Using Bayesian deep learning approaches for uncertainty-aware building energy surrogate models

dc.contributor.authorWestermann, Paul
dc.contributor.authorEvins, Ralph
dc.date.accessioned2021-03-01T23:44:05Z
dc.date.available2021-03-01T23:44:05Z
dc.date.copyright2021en_US
dc.date.issued2021
dc.description.abstractFast machine learning-based surrogate models are trained to emulate slow, high-fidelity engineering simulation models to accelerate engineering design tasks. This introduces uncertainty as the surrogate is only an approximation of the original model. Bayesian methods can quantify that uncertainty, and deep learning models exist that follow the Bayesian paradigm. These models, namely Bayesian neural networks and Gaussian process models, enable us to give predictions together with an estimate of the model’s uncertainty. As a result we can derive uncertainty-aware surrogate models that can automatically identify unseen design samples that may cause large emulation errors. For these samples the high-fidelity model can be queried instead. This paper outlines how the Bayesian paradigm allows us to hybridize fast but approximate and slow but accurate models. In this paper, we train two types of Bayesian models, dropout neural networks and stochastic variational Gaussian Process models, to emulate a complex high dimensional building energy performance simulation problem. The surrogate model processes 35 building design parameters (inputs) to estimate 12 annual building energy performance metrics (outputs). We benchmark both approaches, prove their accuracy to be competitive, and show that errors can be reduced by up to 30% when the 10% of samples with the highest uncertainty are transferred to the high-fidelity model.en_US
dc.description.reviewstatusRevieweden_US
dc.description.scholarlevelFacultyen_US
dc.description.sponsorshipThis research was supported by grant funding from CANARIE via the BESOS project (CANARIE RS-327).en_US
dc.identifier.citationWestermann, P., & Evins, R. (2021). Using Bayesian deep learning approaches for uncertainty-aware building energy surrogate models. Energy and AI, 3, 1-13. https://doi.org/10.1016/j.egyai.2020.100039.en_US
dc.identifier.urihttps://doi.org/10.1016/j.egyai.2020.100039
dc.identifier.urihttp://hdl.handle.net/1828/12738
dc.language.isoenen_US
dc.publisherEnergy and AIen_US
dc.subjectSurrogate modellingen_US
dc.subjectMetamodelen_US
dc.subjectBuilding performance simulationen_US
dc.subjectUncertaintyen_US
dc.subjectBayesian deep learningen_US
dc.subjectGaussian Processen_US
dc.subjectBayesian neural networken_US
dc.titleUsing Bayesian deep learning approaches for uncertainty-aware building energy surrogate modelsen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Westermann_Paul_EnergyAI_2021.pdf
Size:
2.8 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2 KB
Format:
Item-specific license agreed upon to submission
Description: