arXiv subjects

Gianluca Fontanesi

Publications and source records attributed to Gianluca Fontanesi.

At least 19 recordsLinked to original sources

arXiv2026

An Informativeness-based Clustered Federated Learning Method for Reliable Traffic Prediction in Managed Wi-Fi Networks

Centrally-managed Wi-Fi solutions are increasingly leveraging Distributed Artificial Intelligence (AI) to predict key operational statistics of Access Points (APs) and proactively optimize network performance. In this context, Clustered Federated Learning (CFL) represents a fitting methodology, enabling the generation of multiple AI models that account for diverse statistical properties of the APs data distribution. However, identifying informative clusters for grouping APs models remains a significant challenge. In this paper, we address this problem by proposing a novel CFL tool integrating a two step clustering procedure. Initially, multiple clustering solutions are generated and filtered based on a minimum set of desired clustering criteria. Subsequently, if no solutions meet sufficient quality metrics, a global model is produced by aggregating all AP models. Otherwise, the final clustering solution is selected as the one that maximizes the informativeness (quantified via differential entropy) for the smallest cluster. Our results, focusing on a Wi-Fi traffic prediction problem, demonstrate that the developed CFL tool achieves the best predictive performance among all evaluated distributed strategies and the lowest communication and energy footprint among the clustered ones, exceeding the cost of single-model FL only in the regimes where it markedly improves accuracy.

eess.SP↗

arXiv2026

Adaptive Machine Learning Framework for UAV Trajectory Optimization in O-RAN

The deployment of unmanned aerial vehicles (UAV) as open radio units (O-RUs) in 6G cellular systems presents a promising opportunity to achieve scalable and adaptive network coverage. However, optimizing UAV trajectories in dynamic and unfamiliar environments remains a critical challenge, particularly due to the need for extensive retraining in each new scenario. In this paper, we introduce a novel UAV trajectory optimization framework that integrates enhanced continual transfer learning within the O-RAN architecture. The proposed system maintains a library of pre-trained models and employs a model selection mechanism to identify and transfer knowledge from the most relevant environments, minimizing adaptation time and improving efficiency. When no sufficiently similar model is available, a fallback model empowered by continuous refinements ensures baseline performance. The framework leverages real-world city maps and ray tracing techniques to enhance learning reliability and improve trajectory planning. Simulation results demonstrate that the proposed model selection-based transfer learning approach reduces convergence time by 44% to 56% compared to retraining from scratch, and up to 40% compared to traditional transfer learning without model selection.

eess.SP↗

arXiv2026

Cluster-Specific Predictive Modeling: A Scalable Solution for Resource-Constrained Wi-Fi Controllers

This manuscript presents a comprehensive analysis of predictive modeling optimization in managed Wi-Fi networks through the integration of clustering algorithms and model evaluation techniques. The study addresses the challenges of deploying forecasting algorithms in large-scale environments managed by a central controller constrained by memory and computational resources. Feature-based clustering, supported by Principal Component Analysis (PCA) and advanced feature engineering, is employed to group time series data based on shared characteristics, enabling the development of cluster-specific predictive models. Comparative evaluations between global models (GMs) and cluster-specific models demonstrate that cluster-specific models consistently achieve superior accuracy in terms of Mean Absolute Error (MAE) values in high-activity clusters. The trade-offs between model complexity (and accuracy) and resource utilization are analyzed, highlighting the scalability of tailored modeling approaches. The findings advocate for adaptive network management strategies that optimize resource allocation through selective model deployment, enhance predictive accuracy, and ensure scalable operations in large-scale, centrally managed Wi-Fi environments.

eess.SP↗

arXiv2025

Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences

This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.

cs.NI↗

arXiv2025

Energy Consumption Reduction for UAV Trajectory Training : A Transfer Learning Approach

The advent of 6G technology demands flexible, scalable wireless architectures to support ultra-low latency, high connectivity, and high device density. The Open Radio Access Network (O-RAN) framework, with its open interfaces and virtualized functions, provides a promising foundation for such architectures. However, traditional fixed base stations alone are not sufficient to fully capitalize on the benefits of O-RAN due to their limited flexibility in responding to dynamic network demands. The integration of Unmanned Aerial Vehicles (UAVs) as mobile RUs within the O-RAN architecture offers a solution by leveraging the flexibility of drones to dynamically extend coverage. However, UAV operating in diverse environments requires frequent retraining, leading to significant energy waste. We proposed transfer learning based on Dueling Double Deep Q network (DDQN) with multi-step learning, which significantly reduces the training time and energy consumption required for UAVs to adapt to new environments. We designed simulation environments and conducted ray tracing experiments using Wireless InSite with real-world map data. In the two simulated environments, training energy consumption was reduced by 30.52% and 58.51%, respectively. Furthermore, tests on real-world maps of Ottawa and Rosslyn showed energy reductions of 44.85% and 36.97%, respectively.

