AI-enhanced techno-economic and environmental optimization for nearly zero-energy building retrofitting: a case study of university campus

This study presents an AI-enhanced framework for the techno-economic and environmental optimization of nearly zero-energy building (nZEB) retrofitting strategies, demonstrated through a real-world case study at a university campus. The proposed methodology integrates dynamic energy modeling, photovoltaic (PV) system simulation, and artificial intelligence-based optimization to identify retrofit solutions that balance energy efficiency, financial viability, and carbon emissions reduction. Key performance indicators, including the levelized cost of electricity (LCOE), return on investment (ROI), internal rate of return (IRR), energy use intensity (EUI), and cumulative CO2 savings, are analyzed over a 25-year horizon. The study further accounts for improving grid emission factors and dynamic electricity tariffs, enhancing the accuracy of long-term sustainability projections. Results reveal that AI-driven decision support can significantly optimize retrofit pathways, achieving substantial CO2 reduction, financial returns, and renewable energy contributions that surpass the 50% nZEB threshold. The proposed framework offers a scalable, data-driven tool for policymakers, facility managers, and energy planners aiming to accelerate the transition toward decarbonized, resilient built environments.