Future vehicular networks require continuous connectivity to serve highly mobile users in urban environments. To mitigate the coverage limitations of fixed terrestrial macro base stations (MBS) under non line-of-sight (NLoS) conditions, fleets of unmanned aerial base stations (UABSs) can be deployed as aerial base stations, dynamically repositioning to track vehicular users and traffic hotspots in coordination with the terrestrial network. This paper addresses cooperative multi-agent trajectory design under different service areas and takeoff configurations, where rapid and safe adaptation across scenarios is essential. We formulate the problem as a multi-task decentralized partially observable Markov decision process and solve it using centralized training and decentralized execution with double dueling deep Q-network (3DQN), enabling online training for real-world deployments. However, efficient exploration remains a bottleneck, with conventional strategies like ε-greedy requiring careful tuning. To overcome this, we propose the multi-agent meta-advisor with advisor override (MAMO). This framework guides agent exploration through a meta-policy learned jointly across tasks. It uses a dynamic override mechanism that allows agents to reject misaligned guidance when the advisor fails to generalize to a specific scenario. Simulation results across three realistic urban scenarios and multiple takeoff configurations show that MAMO achieves faster convergence and higher returns than tuned ε-greedy baselines, outperforming both an advisor-only ablation and a single generalized policy. Finally, we demonstrate that the learned UABS fleet significantly improves network performance compared to deployments without aerial support.

Unmanned Aerial Vehicle (UAV), when equipped as communication relays, offer a flexible solution to extend Vehicle-to-Vehicle (V2V) communications beyond fixed infrastructure and Non-Line-of-Sight constraints. In this setting, the allocation of radio resources, across time, frequency and space through beamforming, is challenged by the mobility of Connected and Autonomous Vehicles (CAVs) and their temporal dependencies, as access opportunities depend on prior transmission outcomes such as queue backlog or failed attempts. This paper proposes a Radio Resource Assignment (RRA) framework for UAV-aided V2V networks with beamforming-capable UAV relays. The model discretizes time and space to account for mobility and to track the movement of groups of CAVs across beam segments. The model also incorporates Time Division Multiple Access (TDMA)-based scheduling, beam activation constraints, and realistic traffic generation patterns. Analytical expressions are derived for per-user success probability and system throughput under both, ideal and realistic conditions, and they are validated against simulations, confirming the accuracy of the proposed approximations. Numerical results highlight trade-offs involving UAV altitude and resource allocation interval, while a heuristic beam-activation optimization strategy is shown to further enhance performance, achieving up to 12% throughput gain over uniform activation.

Communication at Terahertz (THz) frequencies is strongly affected by high path loss and blockage, making multi-hop strategies essential, especially in obstacle-dense scenarios such as Industrial Internet of Things (IIoT) environments. We propose a joint Medium Access Control (MAC) and Network (NET) layer design, centered on a distributed Table-Based (TB) routing protocol that removes control-plane signaling by leveraging only user-plane data transmissions for route discovery and maintenance. The MAC layer employs a simple contention-based unslotted Aloha protocol, whose fully distributed nature makes it well-suited to THz IIoT multi-hop networks while avoiding the overhead of more complex contention-free schemes. The performance of TB is evaluated against two well-established NET-layer benchmarks: a Table-Less (TL) broadcast-forwarding scheme and the reactive Ad hoc On-Demand Distance Vector (AODV) protocol. Results show that AODV suffers from fairness degradation due to high control overhead and asynchronous route discovery, while TL can achieve higher throughput under congestion, but incurs higher latency due to suboptimal path selection. Overall, TB provides the best trade-off between fairness, throughput and latency. To further minimize the necessity of hyperparameter tuning, we also extend TB with a decentralized Multi-Agent Deep Reinforcement Learning (MADRL) mechanism that enables autonomous MAC-layer parameter adaptation. Simulations in a realistic IIoT scenario demonstrate that MADRL-TB delivers competitive performance compared to optimal static configurations while ensuring high robustness against parameter variations.

