Abstract
Artificial Intelligence has recently expanded across various applications. Machine Learning, a subset of Artificial Intelligence, is a powerful technique for identifying patterns in data to support decision making and managing the increasing volume of information. Simultaneously, Digital Twins have been applied in several fields. In this context, combining Digital Twins, Machine Learning, and Smart Buildings offers significant potential to improve energy efficiency and operational effectiveness in building management. This review aims to identify and analyze studies that explore the application of Machine Learning and Digital Twins for operation and energy management in Smart Buildings, providing an updated perspective on these rapidly evolving topics. The methodology follows the PRISMA guidelines for systematic reviews, using Scopus and Web of Science databases. This review identifies the main concepts, objectives, and trends emerging from the literature. Furthermore, the findings confirm the recent growth in research combining Machine Learning and Digital Twins for building management, revealing diverse approaches, tools, methods, and challenges. Finally, this paper highlights existing research gaps and outlines opportunities for future investigation.

Abstract
In recent years, non-residential buildings have increasingly adopted renewable energy generation systems to align with the European Union's goal of achieving carbon neutrality by 2050. However, energy storage systems play a fundamental role in maximising the use of the generated renewable energy. Due to their high acquisition costs, adequately sizing these systems is essential. Moreover, applying an optimal scheduling strategy for energy storage operation can significantly improve the economic viability of such systems by reducing energy-related costs. In this paper, a MILP-based optimisation algorithm-incorporating battery lifespan constraints-is applied to a reference commercial building to schedule the operation of the storage system. A sensitivity analysis on the installed photovoltaic power and energy storage capacity is performed to evaluate their impact on the economic and operational performance of the optimisation algorithm under different sizing configurations.

Abstract
Recent studies have focused on forecasting power demand in buildings to enhance energy management. However, the literature still lacks comparative analyses of power demand forecasting algorithms. In addition, more case studies involving different building typologies are needed, as each building exhibits distinct behavior and load profiles. This paper aims to develop machine learning models to forecast the power demand of a large shopping center in the northern region of Portugal. The main objective is to compare the performance of several machine learning models. The results are promising, demonstrating adequate performance even during most holidays.

Abstract
The effective management of shared resources within energy communities poses a significant challenge, particularly when balancing renewable energy generation and fluctuating demand. This paper introduces a novel optimization framework that integrates people flow data, modeled using the Social Force Model (SFM), with energy management strategies to enhance the efficiency and sustainability of energy communities. By combining SFM with the Non-dominated Sorting Genetic Algorithm III (NSGA-III), the framework addresses multi-objective optimization problems, including minimizing energy costs, reducing user waiting times, and maximizing renewable energy utilization. The study employs synthesized data to simulate an energy community with shared facilities such as electric vehicle (EV) charging stations, communal kitchens, and laundry rooms. Results demonstrate the framework's ability to align energy generation with resource demand, reducing peak loads and improving user satisfaction. The optimization model effectively incorporates real-time behavioral dynamics, showcasing significant improvements in renewable energy utilization-reaching up to 88% for EV charging stations-and cost reductions across various scenarios. This research pioneers the integration of people flow modeling into energy optimization, providing a robust tool for managing the complexities of energy communities.

Abstract
The increasing reliance on Networked Microgrids (NMGs) for decentralized energy management introduces unprecedented cybersecurity risks, particularly in the context of False Data Injection Attacks (FDIA). While traditional FDIA studies have primarily focused on network-based intrusions, this work explores a novel cyber-physical attack vector leveraging Unmanned Aerial Vehicles (UAVs) to execute sophisticated cyberattacks on microgrid operations. UAVs, equipped with communication jamming and data spoofing capabilities, can dynamically infiltrate microgrid communication networks, manipulate sensor data, and compromise power system stability. This paper presents a multi-objective optimization framework for UAV-assisted FDIA, incorporating Non-dominated Sorting Genetic Algorithm III (NSGA-III) to maximize attack duration, disruption impact, stealth, and energy efficiency. A comprehensive mathematical model is formulated to capture the intricate interplay between UAV operational constraints, cyberattack execution, and microgrid vulnerabilities. The model integrates flight path optimization, energy consumption constraints, signal interference effects, and adaptive attack strategies, ensuring that UAVs can sustain long-duration cyberattacks while minimizing detection risk. Results indicate that UAV-assisted cyberattacks can induce power imbalances of up to 15%, increase operational costs by 30%, and cause voltage deviations exceeding 0.10 p.u.. Furthermore, analysis of attack success rates vs. detection mechanisms highlights the limitations of conventional rule-based anomaly detection, reinforcing the need for adaptive AI-driven cybersecurity defenses. The findings underscore the urgent necessity for advanced intrusion detection systems, UAV tracking technologies, and resilient microgrid architectures to mitigate the risks posed by airborne cyber threats.

Abstract
All over the world, there are several unoccupied spaces without adequate constant control mechanisms to reduce and prevent mold and provide good internal conditions and indoor air quality. A widespread way to reduce building humidity is through heating and dehumidification, which are costly to maintain and have high energy consumption. In addition, there are few studies on adjustable hygro ventilation systems, which do not consider the influence of temperature fluctuations. This work describes the operation of a prototype, which fills existing research gaps by considering not only the control of relative humidity (RH) but also the temperature peaks in indoor air conditions, allowing the maintenance of good air quality. The prototype Smart Hygrothermal Ventilation system uses two pairs of sensors related to RH and temperature, one pair placed inside an unoccupied compartment of the building and the other pair in the external environment, in order to activate a fan and the respective speed. The proposed prototype was applied in a compartment located on the ground floor in an unoccupied old rural building in a village near Porto during the winter period. The results show that the system performed adequately for different configurations of its functionalities. Therefore, the system offers an efficient alternative to minimize mold and the fluctuation of internal RH and temperature. Furthermore, it could be a vital mechanism for the conservation of historic buildings.