M6-A Deep Learning for Energy Usage Prediction in Sustainable Building Design

PI: Praveen Rao

The 2030 Challenge states that all new buildings and developments should be carbon neutral by 2030; that is, no usage of fossil fuels for energy. Achieving sustainable design is the first step towards meeting this challenge. By providing intelligent tools to architects and engineers at design time, energy usage of a building can be predicted before actually constructing it. Deep learning holds promise to accurately model the complex relationship between 100+ building attributes and energy usage. Therefore, the objectives of this research are: (1) Develop a unified and accurate deep learning based regression model for predicting energy usage of different building types. (2) Develop a zero shot learning approach (using an ontology of building types) to accurately predict energy usage of building types whose data are not available during training. (3) Evaluate the deep learning model against traditional machine learning models. If successful, the proposed research can accurately model the energy usage of a variety of building types for architects and engineers (at design time).