Comparison of machine learning techniques for predicting energy loads in buildings

Machine learning methods can be used to help design energy-efficient buildings reducing energy loads while maintaining the desired internal temperature. They work by estimating a response from a set of inputs such as building geometry, material properties, project costs, local weather conditions, as...

पूर्ण विवरण

में बचाया:
ग्रंथसूची विवरण
मुख्य लेखकों: Duarte, Grasiele Regina, Fonseca, Leonardo Goliatt da, Goliatt, Priscila Vanessa Zabala Capriles, Lemonge, Afonso Celso de Castro
स्वरूप: Online
भाषा:eng
प्रकाशित: ANTAC - Associação Nacional de Tecnologia do Ambiente Construído 2017
ऑनलाइन पहुंच:https://seer.ufrgs.br/ambienteconstruido/article/view/69635
टैग : टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
id ojs-article-69635
record_format ojs
spelling ojs-article-696352017-06-30T15:35:30Z Comparison of machine learning techniques for predicting energy loads in buildings Duarte, Grasiele Regina Fonseca, Leonardo Goliatt da Goliatt, Priscila Vanessa Zabala Capriles Lemonge, Afonso Celso de Castro Energy Efficiency; Heating and Cooling Loads; Machine Learning Machine learning methods can be used to help design energy-efficient buildings reducing energy loads while maintaining the desired internal temperature. They work by estimating a response from a set of inputs such as building geometry, material properties, project costs, local weather conditions, as well as environmental impacts. These methods require a training phase which considers a dataset drawn from selected variables in the problem domain. This paper evaluates the performance of four machine learning methods to predict cooling and heating loads of residential buildings. The dataset consists of 768 samples with eight input variables and two output variables derived from building designs. The methods were selected based on exhaustive research with cross validation. Four statistical measures and one synthesis index were used for the performance assessment and comparison. The proposed framework resulted in accurate prediction models with optimized parameters that can potentially avoid modeling and testing various designs, helping to economize in the initial phase of the project. ANTAC - Associação Nacional de Tecnologia do Ambiente Construído FAPEMIG CAPES CNPq 2017-06-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://seer.ufrgs.br/ambienteconstruido/article/view/69635 Ambiente Construído; v. 17, n. 3 (2017); 103-115 Ambiente Construído; v. 17, n. 3 (2017); 103-115 Ambiente Construído; v. 17, n. 3 (2017); 103-115 1678-8621 1415-8876 eng https://seer.ufrgs.br/ambienteconstruido/article/view/69635/42241 Direitos autorais 2017 Ambiente Construído https://creativecommons.org/licenses/by/4.0
institution Universidade Federal do Rio Grande do Sul
collection OJS
language eng
format Online
author Duarte, Grasiele Regina
Fonseca, Leonardo Goliatt da
Goliatt, Priscila Vanessa Zabala Capriles
Lemonge, Afonso Celso de Castro
spellingShingle Duarte, Grasiele Regina
Fonseca, Leonardo Goliatt da
Goliatt, Priscila Vanessa Zabala Capriles
Lemonge, Afonso Celso de Castro
Comparison of machine learning techniques for predicting energy loads in buildings
author_facet Duarte, Grasiele Regina
Fonseca, Leonardo Goliatt da
Goliatt, Priscila Vanessa Zabala Capriles
Lemonge, Afonso Celso de Castro
author_sort Duarte, Grasiele Regina
title Comparison of machine learning techniques for predicting energy loads in buildings
title_short Comparison of machine learning techniques for predicting energy loads in buildings
title_full Comparison of machine learning techniques for predicting energy loads in buildings
title_fullStr Comparison of machine learning techniques for predicting energy loads in buildings
title_full_unstemmed Comparison of machine learning techniques for predicting energy loads in buildings
title_sort comparison of machine learning techniques for predicting energy loads in buildings
description Machine learning methods can be used to help design energy-efficient buildings reducing energy loads while maintaining the desired internal temperature. They work by estimating a response from a set of inputs such as building geometry, material properties, project costs, local weather conditions, as well as environmental impacts. These methods require a training phase which considers a dataset drawn from selected variables in the problem domain. This paper evaluates the performance of four machine learning methods to predict cooling and heating loads of residential buildings. The dataset consists of 768 samples with eight input variables and two output variables derived from building designs. The methods were selected based on exhaustive research with cross validation. Four statistical measures and one synthesis index were used for the performance assessment and comparison. The proposed framework resulted in accurate prediction models with optimized parameters that can potentially avoid modeling and testing various designs, helping to economize in the initial phase of the project.
publisher ANTAC - Associação Nacional de Tecnologia do Ambiente Construído
publishDate 2017
url https://seer.ufrgs.br/ambienteconstruido/article/view/69635
work_keys_str_mv AT duartegrasieleregina comparisonofmachinelearningtechniquesforpredictingenergyloadsinbuildings
AT fonsecaleonardogoliattda comparisonofmachinelearningtechniquesforpredictingenergyloadsinbuildings
AT goliattpriscilavanessazabalacapriles comparisonofmachinelearningtechniquesforpredictingenergyloadsinbuildings
AT lemongeafonsocelsodecastro comparisonofmachinelearningtechniquesforpredictingenergyloadsinbuildings
_version_ 1709370657368702976