Educational building retrofit: a data-driven modelling approach for optimized energy efficiency

Energy efficiency and energy retrofit actions have been essential requirements to satisfy national and international directives and regulations that aim at reducing energy consumption and mitigating the impacts of climate change. Although most of the recent improvements have been carried out for residential buildings, representing around the 80% of the building stocks, the needs of addressing climate change issues shifted also towards non-residential buildings such as schools, which represent a critical target for energy-saving interventions due to their high energy usage and the large number of occupants [1]. School buildings form a significant part of the public building stock and tend to be less energy-efficient, as many were constructed in the post-World War era when energy efficiency was not a priority. However, the significant initial investments needed to address the challenges of these buildings demand optimized strategies that balance energy efficiency with sustainable costs.

The research developed a predictive model using an Artificial Neural Network to estimate the current space heating energy demand in buildings and to plan future retrofit actions. A dataset was created by parametrically generating artificial buildings with varying geometries and envelope properties, simulating them in EnergyPlus, and recording their energy demand. The trained ANN identified relationships between input parameters and heating demand, enabling accurate predictions [2]. Validation against EnergyPlus simulations confirmed the model’s effectiveness, demonstrating its potential for building energy performance assessment. The findings are expected to inform future policy decisions and guide investments in energy retrofitting for educational institutions across the country, while considering the limitations due to the limited timeframes available for the retrofit installation, the operational needs of these buildings and the type of actions applicable.

The identification of the most effective strategies can support the development of policies that not only enhance energy efficiency but also contribute to the broader goals of sustainability and climate resiliencein the built environment. Furthermore, the need of verifying that the expected savings are realized in practice highlight the requirement of ongoing monitoring and evaluation, thereby closing the gap between predicted and actual performance.Concluding, educational buildings play a key role as example of sustainable practices, educating future generations about the impact of energy-related emissions.