ICD researcher Max Zorn will present a paper titled "Replacing Time-Consuming Building Performance Simulations with Real-Time Surrogate Models and their Application in Early-Stage Design Space Exploration", co-authored by Natasha Catunda, Luisa Claus, Natalia Kobylinska, Manuel Frey from Gruner AG and Tenure-Track Prof. Thomas Wortmann. The presentation is part of the BauSIM 2022 conference that will take place in Weimar, Germany.
Sustainable design requires holistic decision making already in the feasibility stage. One critical aspect of a buildings' sustainability is its operational energy consumption, but energy simulations typically are too time-consuming for early, fast-paced design phases. Data-based, Machine Learning models--so called surrogates--can replace time-consuming simulations with real-time estimates. This paper investigates the accuracy of different surrogate models for energy performance by comparing different types of models and numbers of samples. The paper also presents an integrated dashboard for holistic decision making as an application of the developed surrogate.