Energy consumption prediction by using machine learning for smart building: Case study in Malaysia

Building Energy Management System (BEMS) has been a substantial topic nowadays due to its importance in reducing energy wastage. However, the performance of one of BEMS applications which is energy consumption prediction has been stagnant due to problems such as low prediction accuracy. Thus, this r...

Full description

Bibliographic Details
Main Authors: M. Shapi, Mel Keytingan, Nor Azuana, Ramli, Awalin, Lilik J.
Format: Article
Language:English
Published: Elsevier 2021
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/32877/
http://umpir.ump.edu.my/id/eprint/32877/1/Energy_Consumption_Prediction_by_using_Machine_Lea.pdf
_version_ 1848824131325263872
author M. Shapi, Mel Keytingan
Nor Azuana, Ramli
Awalin, Lilik J.
author_facet M. Shapi, Mel Keytingan
Nor Azuana, Ramli
Awalin, Lilik J.
author_sort M. Shapi, Mel Keytingan
building UMP Institutional Repository
collection Online Access
description Building Energy Management System (BEMS) has been a substantial topic nowadays due to its importance in reducing energy wastage. However, the performance of one of BEMS applications which is energy consumption prediction has been stagnant due to problems such as low prediction accuracy. Thus, this research aims to address the problems by developing a predictive model for energy consumption in Microsoft Azure cloud-based machine learning platform. Three methodologies which are Support Vector Machine, Artificial Neural Network, and k-Nearest Neighbour are proposed for the algorithm of the predictive model. Focusing on real-life application in Malaysia, two tenants from a commercial building are taken as a case study. The data collected is analysed and pre-processed before it is used for model training and testing. The performance of each of the methods is compared based on RMSE, NRMSE, and MAPE metrics. The experimentation shows that each tenant’s energy consumption has different distribution characteristics.
first_indexed 2025-11-15T03:08:09Z
format Article
id ump-32877
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:08:09Z
publishDate 2021
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling ump-328772022-02-04T04:33:12Z http://umpir.ump.edu.my/id/eprint/32877/ Energy consumption prediction by using machine learning for smart building: Case study in Malaysia M. Shapi, Mel Keytingan Nor Azuana, Ramli Awalin, Lilik J. QA Mathematics TK Electrical engineering. Electronics Nuclear engineering Building Energy Management System (BEMS) has been a substantial topic nowadays due to its importance in reducing energy wastage. However, the performance of one of BEMS applications which is energy consumption prediction has been stagnant due to problems such as low prediction accuracy. Thus, this research aims to address the problems by developing a predictive model for energy consumption in Microsoft Azure cloud-based machine learning platform. Three methodologies which are Support Vector Machine, Artificial Neural Network, and k-Nearest Neighbour are proposed for the algorithm of the predictive model. Focusing on real-life application in Malaysia, two tenants from a commercial building are taken as a case study. The data collected is analysed and pre-processed before it is used for model training and testing. The performance of each of the methods is compared based on RMSE, NRMSE, and MAPE metrics. The experimentation shows that each tenant’s energy consumption has different distribution characteristics. Elsevier 2021 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/32877/1/Energy_Consumption_Prediction_by_using_Machine_Lea.pdf M. Shapi, Mel Keytingan and Nor Azuana, Ramli and Awalin, Lilik J. (2021) Energy consumption prediction by using machine learning for smart building: Case study in Malaysia. Developments in the Built Environment, 5 (100037). pp. 1-14. ISSN 2666-1659. (Published) https://doi.org/10.1016/j.dibe.2020.100037 https://doi.org/10.1016/j.dibe.2020.100037
spellingShingle QA Mathematics
TK Electrical engineering. Electronics Nuclear engineering
M. Shapi, Mel Keytingan
Nor Azuana, Ramli
Awalin, Lilik J.
Energy consumption prediction by using machine learning for smart building: Case study in Malaysia
title Energy consumption prediction by using machine learning for smart building: Case study in Malaysia
title_full Energy consumption prediction by using machine learning for smart building: Case study in Malaysia
title_fullStr Energy consumption prediction by using machine learning for smart building: Case study in Malaysia
title_full_unstemmed Energy consumption prediction by using machine learning for smart building: Case study in Malaysia
title_short Energy consumption prediction by using machine learning for smart building: Case study in Malaysia
title_sort energy consumption prediction by using machine learning for smart building: case study in malaysia
topic QA Mathematics
TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/32877/
http://umpir.ump.edu.my/id/eprint/32877/
http://umpir.ump.edu.my/id/eprint/32877/
http://umpir.ump.edu.my/id/eprint/32877/1/Energy_Consumption_Prediction_by_using_Machine_Lea.pdf