eess.SP↗

arXiv2024

"It's Your Turn": A Novel Channel Contention Mechanism for Improving Wi-Fi's Reliability

The next generation of Wi-Fi, i.e., the IEEE 802.11bn (aka Wi-Fi 8), is not only expected to increase its performance and provide extended capabilities but also aims to offer a reliable service. Given that one of the main sources of unreliability in IEEE 802.11 stems from the current distributed channel access, which is based on Listen-Before-Talk (LBT), the development of novel contention schemes gains importance for Wi-Fi 8 and beyond. In this paper, we propose a new channel contention mechanism, "It's Your Turn" (IYT), that extends the existing Distributed Coordination Function (DCF) and aims at improving the reliability of distributed LBT by providing ordered device transmissions thanks to neighboring activity awareness. Using simulation results, we show that our mechanism strives to provide reliable performance by controlling the channel access delay. We prove the versatility of IYT against different topologies, coexistence with legacy devices, and increasing network densities.

cs.NI↗

arXiv2024

Performance Evaluation of MLO for XR Streaming: Can Wi-Fi 7 Meet the Expectations?

Extended Reality (XR) has stringent throughput and delay requirements that are hard to meet with current wireless technologies. Missing these requirements can lead to worsened picture quality, perceived lag between user input and corresponding output, and even dizziness for the end user. In this paper, we study the capability of upcoming Wi-Fi 7, and its novel support for Multi-Link Operation (MLO), to cope with these tight requirements. Our study is based on simulation results extracted from an MLO-compliant simulator that realistically reproduces VR traffic. Results show that MLO can sustain VR applications. By jointly using multiple links with independent channel access procedures, MLO can reduce the overall delay, which is especially useful in the uplink, as it has more stringent requirements than the downlink, and is instrumental in delivering the expected performance. We show that using MLO can allow more users per network than an equivalent number of links using SLO. We also show that while maintaining the same overall bandwidth, a higher number of MLO links with narrow channels leads to lower delays than a lower number of links with wider channels.

cs.NI↗

arXiv2024

A Deep-NN Beamforming Approach for Dual Function Radar-Communication THz UAV

In this paper, we consider a scenario with one UAV equipped with a ULA, which sends combined information and sensing signals to communicate with multiple GBS and, at the same time, senses potential targets placed within an interested area on the ground. We aim to jointly design the transmit beamforming with the GBS association to optimize communication performance while ensuring high sensing accuracy. We propose a predictive beamforming framework based on a dual DNN solution to solve the formulated nonconvex optimization problem. A first DNN is trained to produce the required beamforming matrix for any point of the UAV flying area in a reduced time compared to state-of-the-art beamforming optimizers. A second DNN is trained to learn the optimal mapping from the input features, power, and EIRP constraints to the GBS association decision. Finally, we provide an extensive simulation analysis to corroborate the proposed approach and show the benefits of EIRP, SINR performance and computational speed.

eess.SP↗

arXiv2024

Continuous Transfer Learning for UAV Communication-aware Trajectory Design

Deep Reinforcement Learning (DRL) emerges as a prime solution for Unmanned Aerial Vehicle (UAV) trajectory planning, offering proficiency in navigating high-dimensional spaces, adaptability to dynamic environments, and making sequential decisions based on real-time feedback. Despite these advantages, the use of DRL for UAV trajectory planning requires significant retraining when the UAV is confronted with a new environment, resulting in wasted resources and time. Therefore, it is essential to develop techniques that can reduce the overhead of retraining DRL models, enabling them to adapt to constantly changing environments. This paper presents a novel method to reduce the need for extensive retraining using a double deep Q network (DDQN) model as a pretrained base, which is subsequently adapted to different urban environments through Continuous Transfer Learning (CTL). Our method involves transferring the learned model weights and adapting the learning parameters, including the learning and exploration rates, to suit each new environment specific characteristics. The effectiveness of our approach is validated in three scenarios, each with different levels of similarity. CTL significantly improves learning speed and success rates compared to DDQN models initiated from scratch. For similar environments, Transfer Learning (TL) improved stability, accelerated convergence by 65%, and facilitated 35% faster adaptation in dissimilar settings.

eess.SP↗

arXiv2024

Continuous Multi-Link Operation: A Contention-Free Mechanism for the Unlicensed Spectrum

