In the transition towards a more circular built environment at all levels of design, digital support tools are needed to ensure effective material-related data exchange and enable the reduction of embodied energy in both products and buildings.

In this process of change, multi-stakeholder digital platforms can play a key role in promoting the collaboration among the different players involved in the various supply chains, helping them tackle the main challenges, including rising energy and raw material costs and the need to ensure energy and resource efficient solutions.

The AI-powered digital tool resulting from the NPRR research project “From waste to manufacturing: digital tools to establish virtuous cycles” integrates a web platform for circular materials, which enables data exchange between designers, manufacturers and waste recyclers, with a CAD plugin that supports real-time sustainability assessment with the help of AI-enhanced features, focusing on the nexus between the recycled content in materials and the reduction of embodied energy.

AI, trained through scenario-based learning with stakeholder participation during platform use, can support designers in researching and sourcing recycled/reused materials, as well as in data processing. By continuing training, with the support of LCA experts, AI could interpret complex documents such as Environmental Product Declarations, extracting the information needed to guide design towards the selection of circular, low-embodied-energy materials and products, as increasingly required by international regulations.

AI-enhanced design strategies for energy efficiency are opening new options for urban adaptation across diverse environments. Paris, Dijon, and Nice illustrate distinct approaches shaped by climate, governance structures, and policy frameworks. Their experiences show how cities can tailor AI applications in energy management to local constraints and opportunities. This paper identifies the institutional, technical, and social mechanisms that enable successful integration of AI solutions into urban energy systems, and highlights key considerations for adapting them elsewhere.

A comparative case study methodology underpins the analysis, drawing on official French reports, municipal open data, and academic and technical literature. The three cities were selected to represent different climatic zones and governance models. The study focuses on AI deployment in energy management at building and district scales, and on the roles of policy and stakeholder engagement in enabling or constraining experimentation.

The results show that Paris uses AI platforms to manage building energy use, optimize infrastructure, and support smart grid operation in a metropolitan context. Dijon’s centralized operations system coordinates multiple infrastructures, achieving significant energy savings, particularly in public lighting, through real-time monitoring, cross-domain data integration, and predictive control. Nice deploys AI to manage neighborhood-scale smart grids and integrate renewable energy under Mediterranean conditions, with particular emphasis on peak-load management and resilience. These cases reveal how performance is shaped by data governance, institutional capacity, and degrees of citizen and stakeholder participation.

The analysis identifies opportunities for adapting AI-based urban energy applications, while underscoring persistent challenges: data standardization, algorithmic transparency, interoperability across sectors, policy alignment, social acceptance, and privacy and security concerns. Addressing these issues is crucial to align technical innovation with institutional and societal conditions. The paper offers guidance for cities seeking to design and govern AI-based energy solutions that are both effective and context-sensitive.

Isolated microgrid, offshore platforms, and coastal communities face a dual critical challenge: ensuring a reliable electricity supply and continuous access to potable water while limiting dependence on fossil fuels. This paper deals with the design of a new water–energy microgrid architecture dedicated to a small island community and remote area, combining renewable power generation, hybrid energy storage, and seawater desalination. The investigated system integrates onshore photovoltaic (PV) panels, offshore wind turbines connected via a high-voltage direct current (HVDC) link, a seawater pumped storage plant using a single upper reservoir, a flywheel energy storage system (FESS) for fast power smoothing, a reverse osmosis (RO) desalination plant, a freshwater storage tank, and a small backup diesel generator.

In the first stage, a global coupled electricity–water model was developed. Then, an optimal control strategy using a recent metaheuristic algorithm was proposed to coordinate renewable generation, the pumping/turbining modes of the pumped storage plant, and the power allocated to the desalination unit. A small-signal stability analysis was also carried out around several representative operating points, examining dominant eigenvalues, damping margins, and the sensitivity to control and storage parameters (pumped storage, FESS).

Time-domain simulations and frequency-domain analysis show that the proposed architecture can maintain power–frequency balance in the microgrid while ensuring continuity of water supply. This work therefore lays the groundwork for a more advanced study of an Energy Management System (EMS) and multi-objective water–energy optimization, which will be addressed in future works.

