Application of supervised learning methods to better predict building energy performance

Song Wu, Rima Alaaeddine

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Building energy consumption is shaped by a variety of factors which prompts a challenge of accurately predicting the building energy performance. Research findings disclosed a significant gap between the building’s predicted and actual energy performance. One of the key factors behind this gap is the occupant’s behavior during operation which includes a set of dependent and independent parameters generating a greater level of uncertainties. To accurately estimate the energy performance, we need to quantify the impact of any observed parameters and further detect its correlation with other parameters. Human behaviors are complex and quantifying the impact of all its interconnected parameters can be error prone and costly.
To minimize the performance gap, more scalable and accurate prediction approaches, such as supervised machine learning methods, should be considered.
This paper is devoted to investigate the most commonly used supervised learning methods which, when intertwined with conventional building energy performance prediction model, could potentially provide more accurate and reliable estimates. The paper will pinpoint the best use of each studied method in the relation to energy prediction in general and occupant’s behavior in specific and how it can be implemented to better predict building energy performance.
LanguageEnglish
Title of host publicationProceedings of the International Conference on Sustainable Futures
EditorsGhassan Aouad, Assem Alhajj, Charles Egbu
Publication statusPublished - 26 Nov 2017
EventInternational Conference on Sustainable Futures 2017 - Applied Science University, Sitra, Bahrain
Duration: 26 Nov 201727 Nov 2017
http://www.asu.edu.bh/international-conference-sustainable-futures-icsf-26-27-november-2017-applied-science-university-bahrain/ (Link to Conference Details)

Conference

ConferenceInternational Conference on Sustainable Futures 2017
Abbreviated titleICSF 2017
CountryBahrain
CitySitra
Period26/11/1727/11/17
Internet address

Fingerprint

Supervised learning
Learning systems
Energy utilization

Cite this

Wu, S., & Alaaeddine, R. (2017). Application of supervised learning methods to better predict building energy performance. In G. Aouad, A. Alhajj, & C. Egbu (Eds.), Proceedings of the International Conference on Sustainable Futures
Wu, Song ; Alaaeddine, Rima. / Application of supervised learning methods to better predict building energy performance. Proceedings of the International Conference on Sustainable Futures. editor / Ghassan Aouad ; Assem Alhajj ; Charles Egbu. 2017.
@inbook{a174616e90c241aa84764b7304c2a9f7,
title = "Application of supervised learning methods to better predict building energy performance",
abstract = "Building energy consumption is shaped by a variety of factors which prompts a challenge of accurately predicting the building energy performance. Research findings disclosed a significant gap between the building’s predicted and actual energy performance. One of the key factors behind this gap is the occupant’s behavior during operation which includes a set of dependent and independent parameters generating a greater level of uncertainties. To accurately estimate the energy performance, we need to quantify the impact of any observed parameters and further detect its correlation with other parameters. Human behaviors are complex and quantifying the impact of all its interconnected parameters can be error prone and costly. To minimize the performance gap, more scalable and accurate prediction approaches, such as supervised machine learning methods, should be considered. This paper is devoted to investigate the most commonly used supervised learning methods which, when intertwined with conventional building energy performance prediction model, could potentially provide more accurate and reliable estimates. The paper will pinpoint the best use of each studied method in the relation to energy prediction in general and occupant’s behavior in specific and how it can be implemented to better predict building energy performance.",
keywords = "energy performance , energy prediction, occupants' behaviour, performance gap, supervised machine learning",
author = "Song Wu and Rima Alaaeddine",
year = "2017",
month = "11",
day = "26",
language = "English",
isbn = "9789995890360",
editor = "Ghassan Aouad and Assem Alhajj and Charles Egbu",
booktitle = "Proceedings of the International Conference on Sustainable Futures",

}

Wu, S & Alaaeddine, R 2017, Application of supervised learning methods to better predict building energy performance. in G Aouad, A Alhajj & C Egbu (eds), Proceedings of the International Conference on Sustainable Futures. International Conference on Sustainable Futures 2017, Sitra, Bahrain, 26/11/17.

Application of supervised learning methods to better predict building energy performance. / Wu, Song; Alaaeddine, Rima.

Proceedings of the International Conference on Sustainable Futures. ed. / Ghassan Aouad; Assem Alhajj; Charles Egbu. 2017.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Application of supervised learning methods to better predict building energy performance

AU - Wu, Song

AU - Alaaeddine, Rima

PY - 2017/11/26

Y1 - 2017/11/26

N2 - Building energy consumption is shaped by a variety of factors which prompts a challenge of accurately predicting the building energy performance. Research findings disclosed a significant gap between the building’s predicted and actual energy performance. One of the key factors behind this gap is the occupant’s behavior during operation which includes a set of dependent and independent parameters generating a greater level of uncertainties. To accurately estimate the energy performance, we need to quantify the impact of any observed parameters and further detect its correlation with other parameters. Human behaviors are complex and quantifying the impact of all its interconnected parameters can be error prone and costly. To minimize the performance gap, more scalable and accurate prediction approaches, such as supervised machine learning methods, should be considered. This paper is devoted to investigate the most commonly used supervised learning methods which, when intertwined with conventional building energy performance prediction model, could potentially provide more accurate and reliable estimates. The paper will pinpoint the best use of each studied method in the relation to energy prediction in general and occupant’s behavior in specific and how it can be implemented to better predict building energy performance.

AB - Building energy consumption is shaped by a variety of factors which prompts a challenge of accurately predicting the building energy performance. Research findings disclosed a significant gap between the building’s predicted and actual energy performance. One of the key factors behind this gap is the occupant’s behavior during operation which includes a set of dependent and independent parameters generating a greater level of uncertainties. To accurately estimate the energy performance, we need to quantify the impact of any observed parameters and further detect its correlation with other parameters. Human behaviors are complex and quantifying the impact of all its interconnected parameters can be error prone and costly. To minimize the performance gap, more scalable and accurate prediction approaches, such as supervised machine learning methods, should be considered. This paper is devoted to investigate the most commonly used supervised learning methods which, when intertwined with conventional building energy performance prediction model, could potentially provide more accurate and reliable estimates. The paper will pinpoint the best use of each studied method in the relation to energy prediction in general and occupant’s behavior in specific and how it can be implemented to better predict building energy performance.

KW - energy performance

KW - energy prediction

KW - occupants' behaviour

KW - performance gap

KW - supervised machine learning

M3 - Chapter

SN - 9789995890360

BT - Proceedings of the International Conference on Sustainable Futures

A2 - Aouad, Ghassan

A2 - Alhajj, Assem

A2 - Egbu, Charles

ER -

Wu S, Alaaeddine R. Application of supervised learning methods to better predict building energy performance. In Aouad G, Alhajj A, Egbu C, editors, Proceedings of the International Conference on Sustainable Futures. 2017