IBPSA-USA SimBuild 2024
Sustainability through Optimal Design of Buildings for Natural Ventilation using Updated Comfort and Occupancy Models
Figure (a)- The workflow of the research. Figure (b)- Wave Function Collapse (WFC) strategy: (1) Input example for training WFC model, indicating reference building configurations; (2) Output 40×40 solution from WFC solver containing multiple building layout candidates; (3) Tile grouping using graph analysis with red edges indicate building tile connections, blue edges indicate building core connections, and green outlines indicate valid layouts (containing at least one building core) for extraction; (4) Examples of isolated and extracted building layouts. Figure (c)- The Energy Use Intensity (EUI) obtained for all the simulated buildings, assuming: Phoenix, AZ location, multi-mode cooling strategy, a post-COVID occupancy presence model, and middle-income households. Figure (d)- A visual comparison of the hourly values of EUI and Percentage of Neutral Time (PNT) for the month of June in a simulation case for a sample layout, assuming a San Francisco location.
Abstract
IBPSA-USA SimBuild Conference 2024
Sustainability through Optimal Design of Buildings for Natural Ventilation using Updated Comfort and Occupancy Models
Jihoon Chung, Nastaran Shahmansouri, Rhys Goldstein, James Stoddart, John Locke
This research explores the benefits of incorporating natural ventilation (NV) simulation into a generative process of designing residential buildings to improve energy efficiency and indoor thermal comfort. Our proposed workflow uses the Wave Function Collapse algorithm to generate a diverse set of plausible floor plans. It also includes post-COVID occupant presence models while incorporating adaptive comfort models. We conduct four sets of experiments using the workflow, and the simulated results suggest that multi-mode cooling strategies combining conventional air conditioning with NV can often significantly reduce energy use while introducing only slight reductions in thermal comfort.
Download publicationAssociated Researchers
Jihoon Chung
Rensselaer Polytechnic Institute
Nastaran Shahmansouri
Former Autodesk
Related Resources
2024
Experiential Views: Towards Human Experience Evaluation of Designed Spaces using Vision-Language ModelsExploratory research on helping designers and architects anticipate…
2023
Leveraging Graph Neural Networks for Graph Regression and Effective Enumeration ReductionGraph-based framework represents aspects of optimal thermal management…
2023
Multi-split configuration design for fluid-based thermal management systemsThis work introduces a framework for automated exploration of optimal…
2023
Extracting Design Knowledge from Optimization Data: Enhancing Engineering Design in Fluid Based Thermal Management SystemsExtracting knowledge from optimization data in multi-split thermal…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us