ITcon Vol. 28, pg. 622-645, http://www.itcon.org/2023/33

Machine learning-based energy use prediction for the smart building energy management system

DOI:10.36680/j.itcon.2023.033
submitted:April 2023
revised:June 2023
published:September 2023
editor(s):Chansik Park, Nashwan Dawood, Farzad Pour Rahimian, Akeem Pedro
authors:Mustika Sari, Ph.D.
Center for Sustainable Infrastructure Development, Universitas Indonesia, Indonesia;
mustika.sari01@ui.ac.id

Mohammed Ali Berawi, Professor
Department of Civil Engineering, Faculty of Engineering, Universitas Indonesia, Indonesia;
maberawi@eng.ui.ac.id

Teuku Yuri Zagloel, Professor
Department of Industrial Engineering, Faculty of Engineering, Universitas Indonesia, Indonesia;
yuri@ie.ui.ac.id

Nunik Madyaningarum, Ms.
National Research and Innovation Agency (BRIN), Indonesia;
nuni005@brin.go.id

Perdana Miraj, Ph.D. Student
Center for Sustainable Infrastructure Development, Universitas Indonesia, Indonesia;
perdana.miraj@ui.ac.id

Ardiansyah Ramadhan Pranoto, Mr.
Center for Sustainable Infrastructure Development, Universitas Indonesia, Indonesia;
ardiansyahpranoto@gmail.com

Bambang Susantono, Ph.D.
Center for Sustainable Infrastructure Development, Universitas Indonesia, Indonesia;
bsusantono@gmail.com

Roy Woodhead, Ph.D.
Sheffield Business School, Sheffield Hallam University, United Kingdom;
R.M.Woodhead@shu.ac.uk
summary:Smart building is a building development approach utilizing digital and communication technology to improve occupants' comfort inside the building and help increase energy usage efficiency in building operations. Despite its benefits, the smart building concept is still slowly adopted, particularly in developing countries. The advancement of computational techniques such as machine learning (ML) has helped building owners simulate and optimize various building performances in the building design process more accurately. Therefore, this study aims to assist energy efficiency design strategies in a building by identifying the features of the smart building characteristics that can potentially foster building energy efficiency. Furthermore, an ML model based on the features identified is then developed to predict the level of energy use. K-Nearest Neighbor (k-NN) algorithm is employed to develop the model with the openly accessible smart building energy usage datasets from Chulalongkorn University Building Energy Management System (CU-BEMS) as the training and testing datasets. The validation result shows that the predictive model has an average relative error value of 17.76%. The energy efficiency levels obtained from applying identified features range from 34.5% to 45.3%, depending on the reviewed floor. This paper also proposed the dashboard interface design for ML-based smart building energy management.
keywords:smart building, energy management system, energy use prediction, machine learning
full text: (PDF file, 1.112 MB)
citation:Sari M, Berawi M A, Zagloel T Y, Madyaningarum N, Miraj P, Pranoto A R, Susantono B, Woodhead R (2023). Machine learning-based energy use prediction for the smart building energy management system, ITcon Vol. 28, Special issue The future of construction in the context of digital transformation (CONVR 2022), pg. 622-645, https://doi.org/10.36680/j.itcon.2023.033
statistics: