Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis
The problem of energy consumption and the importance of improving existing buildings’ energy performance are notorious. This work aims to contribute to this improvement by identifying the latest and most appropriate machine learning or statistical techniques, which analyze this problem by looking at...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Buildings |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-5309/12/1/28 |
_version_ | 1797495425198981120 |
---|---|
author | Maria Anastasiadou Vítor Santos Miguel Sales Dias |
author_facet | Maria Anastasiadou Vítor Santos Miguel Sales Dias |
author_sort | Maria Anastasiadou |
collection | DOAJ |
description | The problem of energy consumption and the importance of improving existing buildings’ energy performance are notorious. This work aims to contribute to this improvement by identifying the latest and most appropriate machine learning or statistical techniques, which analyze this problem by looking at large quantities of building energy performance certification data and other data sources. PRISMA, a well-established systematic literature review and meta-analysis method, was used to detect specific factors that influence the energy performance of buildings, resulting in an analysis of 35 papers published between 2016 and April 2021, creating a baseline for further inquiry. Through this systematic literature review and bibliometric analysis, machine learning and statistical approaches primarily based on building energy certification data were identified and analyzed in two groups: (1) automatic evaluation of buildings’ energy performance and, (2) prediction of energy-efficient retrofit measures. The main contribution of our study is a conceptual and theoretical framework applicable in the analysis of the energy performance of buildings with intelligent computational methods. With our framework, the reader can understand which approaches are most used and more appropriate for analyzing the energy performance of different types of buildings, discussing the dimensions that are better used in such approaches. |
first_indexed | 2024-03-10T01:48:29Z |
format | Article |
id | doaj.art-bb279ef2ffd04dac9bcca5d634fa590f |
institution | Directory Open Access Journal |
issn | 2075-5309 |
language | English |
last_indexed | 2024-03-10T01:48:29Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Buildings |
spelling | doaj.art-bb279ef2ffd04dac9bcca5d634fa590f2023-11-23T13:11:05ZengMDPI AGBuildings2075-53092021-12-011212810.3390/buildings12010028Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods AnalysisMaria Anastasiadou0Vítor Santos1Miguel Sales Dias2NOVA Information Management School, Universidade Nova de Lisboa, 1070-312 Lisbon, PortugalNOVA Information Management School, Universidade Nova de Lisboa, 1070-312 Lisbon, PortugalDepartment of Information Science and Technology, Instituto Universitário de Lisboa (ISCTE-IUL), ISTAR, 1649-026 Lisbon, PortugalThe problem of energy consumption and the importance of improving existing buildings’ energy performance are notorious. This work aims to contribute to this improvement by identifying the latest and most appropriate machine learning or statistical techniques, which analyze this problem by looking at large quantities of building energy performance certification data and other data sources. PRISMA, a well-established systematic literature review and meta-analysis method, was used to detect specific factors that influence the energy performance of buildings, resulting in an analysis of 35 papers published between 2016 and April 2021, creating a baseline for further inquiry. Through this systematic literature review and bibliometric analysis, machine learning and statistical approaches primarily based on building energy certification data were identified and analyzed in two groups: (1) automatic evaluation of buildings’ energy performance and, (2) prediction of energy-efficient retrofit measures. The main contribution of our study is a conceptual and theoretical framework applicable in the analysis of the energy performance of buildings with intelligent computational methods. With our framework, the reader can understand which approaches are most used and more appropriate for analyzing the energy performance of different types of buildings, discussing the dimensions that are better used in such approaches.https://www.mdpi.com/2075-5309/12/1/28energy performance certificate (EPC)machine learning (ML)energy-efficient retrofitting measures (EERM)energy performance of buildings (EPB)energy efficiency (EE) |
spellingShingle | Maria Anastasiadou Vítor Santos Miguel Sales Dias Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis Buildings energy performance certificate (EPC) machine learning (ML) energy-efficient retrofitting measures (EERM) energy performance of buildings (EPB) energy efficiency (EE) |
title | Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis |
title_full | Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis |
title_fullStr | Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis |
title_full_unstemmed | Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis |
title_short | Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis |
title_sort | machine learning techniques focusing on the energy performance of buildings a dimensions and methods analysis |
topic | energy performance certificate (EPC) machine learning (ML) energy-efficient retrofitting measures (EERM) energy performance of buildings (EPB) energy efficiency (EE) |
url | https://www.mdpi.com/2075-5309/12/1/28 |
work_keys_str_mv | AT mariaanastasiadou machinelearningtechniquesfocusingontheenergyperformanceofbuildingsadimensionsandmethodsanalysis AT vitorsantos machinelearningtechniquesfocusingontheenergyperformanceofbuildingsadimensionsandmethodsanalysis AT miguelsalesdias machinelearningtechniquesfocusingontheenergyperformanceofbuildingsadimensionsandmethodsanalysis |