Industrial environments feature heterogeneous data sources with evolving and often conflicting communication requirements. This dynamic, multi-goal setting poses significant challenges, particularly due to the strict and variable demands on key performance metrics, such as latency and reliability, crucial for wireless networks enabling Industrial Internet of Things (IIoT) applications. Indeed, some sensors require low latency and high success probability, while others can tolerate delays, and these priorities can change over time as industrial processes evolve. Optimizing Medium Access Control (MAC) protocols in such conditions requires an accurate understanding of the temporal and spatial variability of sensor needs, something that traditional MAC designs are not well equipped to handle. To address this, we propose a Reinforcement Learning (RL)-based approach for MAC optimization in industrial networks. The proposed model builds upon a Carrier Sense Multiple Access (CSMA) MAC protocol, adaptively assigning Contention Window (CW) values to individual sensors to reflect the evolving communication demands of industrial processes. Its performance is evaluated against traditional benchmark approaches that rely on fixed CW configurations. Results demonstrate that the proposed solution dynamically adjusts network behavior to meet multi-goal requirements, satisfying both latency and reliability constraints by aligning CW assignments with sensor-specific needs in real time.

The emergence of Terahertz (THz) frequency wireless networks holds great potential for enabling various high-demand services, including Industrial Internet of Things (IIoT) applications. These applications benefit significantly from the ultra-high data rates, low latency, and high spatial resolution offered by THz frequencies. However, a primary well-known challenge of THz networks is their limited coverage range due to high path loss and vulnerability to obstructions. This paper addresses this limitation by proposing two novel multi-hop protocols, Table-Less (TL) and Table-Based (TB), respectively, both avoiding centralized control and/or control plane transmissions. Indeed, both solutions are distributed, simple, and rapidly adaptable to network changes. Simulation results demonstrate the effectiveness of our approaches, as well as revealing interesting trade-offs between TL and TB routing protocols, both in a real IIoT THz network and under static and dynamic conditions.

This paper introduces a dual-mode communication framework for wireless devices that integrates query-driven (pull) and event-driven (push) transmissions within a unified time-frame structure. Devices typically respond to information requests in pull mode, but if an anomaly is detected, they preempt the regular response to report the critical condition. Additionally, push-based communication is used to proactively send critical data without waiting for a request. This adaptive approach ensures timely, context-aware, and efficient data delivery across different network conditions. To achieve high energy efficiency, we incorporate a wake-up radio mechanism and we design a tailored medium access control (MAC) protocol that supports data traffic belonging to the different communication classes. A comprehensive system-level analysis is conducted, accounting for the wake-up control operation and evaluating three key performance metrics: the success probability of anomaly reports (push traffic), the success probability of query responses (pull traffic) and the total energy consumption. Numerical results characterize the system's behavior and highlight the inherent trade-off in success probabilities between push- and pull-based traffic as a function of allocated communication resources. Our analysis demonstrates that the proposed approach reduces energy consumption by up to 30

In modern industrial internet of things (IIoT) networks, efficient management of communications resources is crucial to match stringent application requirements. Differently from traditional resource allocation policies, goal-oriented communications is an emerging paradigm that aims at better optimizing network resource usage by prioritizing the transmission of information that is most relevant to a given task. Moreover, recent trends show increasing interest in distributed machine learning-based optimization to enhance network performance while reducing the reliance on centralized control. In this context, graph neural networks (GNNs) have emerged as a powerful tool for learning distributed policies among nodes facilitating their cooperation. In this paper, we introduce a goal-oriented, distributed framework to optimize uplink scheduling requests for coordinated message transmission to a remote server, while minimizing communication overhead. Our approach employs GNN-based distributed unsupervised learning framework that does not require a centralized controller. Extensive simulations in a 3GPP-compliant industrial scenario demonstrate that the proposed solution effectively reduces redundant uplink scheduling requests while achieving efficient and scalable coordination across multiple networks. Our findings highlight the potential of GNNs for learning distributed policies that enhance communication efficiency in wireless industrial IoT systems.

