Carbon emission and thermal comfort prediction model for an office building considering the contribution rate of design parameters
In recent years, increasing climate change has triggered the development of various techniques and strategies for predicting building energy consumption and thermal comfort. However, many features could affect prediction efficiency, and the coupling of appropriate learning algorithms with different...
Gespeichert in:
Veröffentlicht in: | Energy reports 2022-11, Vol.8, p.8093-8107 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In recent years, increasing climate change has triggered the development of various techniques and strategies for predicting building energy consumption and thermal comfort. However, many features could affect prediction efficiency, and the coupling of appropriate learning algorithms with different sampling methods and input parameters requires further research. In this study, we evaluated 25 features of an office building model. Then, the comprehensive effects of five different sampling methods and cumulative contribution rates (CCR) of input parameters on the prediction performance of building carbon emission (BCE) and indoor discomfort hour (IDH) were explored in 10 machine learning algorithms. The results indicated that the Sobol sampling method could achieve the best prediction effect in the combinations of different contribution rates of features and machine learning algorithms. Meanwhile, an artificial neural network (ANN) was the best learning algorithm when the CCR was 100%. However, the optimal machine learning method corresponding to each CCR stage differed. When the CCR was reduced to 50%, only three influence factors were considered most important, and K-nearest neighbors (KNN) was the best prediction algorithm in this scenario, indicating that the input parameters were reduced by 88%, and the R2 value was only reduced by 6.1%. Therefore, we proposed a new strategy idea for the research of building performance prediction by determining the most important building impact factors and suitable machine learning algorithms, which could simplify the prediction process and improve prediction efficiency while reducing building parameters.
•A prediction strategy with five sampling methods and ten ML algorithms, and eight CCRs of features were proposed.•CCRs of 25 input parameters on carbon emission and thermal comfort were calculated.•Sobol sampling method can achieve the best prediction effect.•K-nearest neighbors was the best learning algorithm when the CCR of features was reduced to 50%.•In the decrease of parameter number, R2 value of best strategy was only reduced by 6.1%. |
---|---|
ISSN: | 2352-4847 2352-4847 |
DOI: | 10.1016/j.egyr.2022.06.012 |