This paper introduces a methodology for predicting a warehouse’s reduced load while offering flexibility. Physics-based energy simulations are first performed to model flexibility events, which involve adjusting cooling setpoints with controlled temperature increases to reduce the cooling load. The warehouse building encompasses office and storage spaces, and three cooling scenarios are implemented, i.e., exclusive storage area cooling, exclusive office area cooling, and cooling in both spaces, to expand the study’s potential applications. Next, the simulation data are utilized for training machine learning (ML)-based pipelines, predicting five subsequent hourly energy consumption values an hour before the setpoint adjustments, providing time to plan participation in demand response programs or prepare for charging electric vehicles. For each scenario, the performance of an Artificial Neural Network (ANN) and a tree-based ML algorithm are compared. Moreover, an expanding window scheme is utilized, gradually incorporating new data and emulating online learning. The results indicate the superior performance of the tree-based algorithm, with an average error of less than 3.5% across all cases and a maximum hourly error of 7%. The achieved accuracy confirms the method’s reliability even in dynamic scenarios where the integrated load of storage space and offices needs to be predicted.

The design of high-performance buildings has been questioned for their actual performance in operation, where the impact of external perturbations such as occupant behavior and climate has proved to be prominent. These sources of variability, called aleatory uncertainties, are inherent variations of nondeterministic systems and are irreducible. Therefore, one of the main approaches to deal with these uncertainties is to consider them as noise during the design phase. The goal of the design is hence achieving a solution whose performance is least sensitive to the noise. This specific design process is called robust design. In this study, a prospect of climate conditions that a building might face during its lifespan is identified. However, although robust design can support the design of building variants whose performance is insensitive to typical climate conditions and also predictable extreme climate conditions, these building variants cannot be considered protected in case of unforeseeable extreme events. During such events, another property called resilience is required, which focuses on withstanding and recovering during and after the occurrence of the event. This study reviews the concepts of robustness and resilience and organizes them into a framework that clarifies their relationships in the protection of buildings against climate uncertainties.