Alessandro Bozzi

This article presents a control framework designed to manage the speed, dwell time, and charging schedules of electric, automated, and connected buses operating on mixed-traffic lines without reserved lanes. The control architecture is composed of two layers, each defined by distinct objectives, levels of detail, and time scales, resulting in a multiscale control framework. The high-level control layer periodically solves a multiobjective optimal control problem to ensure the adequate transport service while considering a prediction of traffic conditions along the bus line. In contrast, the low-level control layer employs a model predictive control to accurately track the high-level control actions. The MPC-based low-level controller accounts for the detailed dynamic behavior of the bus, ensuring robust execution of the high-level directives. The effectiveness of the proposed control scheme is assessed through its application to a realistic case study in Italy, demonstrating improved service reliability and energy efficiency.

Anomaly detection is vital for sustainable petroleum transportation, as faults, or irregular routes cause fuel losses, ecological risks, and resource waste. This paper applies machine learning methods-Logistic Regression, SVM, Random Forest, XGBoost, k-Means, Isolation Forest, and Autoencoders-to detect anomalies in smart fuel distribution. Results on real data show that combining supervised and unsupervised approaches improves accuracy and reliability. To address limited labeled datasets, transfer learning is employed to enhance generalization and reduce data dependency. The proposed approach strengthens operational safety while advancing sustainability by minimizing fuel losses, preventing environmental harm, and promoting efficient resource use.

This article introduces a digital twin framework for greenhouse climate management, utilizing model predictive control (MPC) to enhance smart farming practices and tackle the challenge of maintaining optimal conditions in diverse weather scenarios. The proposed MPC integrates dynamic system modeling, predictive control, and constraint management to regulate critical variables such as ambient temperature, solar radiation, and airflow. To validate the control framework, historical meteorological data from the city of Savona are used for four seasonal scenarios: winter, spring, summer, and autumn. The main contributions include designing and tuning the MPC, applying soft constraints via equal concern for relaxation for feasibility, and implementing scaling factors to ensure numerical stability. Simulation results demonstrate the controller’s ability to maintain desired climatic conditions while meeting physical and operational constraints. This work highlights the potential of combining digital twin technology with advanced control systems to support sustainable and efficient smart farming.

This study addresses the challenge of implementing autonomous navigation on a low-cost robotic platform—a minicar equipped with a Raspberry Pi 3 and the Robot Operating System (ROS). The primary focus is on achieving accurate localization using a simplified sensor setup consisting only of a gyroscope and an odometer. Unlike traditional approaches that rely on expensive and computationally intensive sensor arrays such as LiDAR or cameras, this method estimates the minicar's position and orientation through real-time sensor data processing. The system enables autonomous navigation within a predefined environment, tracking coordinates and displaying movement data on a terminal. This work demonstrates that cost-effective sensor configurations, when integrated with ROS and optimized algorithms, can achieve reliable localization, reducing hardware complexity and making autonomous systems more accessible for resource-constrained applications.

Maintaining the integrity of petroleum transportation is essential for operational safety and efficiency. Substantial issues arise from faults in fuel transportation systems, including distribution valve malfunctions and anomalies in transit patterns, such as theft or unexpected fuel losses. This work presents a machine learning approach that combines supervised fault detection models, like Logistic Regression, SVM, Random Forest, and XGBoost, with unsupervised anomaly detection methods, such as k-means, Isolation Forest, and Autoencoders. The study employs real fuel transportation data and anomaly detection datasets obtained from petroleum distribution networks. Experimental results show that combining supervised and unsupervised methods leads to better detection accuracy and reliability, making the petroleum delivery system more dependable.

This article explores the management of automated guided vehicles within smart manufacturing systems, presenting an architecture designed to handle various stages in a fully automated production system. Trajectory planning is managed using a potential field controller, coupled with a time-of-arrival optimization for vehicles heading to shared resources, exploiting the concepts of virtual platoons. This approach optimizes arrival times at resources and minimizes energy consumption, prioritizing other elements directed toward currently available resources within the system. In addition, a decision-making algorithm schedules vehicles needing recharging due to low battery levels, ensuring uninterrupted production without overloading recharging stations and guaranteeing system efficiency. The proposed architecture is tested on three production orders of increasing complexity. Results demonstrate that the use of virtual platooning simplifies the dynamic trajectory generation of the potential field controller and, consequently, significantly reduces energy consumption and waiting times at shared resources, while reducing the variability on the production chain's makespan.

Today’s increasingly complex energy systems require innovative approaches to integrate and optimize different energy sources and technologies. In this paper, we explore the system of systems (SoS) approach, which provides a comprehensive framework for improving energy systems’ interoperability, efficiency, and resilience. By examining recent advances in various sectors, including photovoltaic systems, electric vehicles, energy storage, renewable energy, smart cities, and rural communities, this study highlights the essential role of SoSs in addressing the challenges of the energy transition. The principal areas of interest include the integration of advanced control algorithms and machine learning techniques and the development of robust communication networks to manage interactions between interconnected subsystems. This study also identifies significant challenges associated with large-scale SoS implementation, such as real-time data processing, decision-making complexity, and the need for harmonized regulatory frameworks. This study outlines future directions for improving the intelligence and autonomy of energy subsystems, which are essential for achieving a sustainable, resilient, and adaptive energy infrastructure.