Paper Conference

Proceedings of eSim 2020: 11th Conference of IBPSA-Canada

     

Net-Zero Navigator: A platform for interactive net-zero building design using surrogate modelling

Gaëlle Faure, Paul Westermann, Kevin Cant, David Rulff, Ralph Evins
University of Victoria, Canada

Abstract: The design of high-performance buildings requires rapid iteration over many highly-integrated choices. These must be made early the design process, as certain performance targets like net-zero energy consumption may not be achievable at later stage. Existing high-resolution simulation approaches are not easily able to deliver fast, integrated design iterations. In this paper we introduce the Net-Zero Navigator, an open-source platform for conceptual building performance design based on surrogate modelling. It leverages state-of-the-art machine learning techniques to provide surrogate models which emulate high-fidelity building performance simulation results, providing accurate design performance estimates instantly. Results are given to quantify the performance of the surrogate modelling approach, which achieved R² values of over 96%. The platform builds on a suite of existing software tools (EnergyPlus, TensorFlow, KERAS API) as well as the codebase of the Building and Energy Simulation, Optimization and Surrogate-modelling (BESOS) platform. Overall, the Net-Zero Navigator platform provides a fast, interactive way to undertake concept-stage building design.
Paper:
esim2020_1235