Michele Pagano’s research while affiliated with University of Pisa and other places

Maintaining optimal microclimatic conditions within greenhouses represents a significant challenge in modern agricultural contexts, where prediction systems play a crucial role in regulating temperature and humidity, thereby enabling timely interventions to prevent plant diseases or adverse growth conditions. In this work, we propose a novel approach which integrates a cascaded Feed-Forward Neural Network (FFNN) with the Granular Computing paradigm to achieve accurate microclimate forecasting and reduced computational complexity. The experimental results demonstrate that the accuracy of our approach is the same as that of the FFNN-based approach but the complexity is reduced, making this solution particularly well suited for deployment on edge devices with limited computational capabilities. Our innovative approach has been validated using a real-world dataset collected from four greenhouses and integrated into a distributed network architecture. This setup supports the execution of predictive models both on sensors deployed within the greenhouse and at the network edge, where more computationally intensive models can be utilized to enhance decision-making accuracy.

In teletraffic engineering, M/G/1 queues are pivotal for optimizing network performance and operational efficiency. Closed formulas like the mean-value Pollaczek-Khinchin (MV-PK) are highly valued by practitioners due to their simplicity, facilitating rapid and flexible system analyses. This formula aids in verifying the reliability of complex simulations concerning M/G/1 models, especially when applicable. The challenge intensifies when dimensioning M/G/1 systems with heavy-tailed service time distributions. Simulation of such queues becomes notably arduous, necessitating increased number of samples and longer simulation durations. Moreover, verification becomes more intricate as the MV-PK formula cannot be straightforwardly applied in such cases. This paper extends the MV-PK formula to heavy tailed service distributions with infinite/infinitesimal moments using Nonstandard Analysis. Additionally , it shows how recently introduced Bounded Algo-rithmic Numbers (BANs) enables numerical verification of the extended PK formula via discrete-event simulations of the M/G/1 queue, even when predicted delay values are infinite. The implemented approach tends to converge fast and exhibits remarkable numerical robustness. It adheres to the principle of "write once, run multiple times", as the same source code for queue simulation handles both finite and infinite variance cases. Index Terms-M/G/1 model, heavy-tailed service time distribution , queuing system simulation, Pollaczek-Khinchin formula , Nonstandard Analysis.

Quantum computers have the potential to break the public-key cryptosystems widely used in key exchange and digital signature applications. To address this issue, quantum key distribution (QKD) offers a robust countermeasure against quantum computer attacks. Among various QKD schemes, BB84 is the most widely used and studied. However, BB84 implementations are inherently imperfect, resulting in quantum bit error rates (QBERs) even in the absence of eavesdroppers. Distinguishing between QBERs caused by eavesdropping and QBERs due to channel imperfections is fundamentally infeasible. In this context, this paper proposes and examines a practical method for detecting eavesdropping via partial intercept-and-resend attacks in the BB84 protocol. A key feature of the proposed method is its consideration of quantum system noise. The efficacy of this method is assessed by employing the Quantum Solver library in conjunction with backend simulators inspired by real quantum machines that model quantum system noise. The simulation outcomes demonstrate the method’s capacity to accurately estimate the eavesdropper’s interception density in the presence of system noise. Moreover, the results indicate that the estimation accuracy of the eavesdropper’s interception density in the presence of system noise is dependent on both the actual interception density value and the key length.

A single-server queueing system with n classes of customers, stationary superposed input processes, and general class-dependent service times is considered. An exponential splitting is proposed to construct classical regeneration in this (originally non-regenerative) system, provided that the component processes have heavy-tailed interarrival times. In particular, we focus on input processes with Pareto interarrival times. Moreover, an approximating GI/G/1-type system is considered, in which the independent identically distributed interarrival times follow the stationary Palm distribution corresponding to the stationary superposed input process. Finally, Monte Carlo and regenerative simulation techniques are applied to estimate and compare the stationary waiting time of a customer in the original and in the approximating systems, as well as to derive additional information on the regeneration cycles’ structure.

Due to limited infrastructure and remote locations, rural areas often need help providing reliable and high-quality network connectivity. We propose an innovative approach that leverages Software-Defined Wide Area Network (SD-WAN) architecture to enhance reliability in such challenging rural scenarios. Our study focuses on cases in which network resources are limited to network solutions such as Long-Term Evolution (LTE) and a Low-Earth-Orbit satellite connection. The SD-WAN implementation compares three tunnel selection algorithms that leverage real-time network performance monitoring: Deterministic, Random, and Deep Q-learning. The results offer valuable insights into the practical implementation of SD-WAN for rural connectivity scenarios, showing its potential to bridge the digital divide in underserved areas.

The paper presents an experimental security assessment within two widely used open-source 5G projects, namely Open5GS and OAI (Open-Air Interface). The examination concentrates on two network functions (NFs) that are externally exposed within the core network architecture, i.e., the Access and Mobility Management Function (AMF) and the Network Repository Function/Network Exposure Function (NRF/NEF) of the Service-Based Architecture (SBA). Focusing on the Service-Based Interface (SBI) of these exposed NFs, the analysis not only identifies potential security gaps but also underscores the crucial role of Mobile Network Operators (MNOs) in implementing robust security measures. Furthermore, given the shift towards Network Function Virtualization (NFV), this paper emphasizes the importance of secure development practices to enhance the integrity of 5G network functions. In essence, this paper underscores the significance of scrutinizing security vulnerabilities in open-source 5G projects, particularly within the core network’s SBI and externally exposed NFs. The research outcomes provide valuable insights for MNOs, enabling them to establish effective security measures and promote secure development practices to safeguard the integrity of 5G network functions. Additionally, the empirical investigation aids in identifying potential vulnerabilities in open-source 5G projects, paving the way for future enhancements and standard releases.

One-sided heavy tailed distributions have been used in many engineering applications, ranging from teletraffic modelling to financial engineering. In practice, the most interesting heavy tailed distributions are those having a finite mean and a diverging variance. The LogNormal distribution is sometimes discarded from modelling heavy tailed phenomena because it has a finite variance, even when it seems the most appropriate one to fit the data. In this work we provide for the first time a LogNormal distribution having a finite mean and a variance which converges to a well-defined infinite value. This is possible thanks to the use of Non-Standard Analysis. In particular, we have been able to obtain a Non-Standard LogNormal distribution, for which it is possible to numerically and experimentally verify whether the expected mean and variance of a set of generated pseudo-random numbers agree with the theoretical ones. Moreover, such a check would be much more cumbersome (and sometimes even impossible) when considering heavy tailed distributions in the traditional framework of standard analysis.