A protocol for developing and evaluating neural network-based surrogate models and its application to building energy prediction

Simple item page
dc.contributor.authorHou, D.
dc.contributor.authorEvins, Ralph
dc.date.accessioned2024-03-27T15:44:12Z
dc.date.available2024-03-27T15:44:12Z
dc.date.issued2024
dc.description.abstractBecause of their low computational costs, surrogate models (SMs), also known as meta-models, have attracted attention as simplified approximations of detailed simulations. Besides conventional statistical approaches, machine-learning techniques, such as neural networks (NNs), have been used to develop surrogate models. However, surrogate models based on NNs are currently not developed in a consistent manner. The development process of the models is not adequately described in most studies. There may be some doubt regarding the abilities of such models due to a lack of documented validation. In order to address these issues, this paper presents a protocol for the systematic development of NN-based surrogate models and how the procedure should be reported and justified. The protocol covers the model development procedure sample generation, data processing, SM training and validation, how to report the implementation, and how to justify the modeling choices. The protocol is used to critically review the quality of NN-based SMs in the prediction of building energy consumption. Sixty-eight papers are reviewed, and details of the developed surrogate models are summarized. The reported developing procedures were evaluated using the criteria proposed in the protocol. The results show that the selection of the number of neurons is the best-implemented step with a justification, followed by the determination of model architecture, mostly justified in a discussion way. While greater focus should be given to sample dataset generation, especially input variables selection, considering independence check and clear report of model validation on training and test data. Also, data preprocessing is strongly recommended.
dc.description.reviewstatusReviewed
dc.description.scholarlevelFaculty
dc.description.sponsorshipThis work was supported by the ReBuild Initiative NSERC Alliance grant.
dc.identifier.citationHou, D., & Evins, R. (2024). A protocol for developing and evaluating neural network-based surrogate models and its application to building energy prediction. Renewable and Sustainable Energy Reviews, 193, 114283. https://doi.org/10.1016/j.rser.2024.114283
dc.identifier.urihttps://doi.org/10.1016/j.rser.2024.114283
dc.identifier.urihttps://hdl.handle.net/1828/16290
dc.language.isoen
dc.publisherRenewable and Sustainable Energy Reviews
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectprotocol
dc.subjectsurrogate model
dc.subjectmeta-model
dc.subjectneural networks
dc.subjectbuilding energy
dc.subjectsynthetic data
dc.subject.departmentDepartment of Civil Engineering
dc.titleA protocol for developing and evaluating neural network-based surrogate models and its application to building energy prediction
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
evins_ralph_RenewableSustainableEnergyRev_2024.pdf
Size:
5.36 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Faculty and Staff Publications
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.