Skip to the content.

Data-Driven Model Reduction, Scientific Frontiers, and Applications ()

Arash Noshadravan, Zachry Department of Civil & Environmental Engineering
Model Reduction for Simplifying Thermal Efficiency Planning at City Scale

Abstract

Thermal efficiency planning is a complex task that requires the consideration of a variety of factors, including the climate, the building stock, and the energy infrastructure. Complex models are often used to plan for thermal efficiency, but these models rely on a multitude of variables that may not always be available with sufficient accuracy and can also be computationally expensive and difficult to use. Model reduction can be used to replace the computationally expensive models without sacrificing accuracy. This can be done by identifying the key parameters that control building energy consumption and then using these parameters to develop physics-constrained data-driven reduced-order models. In this presentation, a model-reduction approach is proposed to simplify the estimates and to relate gas consumption from relevant information at a building level to the size of national sustainability goals. Multisource statistical data from gas bills, buildings' footprints, and physical simulations are incorporated to construct a simple yet efficient physics-based description of heating energy demand based on a model reduction scheme that encloses the most relevant parameters for the observed consumption. The capability of the model is tested in identifying buildings with the greatest potential for improvement and informing the aggregated gas savings.