Artificial intelligence (AI) technology and the industrial revolution (4IR) have potential for the raid advancement of smart buildings, materials, and construction processes to achieve global decarbonization goals. There is a need to perform the assessment work quickly and thoroughly to design the most appropriate retrofit system. Current retrofit techniques can vary a lot in their methodology from place to place, but what most have in common is time contraints and the need to follow budgets often and show significant reductions in energy usage. The objective of this research is to develop a framework that optimizes the façade retrofitting process with the help of AI, bringing it in as a decision-making tool that also accounts for other parameters, but differently to traditional retrofit methodologies, where both the designer and the user are the judges. Thus, this research explores the possibilities of recent AI tools such as Midjourney to be used for problem-solving in retrofitting. This is done with a literature review of the application of AI in the architectural field for retrofits, façade optimization, and image generation. From there, the overall framework suggested is developed addressing materiality, high performance analysis, affordable costs, and user-experience inputs, aiming for a successful retrofit. Furthermore, this research contributes to the retrofit discussions by initiating steps on how available AI tools can add to the discussion, carving out a pathway on how AI can help in this process. The results show an improvement in the way retrofits are addressed with the help of AI, mainly on user-experience, with their integration in the decision-making process.

Modern smart grids increasingly incorporate distributed energy resources, electric vehicles and renewable generation, which are creating complex energy management challenges. Traditional control approaches lack the intelligence and responsiveness required to manage rapidly fluctuating loads and irregular renewable production. To address these limitations, this study proposes an AI-driven Energy Management System (EMS) designed to enhance grid stability, operational efficiency and energy optimization in smart grid environments.

The proposed EMS integrates a Long Short-Term Memory (LSTM) model for short-term load forecasting with a Reinforcement Learning (RL) controller for real-time operational decision-making. The LSTM model is trained using historical load demand data to generate accurate short-term predictions while the RL agent learns optimal coordination strategies for distributed resources such as battery storage systems and rooftop photovoltaic (PV) units. System performance was evaluated using multiple test scenarios reflecting variable consumer demand and fluctuating renewable energy availability.

Results demonstrate that the AI-based forecasting approach improves prediction accuracy by 22% compared with conventional statistical models. Intelligent battery scheduling achieved a 15% reduction in peak demand while renewable energy utilization increased by 26%. The system also exhibited strong adaptability to sudden load variations, improved voltage and frequency stability and enabled cost-effective operation under dynamic grid conditions.

These findings highlight the significant potential of AI-enabled energy management to increase the flexibility, efficiency and resilience of next-generation smart grids. The proposed framework presents a scalable pathway for managing complex distributed energy environments and supports the global transition toward more intelligent and sustainable energy systems.

With energy demand increasing year by year, high-yield crop production requires the use of Controlled Environment Agriculture (CEA) facilities, such as modern greenhouses and precision technologies. However, the energy consumption for maintaining such an outstanding indoor climate, including temperature, humidity, and concentration, is exceptionally high. This study primarily focuses on the engineering challenge of improving energy efficiency through an Intelligent Hybrid Energy Management System (IHEMS) that leverages Artificial Intelligence (AI) to optimize in real-time solar photovoltaic (PV) and thermal energy storage systems in combination. The IHEMS employs a Model Predictive Control (MPC) algorithm integrated with a Deep Reinforcement Learning (DRL) agent. The MPC predicts future thermal and electrical loads based on crop-specific requirements, including external weather forecasts and historical, operational, and statistical data. The DRL agent then learns the most cost-effective and energy-efficient control plans for the hybrid system's components (e.g., maximizing PV self-consumption, coordinating the charging/discharging of the thermal storage tank, and modulating HVAC unit operation). The main objective is dual-target optimization. Firstly, minimize the net energy cost, and secondly, maintain the microclimate within a narrow, ideal band for maximum crop growth. The experimental validation using a test greenhouse facility shows that the IHEMS achieves up to a 25% reduction in peak power demand and an overall 18% reduction in energy consumption compared to traditional and conventional rule-based control systems, while significantly enhancing the potential for crop productivity. This research provides a robust engineering solution for sustainable, high-precision energy management in the future of the agriculture sector.

The shortage of medical oxygen during the COVID-19 pandemic exposed critical gaps in the healthcare infrastructure, particularly in hospitals that rely entirely on external supply chains and lack their own oxygen generation systems. This research presents a hybrid renewable energy solution that combines solar photovoltaic (PV) energy with a Proton Exchange Membrane (PEM) electrolyzer to produce medical-grade oxygen on-site and continuously, contributing to long-term resilience in oxygen availability.

The system is designed to operate in grid-connected environments with intermittent reliability, providing autonomy and security in oxygen supply without depending on conventional oxygen cylinders or bulk supply deliveries. A comprehensive techno-economic and energy optimization analysis was conducted to improve the system’s performance, considering variables such as solar irradiance, panel configuration, electrolyzer capacity, and daily oxygen demand.