This paper addresses the joint design of Unmanned Aerial Vehicles (UAVs) trajectory and radio resource management (RRM) in dynamic wireless environments by leveraging a multi-agent deep reinforcement learning (MADRL) framework. In contrast to prior works that either assume constant synchronization between agents and the controller or overlook the communication cost, we explicitly model the interaction between UAVs and the central controller. We propose an adaptive synchronization strategy that selectively transmits model parameters and experience data based on their relevance, enabling a resource-aware RRM algorithm that optimally balances learning performance and communication overhead. The MADRL agents optimize their trajectories based on rewards that incorporate priorities derived from the RRM layer, which jointly manages both uplink and downlink communications. Simulation results demonstrate that our event-driven synchronization strategy outperforms periodic baselines in both convergence speed and communication overhead, towards scalable deployment in realistic urban environments.

Unmanned Aerial Vehicles (UAVs) deployed as aerial base stations (UABS) offer an adaptable solution for enhancing network performance, especially in vehicular networks. A key challenge is optimizing UABS trajectories in these dynamic environments. While Deep Reinforcement Learning (DRL) algorithms show the potential to solve this issue, their outcome wildly depends on the exploration phase carried out at the beginning of training. To address this, we introduce a deep meta advisor that, by applying efficient adaptation across similar tasks, learns an optimal exploration policy using augmented state inputs as additional context. Numerical results show that our approach improves agents learning efficiency across multiple tasks by enhancing the exploration phase, allowing to reach target performance with fewer training episodes compared to existing methods.

Unmanned aerial base stations (UABSs) are a promising solution for improving coverage and capacity in vehicle-to-everything (V2X) communications, particularly in dense urban areas. However, their operation is constrained by onboard energy consumption, required for both flight and communication. Beamforming, while enhancing network performance, adds to this challenge due to its energy-intensive nature.This paper proposes a sequential and hierarchical decision-making framework for UABS operations, considering trajectory planning, dynamic beamforming, and radio resource assignment (RRA). While heuristic and optimal solutions are employed for trajectory planning and RRA respectively, the beamforming model is modeled as Markov decision process (MDP) to maximize served user demand, weighted by time-varying priorities, under strict energy constraints. Leveraging a dueling double deep q-network (3DQN) algorithm that penalizes energy budget violations, an agent policy for the beamformer is then trained. Simulation results demonstrate that the proposed approach outperforms static beamforming benchmarks and closely matches an ideal step-wise oracle, achieving a balance between energy efficiency and served user demand while adapting to dynamic V2X traffic conditions.

In recent years, the integration of unmanned aerial vehicles (UAVs) into wireless networks has emerged as a promising solution to enhance coverage, optimize resourse allocation, and improve network performance in both uplink (UL) and downlink (DL) scenarios. This paper proposes a novel multi-agent deep reinforcement learning (MADRL) approach that combines UAV trajectory design with radio resource management (RRM). Our system adapts dynamically to user demands and network conditions, incorporating an interference management strategy and continuous service approach to enhance quality of experience (QoE) across multiple time instants. Experimental results demonstrate that our algorithm outperforms traditional placement strategies, achieving significant improvements in network performance, user satisfaction, and robustness under varying demand conditions. This work offers a practical solution for deploying UAVs in dense, real-world scenarios that require continuous and reliable connectivity.

This paper considers an Industrial Internet of Things (IIoT) scenario, where wireless devices embedded with sensors are deployed over an industrial machine, and transmit the measured data to a final Gateway (GW) using Terahertz (THz) frequencies. To mitigate the path loss of such high frequencies, the GW is equipped with multiple radiating elements, thereby generating highly directive beams, while sensors have just one single radiating element for miniaturization purposes. In this scenario, we study the applicability of a slotted Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) from a mathematical perspective. The analytical model is validated via comparison with simulations, and the impact of different simplifying assumptions in shown. We also demonstrate the effectiveness of the CSMA/CA when compared to ALOHA, and we prove that propagation delays cannot be neglected at THz frequencies.