This paper proposes a novel mechanism to enforce contention-free channel access in the unlicensed spectrum, as opposed to the traditional contention-based approach. To achieve this objective, we build on the Wi-Fi~7 multi-link operation (MLO) and define the means whereby independent channel access attempts are performed in all the addressable links to ensure one available channel/link is ready for transmission at all times, such that a sequence of continuous acquired channels can be maintained. We call this method continuous multi-link operation (ConMLO). In this work, we aim to verify the applicability of ConMLO, its ability to retain spectrum resources for a given duration of time, and its fairness with respect existing approaches, namely legacy single-link operation (SLO) and MLO. To this end, we use realistic data traffic measurements acquired in a crowded football stadium as an exemplary case of challenging spectrum occupation. Our results show that the proposed ConMLO can effectively guarantee continuous channel acquisition under different occupancy scenarios without compromising fairness of channel access compared to existing legacy modes.

eess.SP↗

arXiv2024

ConPA: A Contention-free Mechanism with Power Adaptation for Beyond Listen-Before-Talk

In view of the need to find novel means to utilize the unlicensed spectrum to meet the rising latency and reliability requirements of new applications, we propose a novel mechanism that allows devices to transmit anytime that a packet has to be delivered. The proposed mechanism, Contention-free with Power Adaptation (ConPA), aims to bypass the contention periods of current Listen-Before-Talk (LBT) approaches, which are the main source of unreliability in unlicensed technologies like Wi-Fi. To assess the feasibility of ConPA, we provide an analytical method based on Markov chains, which allows deriving relevant performance metrics, including throughput, airtime, and quality of transmissions. Using such a model, we study the performance of ConPA in various scenarios, and compare it to baseline channel access approaches like the Distributed Coordination Function (DCF) and the IEEE 802.11ax Overlapping Basic Service Set (OBSS) Packet Detect (PD)-based Spatial Reuse (SR). Our results prove the effectiveness of ConPA in reusing the space to offer substantial throughput gains with respect to the baselines (up to 76% improvement).

cs.NI↗

arXiv2023

Throughput Analysis of IEEE 802.11bn Coordinated Spatial Reuse

Multi-Access Point Coordination (MAPC) is becoming the cornerstone of the IEEE 802.11bn amendment, alias Wi-Fi 8. Among the MAPC features, Coordinated Spatial Reuse (C-SR) stands as one of the most appealing due to its capability to orchestrate simultaneous access point transmissions at a low implementation complexity. In this paper, we contribute to the understanding of C-SR by introducing an analytical model based on Continuous Time Markov Chains (CTMCs) to characterize its throughput and spatial efficiency. Applying the proposed model to several network topologies, we show that C-SR opportunistically enables parallel high-quality transmissions and yields an average throughput gain of up to 59% in comparison to the legacy 802.11 Distributed Coordination Function (DCF) and up to 42% when compared to the 802.11ax Overlapping Basic Service Set Packet Detect (OBSS/PD) mechanism.

cs.NI↗

arXiv2023

AI/ML-based Load Prediction in IEEE 802.11 Enterprise Networks

Enterprise Wi-Fi networks can greatly benefit from Artificial Intelligence and Machine Learning (AI/ML) thanks to their well-developed management and operation capabilities. At the same time, AI/ML-based traffic/load prediction is one of the most appealing data-driven solutions to improve the Wi-Fi experience, either through the enablement of autonomous operation or by boosting troubleshooting with forecasted network utilization. In this paper, we study the suitability and feasibility of adopting AI/ML-based load prediction in practical enterprise Wi-Fi networks. While leveraging AI/ML solutions can potentially contribute to optimizing Wi-Fi networks in terms of energy efficiency, performance, and reliability, their effective adoption is constrained to aspects like data availability and quality, computational capabilities, and energy consumption. Our results show that hardware-constrained AI/ML models can potentially predict network load with less than 20% average error and 3% 85th-percentile error, which constitutes a suitable input for proactively driving Wi-Fi network optimization.

cs.NI↗

arXiv2022

A Transfer Learning Approach for UAV Path Design with Connectivity Outage Constraint

The connectivity-aware path design is crucial in the effective deployment of autonomous Unmanned Aerial Vehicles (UAVs). Recently, Reinforcement Learning (RL) algorithms have become the popular approach to solving this type of complex problem, but RL algorithms suffer slow convergence. In this paper, we propose a Transfer Learning (TL) approach, where we use a teacher policy previously trained in an old domain to boost the path learning of the agent in the new domain. As the exploration processes and the training continue, the agent refines the path design in the new domain based on the subsequent interactions with the environment. We evaluate our approach considering an old domain at sub-6 GHz and a new domain at millimeter Wave (mmWave). The teacher path policy, previously trained at sub-6 GHz path, is the solution to a connectivity-aware path problem that we formulate as a constrained Markov Decision Process (CMDP). We employ a Lyapunov-based model-free Deep Q-Network (DQN) to solve the path design at sub-6 GHz that guarantees connectivity constraint satisfaction. We empirically demonstrate the effectiveness of our approach for different urban environment scenarios. The results demonstrate that our proposed approach is capable of reducing the training time considerably at mmWave.

