Multi-criteria comprehensive study on predictive algorithm of hourly heating energy consumption for residential buildings

•Compared five models with respect to interpretability, accuracy, robustness, and efficiency.•Studied the influence of the training dataset on the prediction performance.•The average of the indicators under different problems is used to measure the model accuracy.•Serves as a reference for the effic...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Sustainable cities and society Ročník 49; s. 101623
Hlavní autori: Wang, Ran, Lu, Shilei, Li, Qiaoping
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.08.2019
Predmet:
ISSN:2210-6707, 2210-6715
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •Compared five models with respect to interpretability, accuracy, robustness, and efficiency.•Studied the influence of the training dataset on the prediction performance.•The average of the indicators under different problems is used to measure the model accuracy.•Serves as a reference for the efficient implementation of an energy management system. The increasing of building energy necessitates reliable energy consumption prediction. Certain research work is necessary to thoroughly illustrate and compare advantages and disadvantages of various models. Therefore, this study investigated comprehensive trade-off between performances of commonly used forecasting models based on multiple performance metrics. Considering the requirements of actual building energy system, the objectives included accuracy, interpretability, robustness, and efficiency. With actual heating energy, prediction models were established by applying extreme gradient boosting (XGBoost), random forest (RF), artificial neural network (ANN), gradient boosting decision tree (GBDT), and support vector regression (SVR). A comparison revealed the following: 1) RF exhibits optimal average accuracy (under different training datasets), whereas ANN exhibits contrary properties. 2) The robustness of RF is the highest from adaptation to different training datasets with minimum standard deviation of error; XGBoost and ANN exhibit contrary properties. 3) RF, GBDT, and XGBoost are rendered effectively interpretable. 4) At equivalent accuracy level, ANN and SVR require auxiliary algorithms, whereas other models can achieve reasonable accuracy no tuning required. BPNN's calculation time is of an order magnitude higher than those of other models. Overall, XGBoost exhibits the optimal efficiency. This study can provide guidance for effectively selecting prediction models for energy management.
AbstractList •Compared five models with respect to interpretability, accuracy, robustness, and efficiency.•Studied the influence of the training dataset on the prediction performance.•The average of the indicators under different problems is used to measure the model accuracy.•Serves as a reference for the efficient implementation of an energy management system. The increasing of building energy necessitates reliable energy consumption prediction. Certain research work is necessary to thoroughly illustrate and compare advantages and disadvantages of various models. Therefore, this study investigated comprehensive trade-off between performances of commonly used forecasting models based on multiple performance metrics. Considering the requirements of actual building energy system, the objectives included accuracy, interpretability, robustness, and efficiency. With actual heating energy, prediction models were established by applying extreme gradient boosting (XGBoost), random forest (RF), artificial neural network (ANN), gradient boosting decision tree (GBDT), and support vector regression (SVR). A comparison revealed the following: 1) RF exhibits optimal average accuracy (under different training datasets), whereas ANN exhibits contrary properties. 2) The robustness of RF is the highest from adaptation to different training datasets with minimum standard deviation of error; XGBoost and ANN exhibit contrary properties. 3) RF, GBDT, and XGBoost are rendered effectively interpretable. 4) At equivalent accuracy level, ANN and SVR require auxiliary algorithms, whereas other models can achieve reasonable accuracy no tuning required. BPNN's calculation time is of an order magnitude higher than those of other models. Overall, XGBoost exhibits the optimal efficiency. This study can provide guidance for effectively selecting prediction models for energy management.