In upcoming 6G networks, unmanned aerial vehicles (UAVs) are expected to play a fundamental role by acting as mobile base stations, particularly for demanding vehicle-to-everything (V2X) applications. In this scenario, one of the most challenging problems is the design of trajectories for multiple UAVs, cooperatively serving the same area. Such joint trajectory design can be performed using multi-agent deep reinforcement learning (MADRL) algorithms, but ensuring collision-free paths among UAVs becomes a critical challenge. Traditional methods involve imposing high penalties during training to discourage unsafe conditions, but these can be proven to be ineffective, whereas binary masks can be used to restrict unsafe actions, but naively applying them to all agents can lead to suboptimal solutions and inefficiencies. To address these issues, we propose a rank-based binary masking approach. Higher-ranked UAVs move optimally, while lower-ranked UAVs use this information to define improved binary masks, reducing the number of unsafe actions. This approach allows to obtain a good trade-off between exploration and exploitation, resulting in enhanced training performance, while maintaining safety constraints.

The introduction of LoRa chipsets operating in the 2.4 GHz band paves the way to unprecedented performance enhancements compared to their sub GHz counterparts, attributed to factors such as the absence of duty cycle constraints and higher data rates. Despite its potential benefits for Internet of Thing (IoT) applications, the LoRa Alliance has not yet proposed the integration of this new frequency spectrum into the LoRaWAN standard. Addressing this gap, this article proposes a roadmap for the evolution of the LoRaWAN standard, outlining three stages for seamless integration of the 2.4 GHz LoRa version. These stages are sequenced based on implementation complexity, starting from the current LoRaWAN standard (Stage 0), moving to the coexistence of two separate LoRaWAN networks (Stage 1), and ending with a single LoRaWAN network capable of supporting both sub GHz and 2.4 GHz bands (Stage 2). Additionally, the document enumerates all possible implementation options for each stage and outlines the main modifications required in the documents of the LoRaWAN standard. Through LoRaWAN-compliant simulation results, we demonstrate the performance advantages of the proposed multi-band approach over the existing LoRaWAN standard for the first stage of the suggested roadmap. Finally, the article discusses the challenges associated with the proposed roadmap and identifies corresponding research gaps to be addressed in the future.

We consider a setup with Internet of Things (IoT), where a base station (BS) collects data from nodes that use two different communication modes. The first is pull-based, where the BS retrieves the data from specific nodes through queries. In addition, the nodes that apply pull-based communication contain a wake-up receiver: upon a query, the BS sends wake-up signal (WuS) to activate the corresponding devices equipped with wake-up receiver (WuDs). The second one is push-based communication, in which the nodes decide when to send to the BS. Consider a time-slotted model, where the time slots in each frame are shared for both pull-based and push-based communications. Therein, this coexistence scenario gives rise to a new type of problem with fundamental trade-offs in sharing communication resources: the objective to serve a maximum number of queries, within a specified deadline, limits the transmission opportunities for push sensors, and vice versa. This work develops a mathematical model that characterizes these trade-offs, validates them through simulations, and optimizes the frame design to meet the objectives of both the pull- and push-based communications.

Unmanned Aerial Vehicles (UAVs), functioning as Unmanned Aerial Base Stations (UABSs), hold considerable potential for augmenting vehicular network performance through on-demand enhanced radio coverage. A pivotal challenge lies in devising algorithms that efficiently optimize UABS trajectories under strict Radio Resource Management (RRM) and coverage gap discovery. This can be tackled using Deep Reinforcement Learning (DRL) models. However, their effectiveness relies on the relevance of acquired knowledge to the current scenario, posing a challenge when the underlying dynamics or governing rules undergo modifications. To address this issue, we propose a framework integrating a deep meta-learning algorithm to enhance the adaptability of our DRL-based trajectory design to newly encountered scenarios. Scenarios may vary in mobile users’ movement profiles, UABS take-off zones, or new service maps. Our numerical results demonstrate that an agent that leverages information from prior tasks achieves target performance in fewer episodes compared to a conventional DRL agent, while also ensuring superior long-term training proficiency.