cs.RO↗

arXiv2021

Embedded Firmware Development for a Novel CubeSat Gamma-Ray Detector

The Gamma-ray Module (GMOD) is an experiment designed for the detection of gamma-ray bursts in low Earth orbit as the principal scientific payload on a 2-U CubeSat, EIRSAT-1. GMOD comprises a cerium bromide scintillator coupled to silicon photomultipliers which are processed and digitised by a bespoke ASIC. Custom firmware on the GMOD motherboard has been designed, implemented and tested for the MSP430 microprocessor which manages the experiment including readout, storage and configuration of the system. The firmware has been verified in a series of experiments testing the response over a realistic range of input detector trigger frequencies from 50Hz to 1kHz for the primary time tagged event (TTE) data. The power consumption and ability of the firmware to successfully receive and transmit the packets to the on-board computer was investigated. The experiment demonstrated less than 1% loss of packets up to 1kHz for the standard transfer mode with the power not exceeding 31mW. The transfer performance and power consumption demonstrated are within the required range of this CubeSat instrument.

astro-ph.IM↗

arXiv2021

Deep Reinforcement Learning for Dynamic Band Switch in Cellular-Connected UAV

The choice of the transmitting frequency to provide cellular-connected Unmanned Aerial Vehicle (UAV) reliable connectivity and mobility support introduce several challenges. Conventional sub-6 GHz networks are optimized for ground Users (UEs). Operating at the millimeter Wave (mmWave) band would provide high-capacity but highly intermittent links. To reach the destination while minimizing a weighted function of traveling time and number of radio failures, we propose in this paper a UAV joint trajectory and band switch approach. By leveraging Double Deep Q-Learning we develop two different approaches to learn a trajectory besides managing the band switch. A first blind approach switches the band along the trajectory anytime the UAV-UE throughput is below a predefined threshold. In addition, we propose a smart approach for simultaneous learning-based path planning of UAV and band switch. The two approaches are compared with an optimal band switch strategy in terms of radio failure and band switches for different thresholds. Results reveal that the smart approach is able in a high threshold regime to reduce the number of radio failures and band switches while reaching the desired destination.

eess.SP↗

arXiv2020

Assembly, Integration, and Verification Activities for a 2U CubeSat, EIRSAT-1

The Educational Irish Research Satellite, EIRSAT-1, is a project developed by students at University College Dublin that aims to design, build, and launch Ireland's first satellite. EIRSAT-1 is a 2U CubeSat incorporating three novel payloads; GMOD, a gamma-ray detector, EMOD, a thermal coating management experiment, and WBC, a novel attitude control algorithm. The EIRSAT-1 project is carried out with the support of the Education Office of the European Space Agency, under the educational Fly your Satellite! programme. The Assembly, Integration and Verification plan for EIRSAT-1 is central to the philosophy and the development of the spacecraft. The model philosophy employed for the project is known as the 'prototype' approach in which two models of the spacecraft are assembled; an Engineering Qualification Model (EQM) and a Flight Model (FM). The payloads, GMOD and EMOD, and the Antenna Deployment Module (ADM) platform element warrant a Development Model in addition to an EQM and a FM, as they have been designed and developed in-house. After successful completion of the Critical Design Review and Ambient Test Readiness Review phases of the project, the EQM of EIRSAT-1 will be assembled and integrated. After assembly and integration of the EQM, the project will begin the ambient test campaign, in which the EQM undergoes ambient functional and mission testing. This work details the preparation and execution of the assembly, integration, and verification activities of EIRSAT-1 EQM.

astro-ph.IM↗

arXiv2020

Flight Software Development for the EIRSAT-1 Mission

The Educational Irish Research Satellite, known as EIRSAT-1, is a student-led project to design, build, test and launch Ireland's first satellite. The on-board software for this mission is being developed using Bright Ascension's GenerationOne Flight Software Development Kit. This paper provides an overview of this kit and of EIRSAT-1's on-board software design. Drawing on the team's contrasting experience with writing entirely custom firmware for the mission's science payloads, this work discusses the impact of using a kit on the software development process. The challenges associated with the educational nature of this project are the focus of this discussion. The objective of this paper is to provide useful information for other CubeSat teams assessing software development options.

astro-ph.IM↗