Abstract
The advent of smart buildings owes much to the emergence of digital twins. In contemporary structures, a wealth of data is available, enabling the digital representation of buildings and facilitating improvements in energy management, particularly in heating, ventilation, and air conditioning (HVAC) systems. To effectively implement an energy management strategy within a building, a data-driven approach must accurately assess HVAC system attributes, with a focus on room temperature. Precise temperature forecasts not only enhance thermal comfort but also play a pivotal role in energy conservation. This research aims to explore data-driven methodologies and develop a model for room temperature prediction, employing machine learning algorithms in a case study of an educational building. This article details the methodology, points of interaction, and findings of this study. Relevant model parameters are identified to construct temperature prediction models using real-world data, demonstrating the efficacy of the proposed system, with an average prediction accuracy exceeding 95%. These results underscore its potential to enhance energy efficiency and thermal comfort, highlighting the use of Artificial Neural Networks (ANNs) as a pivotal component in achieving these goals.