Repository logo
 

Comparative Study on Machine Learning for Urban Building Energy Analysis


Change log

Authors

Wei, L 
Tian, W 
Silva, EA 
Choudhary, R 
Meng, Q 

Abstract

There has been an increasing interest in applying machine learning methods in urban energy assessment. This research implemented six statistical learning methods in estimating domestic gas and electricity using both physical and socio-economic explanatory variables in London. The input variables include dwelling types, household tenure, household composition, council tax band, population age groups, etc. Six machine learning methods include two linear approaches (full linear and Lasso) and four non-parametric methods (MARS multivariate adaptive regression spline, SVM support vector machine, bagging MARS, and boosting). The results indicate all the four non-parametric models outperform two linear models. The SVM models perform the best among these models for both gas and electricity. The bagging MARS performs only a little worse than the SVM for gas use prediction. The Lasso model has the similar predictive capability to the full linear model in this case.

Description

Keywords

Urban buildings, Energy use, Machine learning, Comparative learning, Cross validation

Journal Title

Procedia Engineering

Conference Name

Journal ISSN

1877-7058
1877-7058

Volume Title

121

Publisher

Elsevier BV
Sponsorship
Engineering and Physical Sciences Research Council (EP/F034350/1)
Engineering and Physical Sciences Research Council (EP/L010917/1)
Engineering and Physical Sciences Research Council (EP/L024454/1)
This research is supported by the Tianjin Research Program of Application Foundation and Advanced Technology (No. 14JCYBJC42600) and the Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry of China.