this paper provide a proof-of-concept of the system design and indicate its technical feasibility. It also shows the need for further developments for a mature technology allowing on-demand robotic maritime assistance services in real operational scenarios.

cs.RO↗

arXiv2022

An Open Framework to Model Diffraction by Dynamic Blockers in Millimeter Wave Simulations

The millimeter wave (mmWave) band will be exploited to address the growing demand for high data rates and low latency. The higher frequencies, however, are prone to limitations on the propagation of the signal in the environment. Thus, highly directional beamforming is needed to increase the antenna gain. Another crucial problem of the mmWave frequencies is their vulnerability to blockage by physical obstacles. To this aim, we studied the problem of modeling the impact of second-order effects on mmWave channels, specifically the susceptibility of the mmWave signals to physical blockers. With respect to existing works on this topic, our project focuses on scenarios where mmWaves interact with multiple, dynamic blockers. Our open source software includes diffraction-based blockage models and interfaces directly with an open source Radio Frequency (RF) ray-tracing software.

cs.NI↗

arXiv2022

Temporal Characterization of VR Traffic for Network Slicing Requirement Definition

Over the past few years, the concept of VR has attracted increasing interest thanks to its extensive industrial and commercial applications. Currently, the 3D models of the virtual scenes are generally stored in the VR visor itself, which operates as a standalone device. However, applications that entail multi-party interactions will likely require the scene to be processed by an external server and then streamed to the visors. However, the stringent Quality of Service (QoS) constraints imposed by VR's interactive nature require Network Slicing (NS) solutions, for which profiling the traffic generated by the VR application is crucial. To this end, we collected more than 4 hours of traces in a real setup and analyzed their temporal correlation. More specifically, we focused on the CBR encoding mode, which should generate more predictable traffic streams. From the collected data, we then distilled two prediction models for future frame size, which can be instrumental in the design of dynamic resource allocation algorithms. Our results show that even the state-of-the-art H.264 CBR mode can have significant fluctuations, which can impact the NS optimization. We then exploited the proposed models to dynamically determine the Service Level Agreement (SLA) parameters in an NS scenario, providing service with the required QoS while minimizing resource usage.

cs.NI↗

arXiv2022

Autonomous Driving From the Sky: Design and End-to-End Performance Evaluation

For autonomous vehicles to operate without human intervention, information sharing from local sensors plays a fundamental role. This can be challenging to handle with bandwidth-constrained communication systems, which calls for the adoption of new wireless technologies, like in the mmwave bands, to solve capacity issues. Another approach is to exploit uav, able to provide human users and their cars with an aerial bird's-eye view of the scene otherwise unavailable, thus offering broader and more centralized observations. In this article we combine both aspects and design a novel framework in which uav, operating at mmwave, broadcast sensory information to the ground as a means to extend the (local) perception range of vehicles. To do so, we conduct a full-stack end-to-end simulation campaign with ns-3 considering real UAV data from the Stanford Drone Dataset, and study four scenarios representing different uav-to-ground communication strategies. Our results focus on the trade-off between centralized data processing in the sky vs. distributed local processing on the ground, with considerations related to the throughput, latency and reliability of the communication process.

cs.NI↗

arXiv2022

Rate-Constrained Remote Contextual Bandits

We consider a rate-constrained contextual multi-armed bandit (RC-CMAB) problem, in which a group of agents are solving the same contextual multi-armed bandit (CMAB) problem. However, the contexts are observed by a remotely connected entity, i.e., the decision-maker, that updates the policy to maximize the returned rewards, and communicates the arms to be sampled by the agents to a controller over a rate-limited communications channel. This framework can be applied to personalized ad placement, whenever the content owner observes the website visitors, and hence has the context, but needs to transmit the ads to be shown to a controller that is in charge of placing the marketing content. Consequently, the rate-constrained CMAB (RC-CMAB) problem requires the study of lossy compression schemes for the policy to be employed whenever the constraint on the channel rate does not allow the uncompressed transmission of the decision-maker's intentions. We characterize the fundamental information theoretic limits of this problem by letting the number of agents go to infinity, and study the regret that can be achieved, identifying the two distinct rate regions leading to linear and sub-linear regrets respectively. We then analyze the optimal compression scheme achievable in the limit with infinite agents, when using the forward and reverse KL divergence as distortion metric. Based on this, we also propose a practical coding scheme, and provide numerical results.

cs.LG↗

arXiv2022

SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints

Accurate scene understanding from multiple sensors mounted on cars is a key requirement for autonomous driving systems. Nowadays, this task is mainly performed through data-hungry deep learning techniques that need very large amounts of data to be trained. Due to the high cost of performing segmentation labeling, many synthetic datasets have been proposed. However, most of them miss the multi-sensor nature of the data, and do not capture the significant changes introduced by the variation of daytime and weather conditions. To fill these gaps, we introduce SELMA, a novel synthetic dataset for semantic segmentation that contains more than 30K unique waypoints acquired from 24 different sensors including RGB, depth, semantic cameras and LiDARs, in 27 different atmospheric and daytime conditions, for a total of more than 20M samples. SELMA is based on CARLA, an open-source simulator for generating synthetic data in autonomous driving scenarios, that we modified to increase the variability and the diversity in the scenes and class sets, and to align it with other benchmark datasets. As shown by the experimental evaluation, SELMA allows the efficient training of standard and multi-modal deep learning architectures, and achieves remarkable results on real-world data. SELMA is free and publicly available, thus supporting open science and research.

cs.CV↗