Simulation results, based on real solar radiation data and hospital oxygen consumption profiles, demonstrate that the optimized hybrid solar-electrolyzer system is capable of meeting the hospital’s oxygen demand with stable performance. The results highlight the system’s potential to reduce reliance on external suppliers and increase operational independence for healthcare centers.

This study contributes to the development of sustainable, decentralized energy-based solutions tailored to real healthcare needs, enabling hospitals to ensure continuous oxygen availability through the integration of renewable energy technologies.

Fixed-bottom or floating offshore structures, including wind farms, oil/gas platforms, and subsea systems, provide higher and more consistent wind speeds, higher energy yield per turbine and per km, vast available area, reduced visual and noise impact, proximity to coastal load centres, lower land acquisition costs and conflicts, and synergies with existing maritime infrastructure, ports built for oil/gas, or shipping that can be repurposed. Design-to-Decommissioning AI-Driven Plant Design Modelling (D2D-AI-PDM) has the potential to enable a scalable, sustainable offshore energy, whether renewables or transition fuels, ensuring assets are designed once but optimised forever. Traditional fragmented approaches adopt tools that create data silos, leading to inefficiencies in the process. The end-to-end D2D-AI-PDM approach has the potential to evolve autonomously with real-world data, enabling predictive, optimised, and increasingly autonomous decision making.

This study reviews and highlights the current trends and level of adoption of the latest technologies, such as generative AI, neural networks, reinforcement learning, and self-updating digital twins, into a unified, continuous workflow that spans the entire offshore asset lifecycle, from conceptual design and engineering, procurement, construction, installation, and operations and maintenance (O&M), to decommissioning. The current trends and available platforms for achieving D2D-AI-PDM, as well as the current state and level of readiness of International Oil Companies (IOCs) to adopt them, were analysed using publicly available information. This study also highlights the challenges of data integration and interoperability, data privacy and governance, trust, and regulation, as well as skills in the offshore energy sector.

The biggest drawback for solar energy systems is the lack of performance during non-sunlit hours. While this can be overcome by integrating energy storage units into the systems, the initial investment cost and maintenance costs are disadvantages. Solar chimney power plants, a type of solar energy system, have a simple structure consisting of a collector, chimney, and turbine and operate solely on the principle of generating electricity by accelerating heated air upwards. The system's feasibility was demonstrated with the first prototype, Manzanares, which serves as the reference pilot plant in this study. Solutions are obtained after the validation and mesh-independent solution steps of the model created with the 3D CFD model. For real-world simulation, a discrete ordinates (DO) solar ray tracking algorithm is implemented in the analysis, assuming turbulent flow. Solar radiation enters the system through the translucent collector and reaches the ground. Solar radiation reaching the ground can be stored for heat transfer to the system air during non-sunlit hours using energy storage materials. Due to the system's structure, using storage materials in the ground is quite easy, and even using water with high heat capacity is possible. This study discusses the appropriate amounts of artificial intelligence-based energy storage systems for use on the ground. Solutions to increase energy storage efficiency and reduce performance degradation throughout the day are discussed. In particular, comprehensive recommendations are offered for maximum 24-hour performance.

This research develops a strategic management framework examining artificial intelligence integration with next-generation smart grids to enhance energy efficiency in university settings. As energy infrastructures become increasingly decentralized with higher renewable energy adoption and fluctuating demand patterns, academic institutions need sophisticated solutions to optimize consumption, minimize operational expenses, and achieve sustainability targets. The framework employs machine learning forecasting algorithms, multi-agent coordination systems, and reinforcement-learning optimization techniques to improve energy distribution, predict consumption patterns, and strengthen financial planning across campus operations. Additionally, it establishes energy governance metrics, enabling institutions to formulate transparent, evidence-based sustainability policies. Through combining organizational assessment, economic analysis, and AI-driven decision-making processes, this model demonstrates substantial capacity to decrease peak demand, enhance demand-response program participation, and boost system resilience. This interdisciplinary work bridges smart grid technology, artificial intelligence applications, and business management, providing a scalable methodology for universities, energy suppliers, and governmental organizations pursuing energy transition goals. The results underscore how intelligent management platforms facilitate more efficient, adaptable, and environmentally sustainable energy ecosystems. The proposed approach offers practical implementation pathways for institutions seeking to modernize their energy infrastructure while balancing economic viability with environmental responsibility, operational excellence, and strategic positioning in evolving energy landscapes characterized by technological and regulatory transformation.