Arcangela Rago

Dr. Arcangela Rago

DEI, Politecnico di Bari, Bari, Puglia, Italy
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 June 2020 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
Arcangela RagoArcangela Rago
Arcangela Rago
Giuseppe PiroGiuseppe Piro
Giuseppe Piro
GBGennaro Boggia
Gennaro Boggia
Paolo DiniPaolo Dini
Paolo Dini
Mobile traffic classification and prediction are key tasks for network optimization. Most of the works in this area present two main drawbacks. First, they treat the two tasks separately, thus requiring high computational capabilities. Second, they perform data mining on the information collected from the data plane, which is unsuitable for the mobile edge. To bridge this gap, this paper properly tailors a Multi-Task Learning model running directly at the edge of the network to anticipate information on the type of traffic to be served and the resource allocation pattern requested by each service during its execution. Our study exploits data mining from the control channel of an operative mobile network to also reduce storage and monitoring processing. Different configurations of neural networks, which adopt autoencoders (i.e. Undercomplete Autoencoder or Sequence to Sequence Autoencoder) as key building blocks of the proposed Multi-Task Learning methodology for common feature representations, are investigated to evaluate the impact of the observation window of traffic profiles on the classification accuracy, prediction loss, complexity, and convergence. The comparison with respect to conventional single-task learning approaches, that do not use autoencoders and tackle classification and prediction tasks separately, clearly demonstrates the effectiveness of the proposed Multi-Task Learning approach under different system configurations.

26 July 2021 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
Arcangela RagoArcangela Rago
Arcangela Rago
Giuseppe PiroGiuseppe Piro
Giuseppe Piro
GBGennaro Boggia
Gennaro Boggia
Paolo DiniPaolo Dini
Paolo Dini
Multi-access Edge Computing represents a key enabling technology for emerging mobile networks. It offers intensive computational resources very close to the end-users, useful for task offloading purposes. Many scientific contributions already proposed approaches for optimally allocating these resources over time. However, most of them fail to take advantage of the prediction of both users’ mobility and service demands over a look-ahead temporal horizon. To bridge this gap, this paper formulates a novel methodology for anticipatorily allocating communication and computational resources at the network edge, based on the prediction of spatio-temporal dynamics of mobile users. The conceived architecture exploits a Software-Defined Networking approach to monitor users’ mobility, a Convolutional Long Short-Term Memory to predict over different look-ahead horizons the number of users within a given number of cells and their related service demands, and Dynamic Programming to optimally allocate users’ requests among available Multi-access Edge Computing servers. Computer simulations investigate the effectiveness of the proposed approach in a realistic autonomous driving use case and compare its behavior against a baseline solution. Obtained results demonstrate its unique ability to dynamically and fairly distribute users’ requests among the resources available at the network edge, while ensuring the targeted quality of service level.

12 May 2025 in IEEE Communications Standards Magazine
Verified
Journal Article
Open access
Arcangela RagoArcangela Rago
Arcangela Rago
AGAlessandro Guidotti
Alessandro Guidotti
CACarla Amatetti
Carla Amatetti
NSNicola Sambo
Nicola Sambo
SMSimone Morosi
Simone Morosi
LGLuigi Alfredo Grieco
Luigi Alfredo Grieco
This paper explores the integration of Terrestrial Networks and Non-Terrestrial Networks (T/NTNs) as a critical enabler for the 6th Generation (6G) of communication systems. Starting from the 3rd Generation Partnership Project (3GPP) specifications and roadmap, this article investigates cutting-edge aspects of architectural designs, advanced transmission techniques, and cross-domain management strategies. In particular, in order to address challenges in seamless connectivity and optimized resource utilization, the proposed multi-layer approach combines terrestrial, aerial, and satellite components for improved coverage, scalability, and adaptability. Key and innovative contributions include modular waveform designs, efficient management of free-space optical links, and a comprehensive NTN framework.

19 December 2025 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
SCSalvatore Carbonara
Salvatore Carbonara
MOMarco Olivieri
Marco Olivieri
Arcangela RagoArcangela Rago
Arcangela Rago
VSVincenzo Sciancalepore
Vincenzo Sciancalepore
Giuseppe PiroGiuseppe Piro
Giuseppe Piro
LGLuigi Alfredo Grieco
Luigi Alfredo Grieco
The integration of Terrestrial and Non-Terrestrial Networks (T/NTNs) represents one of the most disruptive innovations on the basis of the upcoming 6th Generation (6G) of mobile communication systems. By incorporating Unmanned Aerial Vehicles, High Altitude Platform, and multi-orbit satellite constellations, it ushers in a new concept of network deployment that intends to enrich the coverage of typical terrestrial wireless systems in congested scenarios, provide ubiquitous connectivity to unconnected areas, and offer concrete support to next-generation use cases and applications. At the time of this writing, the standardization process of integrated T/NTNs is going to reach its peak of activity and many technological issues (spanning from advanced physical layer transmission techniques to flexible network management operations) are still under investigation. Indeed, considering that experimental tests can significantly sustain the study of both academia and industry, the knowledge of hardware and software tools able to emulate specific aspects of the overall network architecture would significantly boost the research towards concrete and solid technical solutions moving from theory to practice. Based on these premises, the contribution presented herein provides a comprehensive survey of hands-on solutions through which experimental testbeds dedicated to integrated T/NTNs can be deployed. Specifically, it encompasses hardware (such as Software-Defined Radios, channel emulators, Commercial Off-The-Shelf User Equipment, etc.), software (including those emulating core and radio access network), remotely accessible platforms, and other key enabling technologies of 6G. After reviewing some significant scientific works that adopted a subset of these solutions in their investigations, this survey sheds light on their adoption in more complex and heterogeneous network deployments. Finally, it summarizes the lessons learned and provides a list of challenging research topics related to the experimental tests of integrated T/NTNs.

26 March 2026 in IEEE Internet of Things Magazine
Verified
Journal Article
Closed access
Arcangela RagoArcangela Rago
Arcangela Rago
Alessio FascistaAlessio Fascista
Alessio Fascista
Giuseppe PiroGiuseppe Piro
Giuseppe Piro
GBGennaro Boggia
Gennaro Boggia
LGLuigi Alfredo Grieco
Luigi Alfredo Grieco
Explainable Artificial Intelligence (XAI) is emerging as an enabler of trustworthy and human-aligned decision making in next-generation IoT ecosystems. As 6G envisions a highly distributed Global Internet of Things paradigm, embedding explainability of AI models at the network edge will be essential for supporting critical emerging domains such as the Internet of Medical Things (IoMT). In this paper, we explore a practical integration of XAI methods at the edge of 6G IoT architectures and propose novel explainable feature selection and adaptive sample selection strategies that allow low-cost IoT devices to improve data acquisition, on-device processing, and communication efficiency in large-scale deployments. Through a practical case study using an experimental IoMT dataset and comparing different learning models, we show how SHapley Additive exPlanations (SHAP) can be used to interpret patient-related data, improve clinical insight, and significantly boost key performance and value indicators such as learning accuracy, energy consumption, and bandwidth utilization, outperforming traditional dimensionality-reduction techniques.

23 September 2026 in Computer Networks
Verified
Journal Article
Closed access
ARAdnan Rashid
Adnan Rashid
Adeel IqbalAdeel Iqbal
Adeel Iqbal
MFMuhammad Furqan
Muhammad Furqan
MKMuhammad Farhan Khan
Muhammad Farhan Khan
GSGiancarlo Sciddurlo
Giancarlo Sciddurlo
Arcangela RagoArcangela Rago
Arcangela Rago