ArticleNumber 101623
Author Wang, Ran
Lu, Shilei
Li, Qiaoping
Author_xml – sequence: 1
  givenname: Ran
  surname: Wang
  fullname: Wang, Ran
– sequence: 2
  givenname: Shilei
  surname: Lu
  fullname: Lu, Shilei
  email: lvshilei@tju.edu.cn
– sequence: 3
  givenname: Qiaoping
  surname: Li
  fullname: Li, Qiaoping
BookMark eNp9kMtOwzAQRS0EEqX0A9j5B1Ls1HmJFap4SUVsYB059qSZKrUr26mUv8ehiAWLejOe0T0jzbkhl8YaIOSOsyVnPL_fLb3yy5Tx6qdPVxdklqacJXnBs8u_PyuuycL7HYsvy3klshkZ34c-YKIcBnAoqbL7g4MOjMcjUB8GPVJraJxpVGGayX5rY7rbU9vSzg6uH2kHMqDZUjDgtmNcYvywPwSMZGsddeBRgwkoe9oM2OuY9bfkqpW9h8VvnZOv56fP9Wuy-Xh5Wz9uEpVWRUgk16KsZMkzJVibZWlRlKWQTSt01Yg8bXipdcOlqAQrlMpVw4ApyBsuRMkkrOaEn_YqZ7130NYHh3vpxpqzetJV7-qor5701Sd9kSn-MQqDnO4JTmJ_lnw4kRBPOiK4mEAwKupzoEKtLZ6hvwEg9Y_m
CitedBy_id crossref_primary_10_1016_j_biortech_2025_133119
crossref_primary_10_1177_17442591251333144
crossref_primary_10_3390_modelling5020024
crossref_primary_10_1016_j_scs_2023_104892
crossref_primary_10_3390_buildings13020312
crossref_primary_10_1109_ACCESS_2021_3093094
crossref_primary_10_3390_buildings15142573
crossref_primary_10_1016_j_energy_2020_117714
crossref_primary_10_3390_s23094182
crossref_primary_10_1007_s10845_022_01912_5
crossref_primary_10_3390_en17040881
crossref_primary_10_1016_j_wace_2023_100595
crossref_primary_10_3390_en15072654
crossref_primary_10_1016_j_scs_2022_103723
crossref_primary_10_1016_j_apenergy_2020_114561
crossref_primary_10_1016_j_egyr_2022_01_162
crossref_primary_10_3390_su16125170
crossref_primary_10_1016_j_enbuild_2022_111943
crossref_primary_10_1080_23744731_2020_1787083
crossref_primary_10_1109_ACCESS_2022_3161654
crossref_primary_10_1016_j_enbuild_2022_112357
crossref_primary_10_1016_j_energy_2024_133639
crossref_primary_10_1016_j_heliyon_2024_e41507
crossref_primary_10_1016_j_enconman_2022_115507
crossref_primary_10_3390_en15217824
crossref_primary_10_1016_j_jobe_2025_113218
crossref_primary_10_3390_atmos12101341
crossref_primary_10_3390_jmse9020156
crossref_primary_10_3390_su132112302
crossref_primary_10_1016_j_energy_2019_116723
crossref_primary_10_1016_j_energy_2022_124179
crossref_primary_10_1007_s11760_025_04801_5
crossref_primary_10_1007_s10668_024_05263_4
crossref_primary_10_1051_itmconf_20246901009
crossref_primary_10_1177_0958305X231174000
crossref_primary_10_1016_j_asoc_2022_109520
crossref_primary_10_1186_s13638_020_01729_x
crossref_primary_10_3390_en14217367
crossref_primary_10_5194_hess_26_2969_2022
crossref_primary_10_1016_j_ijrefrig_2025_03_033
crossref_primary_10_1016_j_enbuild_2020_110022
crossref_primary_10_1016_j_fuel_2020_118848
crossref_primary_10_3390_en16062844
crossref_primary_10_1016_j_ijrefrig_2024_01_025
crossref_primary_10_1016_j_energy_2023_127069
crossref_primary_10_11627_jksie_2023_46_3_186
crossref_primary_10_1016_j_enbuild_2023_113217
crossref_primary_10_1016_j_enbuild_2025_115517
crossref_primary_10_1016_j_jag_2023_103383
crossref_primary_10_1016_j_energy_2024_131726
crossref_primary_10_1186_s13717_024_00515_7
crossref_primary_10_1016_j_rineng_2025_106132
crossref_primary_10_1016_j_atmosenv_2019_116973
crossref_primary_10_1016_j_jobe_2023_106403
crossref_primary_10_1080_19401493_2021_1927189
crossref_primary_10_3390_en14185947
crossref_primary_10_3390_fi13100242
crossref_primary_10_1016_j_envpol_2020_115720
crossref_primary_10_1016_j_jobe_2023_107855
crossref_primary_10_1016_j_jobe_2025_111809
crossref_primary_10_1016_j_scs_2020_102654
crossref_primary_10_1016_j_apenergy_2021_118410
crossref_primary_10_1016_j_eswa_2025_126783
crossref_primary_10_1016_j_jobe_2024_110500
crossref_primary_10_1016_j_apenergy_2022_118947
crossref_primary_10_1016_j_jobe_2024_109657
crossref_primary_10_1016_j_energy_2022_124919
crossref_primary_10_1109_TEM_2024_3422821
crossref_primary_10_3233_JIFS_213176
crossref_primary_10_1016_j_apenergy_2020_114822
crossref_primary_10_1016_j_jobe_2025_112542
crossref_primary_10_3390_en16062574
crossref_primary_10_1016_j_enbuild_2025_115309
crossref_primary_10_34248_bsengineering_1700159
crossref_primary_10_1016_j_engappai_2023_106958
crossref_primary_10_1016_j_energy_2024_131318
crossref_primary_10_1016_j_apenergy_2024_123488
crossref_primary_10_1016_j_enbuild_2024_115001
crossref_primary_10_3390_en15217856
crossref_primary_10_1016_j_enbuild_2023_113321
