It is essential to balance energy supply and demand in residential buildings through accurate forecasting of energy use due to varying daily and seasonal residential building loads. This study demonstrates a data-driven Virtual Energy Replication Framework (VERF) to predict the behavior of residential buildings using weather forecast data. The framework integrates supervised machine learning models and time-ahead weather parameters to estimate photovoltaic (PV) power production, heat pump energy consumption, and indoor thermal comfort. The accuracy of prediction models is validated using TRNSYS simulations of a typical household in Saarbrucken, Germany, a temperate oceanic climate region. The XGBoost model exhibits the highest reliability, achieving a root mean square error (RMSE) of 0.003 kW for PV power generation and 0.025 kW for heat pump energy use, with R² scores of 0.94 and 0.87, respectively. XGBoost and random forest regression models perform well in predicting PV generation and HP electricity load, with mean prediction errors of 5.27–6% and 0–7.7%, respectively. In addition, the thermal comfort index (PPD) is predicted with an RMSE of 1.84 kW and an R² score of 0.80 using the XGBoost model. The mean prediction error remains between 2.4% (XGBoost regression) and −11.5% (lasso regression) throughout the forecasted data. Because the framework requires no real-time instrumentation or detailed energy modelling, it is scalable and adaptable for smart building energy systems, and has particular value for Building-Integrated Photovoltaics (BIPV) demonstration projects on account of its predictive load-matching capabilities. The research findings justify the applicability of VERF for efficient and sustainable energy management using weather-informed prediction models in residential buildings.

The rapid evolution of supply chain management has necessitated the adoption of advanced technologies to enhance operational efficiency, sustainability, and resilience. This study investigated the role of artificial intelligence (AI) in building Intelligent Supply Chains 5.0, focusing on predictive analytics, adaptive logistics, and sustainable operations. Employing a mixed-methods research design, data were collected through structured surveys from supply chain professionals and semi-structured interviews with key stakeholders in organizations that had implemented AI-driven logistics systems. Quantitative findings indicated significant improvements in demand forecasting accuracy, real-time inventory management, and disruption response, while qualitative insights revealed enhanced decision-making capabilities, operational resilience, and environmental performance. AI-enabled predictive models facilitated precise demand estimations, reducing stockouts and optimizing inventory levels. Adaptive logistics applications allowed dynamic route adjustments and rapid response to unforeseen disruptions, thereby strengthening supply chain resilience. Sustainability outcomes included reductions in carbon emissions, energy consumption, and waste, highlighting AI’s contribution to environmentally responsible operations. Despite these benefits, challenges such as data quality issues, integration complexities, and ethical considerations were identified as critical barriers to successful implementation. The study concludes that AI serves as a strategic enabler for Intelligent Supply Chains 5.0, aligning operational performance with organizational sustainability and resilience objectives. Recommendations include workforce training, enhanced data governance, and ethical AI frameworks to support long-term adoption.

Solar–hydrogen hybrid systems provide low-carbon and dispatchable energy, yet most existing configurations implicitly assume freshwater availability, thereby overlooking the role of water reuse in water-stressed regions. In semi-arid industrial contexts, the integration of clean energy systems with circular water management is essential for long-term sustainability. This study develops a closed-loop Solar–Green Hydrogen Hybrid System (SGHHS) in which industrial effluent is treated through a membrane bioreactor–reverse osmosis–deionization (MBR→RO→DI) sequence to satisfy proton exchange membrane (PEM) electrolyzer water-quality requirements, while water recovered from fuel-cell exhaust is captured as condensate, achieving an overall water recovery rate of approximately 90%. The proposed system consists of a 22.75 MW photovoltaic array, a 2.25 MW electrolyzer, 450 kg of hydrogen storage, and a 1 MW fuel cell, and is evaluated using a 25-year hourly-resolution simulation framework. Economic performance is assessed through discounted cash-flow analysis, while environmental impacts are quantified using life-cycle assessment. Results demonstrate that integrating water reuse reduces the levelized cost of electricity from 0.10 to 0.0866 USD/kWh, avoids approximately 157,000 tonnes of CO₂-equivalent (tCO₂-eq)emissions, and enables the recovery of nearly 400,000 L/day of process water. By explicitly internalizing water-treatment capital and operating costs alongside water-savings benefits within the energy cost formulation, the study presents a generalizable framework linking hydrogen-based energy systems with circular water infrastructure, supporting industrial decarbonization and Sustainable Development Goals related to clean energy, responsible resource use, and climate action.