In this article, we address the deployment of Unmanned Aerial Vehicles (UAVs) as Unmanned Aerial Base Stations (UABSs) which cooperate with Macro Base Stations (MBSs) in an urban environment to serve vehicles, denoted as Ground User Equipments (GUEs), implementing vehicle-to-everything (V2X) services. As vehicles perform extended sensing, exchanging data with nearby GUEs through UAVs and MBSs links, we propose an Integer Linear Programming (ILP) model that jointly optimizes radio resources allocation and beamforming, while accounting for vehicular application requirements, backhaul capacity limits and interference between GUE-UABS and GUE-MBS links. The model allows also to find a trade-off between benefits and cost of UABSs activation. Two system architectures are considered: a distributed model, where MBSs independently run the Radio Resource Management (RRM) algorithm sharing information with each other, and a centralized model, where MBSs send information to the network core, where the optimization algorithm runs. The study investigates interference through two resource allocation approaches, considering splitting and sharing of resources among UABSs and MBSs. Numerical evaluations demonstrate the effectiveness of using UABSs to improve the Quality of Experience (QoE) of GUEs. We also compare the two architectures, considering both resource pool assignments, and highlighting the impact of varying UABSs parameters and activation costs.

The rapid expansion of connected and autonomous vehicles (CAVs) and the shift towards millimiter-wave (mmWave) frequencies offer unprecedented opportunities to enhance road safety and traffic efficiency. Sidelink communication, enabling direct Vehicle-to-Vehicle (V2V) communications, play a pivotal role in this transformation. As communication technologies transit to higher frequencies, the associated increase in bandwidth comes at the cost of a severe path and penetration loss. In response to these challenges, we investigate a network configuration that deploys beamforming-capable Unmanned Aerial Vehicles (UAVs) as relay nodes. In this work, we present a comprehensive analytical framework with a groundbreaking performance metric, i.e. average access probability, that quantifies user satisfaction, considering factors across different protocol stack layers. Additionally, we introduce two Radio Resources Assignment (RRA) methods tailored for UAVs. These methods consider parameters such as resource availability, vehicle distribution, and latency requirements. Through our analytical approach, we optimize the average access probability by controlling UAV altitude based on traffic density. Our numerical findings validate the proposed model and strategy, which ensures that Quality of Service (QoS) standards are met in the domain of Vehicle-to-Anything (V2X) sidelink communications.

In recent years, the use of unmanned aerial vehicles (UAVs) for wireless communications has been shown promising in a plethora of different applications. Their flexible deployment and mobility make them key enablers for the next generation of networks, provided that system design is properly addressed. In this article, we analyze a beyond-5G network where a UAV, acting as an unmanned aerial base station (UAB), is employed to collect data from reduced capability user equipments (UEs), deployed in an urban area. Specifically, we study a cluster-based scenario, where UEs are deployed following a Thomas cluster process, and the UAB flies over cluster centers according to the traveling salesman problem solution. Through the use of a stochastic approach, we mathematically devise the system performance accounting for uplink transmission protocol constraints, random access procedure, finite number of radio resources available, and coverage issues during the UAB flight. The mathematical model, validated via comparison with simulations, allows to optimize some system parameters, like the UAB speed, the number of UEs per cluster, and the number of radio resources to be used for the access and for data transmissions.

It is expected that future 6G vehicular networks will rely on Unmanned Aerial Vehicles (UAVs) acting as flying Base Stations, namely Unmanned Aerial Base Stations (UABSs), in order to provide a wide range of services that current terrestrial networks cannot manage. Vehicles may exploit strong links with the UABS, enabling applications such as advanced driving and extended sensing. In this context, if vehicular users are satisfied with an appropriate Quality of Experience (QoE), they are able to upload a given amount of data for a given time window, continuously. To allow this, an efficient path planning is fundamental. This paper presents a Deep Reinforcement Learning (DRL)-based solution, where a novel reward function is proposed with the aim of offering a continuous service to vehicles. Results are presented in terms of the percentage of satisfied users and both, a continuous action space as well as a discrete action space, are considered exploiting two different DRL algorithms (i.e., Double Dueling Deep Q Network (3DQN) and Deep Deterministic Policy Gradient (DDPG)) in order to compare the two and select the best one according to the described scenario of interest.