Enhancing Building Cooling Load Prediction with a Novel Time Series Approach for Sustainable Energy Management

Building cooling load prediction is a critical challenge for optimizing the energy performance of air conditioning systems, especially with rising global temperatures and the need for sustainable building management. This study introduces a novel time series approach to accurately predict building cooling loads. Considering seasonal weather changes and time-based schedules, we developed a Prophet model capable of providing reliable short-term to long-term cooling load predictions. The model underwent rigorously testing on a hypothetical hotel case study, showcasing higher prediction accuracy compared to the SARIMA model. These precise cooling load predictions enable proactive design and operation of chiller systems, resulting in significant energy savings and reduced environmental impact. The research findings emphasize the potential of advanced time series decomposition techniques to improve the accuracy of building cooling load prediction. This innovation sets the stage for widespread exploration and integration of low-carbon technologies to address the effects of climate change on the built environment.