A comparison of six metamodeling techniques applied to building performance simulations

Publikation: Forskning - peer reviewTidsskriftartikel

Abstrakt

Highlights
•Linear regression (OLS), support vector regression (SVR), regression splines (MARS).
•Random forest (RF), Gaussian processes (GPR), neural network (NN).
•Accuracy, time, interpretability, ease-of-use, model selection, and robustness.
•13 problems modelled for 9 training set sizes spanning from 32 to 8192 simulations.
•Methodology for comparison using exhaustive grid searches and sensitivity analysis.
Luk

Detaljer

Highlights
•Linear regression (OLS), support vector regression (SVR), regression splines (MARS).
•Random forest (RF), Gaussian processes (GPR), neural network (NN).
•Accuracy, time, interpretability, ease-of-use, model selection, and robustness.
•13 problems modelled for 9 training set sizes spanning from 32 to 8192 simulations.
•Methodology for comparison using exhaustive grid searches and sensitivity analysis.
OriginalsprogEngelsk
TidsskriftApplied Energy
Vol/bind211
Sider (fra-til)89-103
ISSN0306-2619
DOI
StatusE-pub ahead of print - 2018
PublikationsartForskning
Peer reviewJa

    Forskningsområder

  • Gaussian process regression (kriging), Random forest, Neural network, Support vector regression, Sensitivity analysis, Supervised learning
ID: 265086489