crossref_primary_10_1016_j_energy_2023_127645
crossref_primary_10_1016_j_enbuild_2025_115589
crossref_primary_10_1016_j_energy_2020_118045
crossref_primary_10_3390_su12208738
crossref_primary_10_1007_s12273_020_0637_y
crossref_primary_10_1016_j_energy_2022_123502
crossref_primary_10_1007_s00202_024_02611_5
crossref_primary_10_1007_s12273_024_1112_y
crossref_primary_10_1371_journal_pone_0312573
Cites_doi 10.1016/j.rser.2014.05.056
10.1016/j.rser.2016.10.079
10.1016/j.scs.2017.05.012
10.1016/j.apenergy.2017.10.102
10.1016/j.enbuild.2014.07.036
10.1016/j.applthermaleng.2017.09.007
10.1016/j.rser.2014.08.039
10.1023/A:1010933404324
10.1016/j.enbuild.2012.08.018
10.1016/j.enbuild.2017.08.077
10.1145/2939672.2939785
10.1109/TII.2011.2158841
10.1016/j.energy.2018.03.169
10.1016/j.buildenv.2008.01.002
10.1016/j.enbuild.2017.04.038
10.1016/j.asoc.2013.12.001
10.1016/j.apenergy.2008.11.035
10.1016/j.enbuild.2011.09.012
10.1016/j.enbuild.2010.04.006
10.1016/j.scs.2018.12.013
10.1016/j.enbuild.2018.12.032
10.1007/s00158-001-0160-4
10.1016/j.scs.2019.101533
10.1214/aos/1013203451
10.1109/TMECH.2014.2301716
10.1016/j.scs.2016.12.001
10.1016/j.rser.2017.04.095
10.1016/j.enconman.2017.04.077
10.1016/j.enconman.2018.02.087
10.1016/j.advengsoft.2008.05.003
10.1016/j.enconman.2016.04.051
10.1016/j.enbuild.2004.09.009
10.1016/j.agrformet.2018.08.019
10.1016/j.scs.2019.101484
10.1016/j.jclepro.2018.10.013
10.1016/j.scs.2015.12.001
10.1214/aos/1032181158
10.1016/j.asoc.2009.11.034
10.1016/j.enbuild.2017.01.083
10.1109/34.58871
10.1080/19401493.2010.524711
10.1007/s00158-009-0420-2
10.1016/j.aap.2006.04.009
10.1016/j.enbuild.2018.04.008
10.1016/j.scs.2018.06.008
10.1016/j.enbuild.2015.11.045
10.1111/j.1600-0587.2012.07348.x
10.1016/j.enbuild.2015.09.002
10.1016/j.enbuild.2018.06.050
10.1016/j.enconman.2008.08.033
10.1016/j.buildenv.2012.07.009
10.1016/j.apenergy.2014.04.016
ContentType Journal Article
Copyright 2019 Elsevier Ltd
Copyright_xml – notice: 2019 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.scs.2019.101623
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2210-6715
ExternalDocumentID 10_1016_j_scs_2019_101623
S2210670719309527
GroupedDBID --K
--M
.~1
0R~
1~.
4.4
457
4G.
5VS
7-5
8P~
AACTN
AAEDT
AAEDW
AAHCO
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARJD
AAXUO
ABFYP
ABJNI
ABLST
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ADBBV
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHEUO
AHIDL
AHJVU
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
AKIFW
AKYCK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOMHK
AVARZ
AXJTR
BELTK
BJAXD
BKOJK
BLECG
BLXMC
EBS
EFJIC
EFLBG
EJD
FDB
FEDTE
FIRID
FNPLU
FYGXN
GBLVA
HVGLF
HZ~
J1W
JARJE
JJJVA
KCYFY
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
P-8
P-9
PC.
Q38
RIG
ROL
SDF
SES
SPC
SPCBC
SSB
SSJ
SSO
SSR
SST
SSZ
T5K
~G-
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c297t-a1d489a815c40f55277884abf4d9b462b18ddb1a49407cc6cb0e0ce6b14480ae3
ISICitedReferencesCount 104
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000475860700036&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2210-6707
IngestDate Sat Nov 29 06:20:16 EST 2025
Tue Nov 18 22:28:01 EST 2025
Fri Feb 23 02:32:36 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Building energy prediction
Accuracy
Robustness
Extreme gradient boosting
Interpretability
Efficiency
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-a1d489a815c40f55277884abf4d9b462b18ddb1a49407cc6cb0e0ce6b14480ae3
ParticipantIDs crossref_primary_10_1016_j_scs_2019_101623
crossref_citationtrail_10_1016_j_scs_2019_101623
elsevier_sciencedirect_doi_10_1016_j_scs_2019_101623
PublicationCentury 2000
PublicationDate August 2019
2019-08-00
PublicationDateYYYYMMDD 2019-08-01
PublicationDate_xml – month: 08
  year: 2019
  text: August 2019
PublicationDecade 2010
PublicationTitle Sustainable cities and society
PublicationYear 2019
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Kyrö, Heinonen, Säynäjoki (bib0210) 2011; 43
Shan, Wang (bib0320) 2010; 41
Ahmad, Chen, Shair (bib0020) 2018; 152
Jin (bib0195) 2001; 23
Dormann, Elith, Bacher (bib0125) 2013; 36
Ouyang, Zha, Qin (bib0270) 2017; 144
Ding (bib0110) 2018; 128
Candanedo, Feldheim, Deramaix (bib0055) 2017; 140
Safa (bib0295) 2017; 29
Ürge-Vorsatz (bib0335) 2015; 41
Chang, Wang (bib0070) 2006; 38
Chen, Guestrin (bib0075) 2016
Ahmad, Mourshed, Rezgui (bib0015) 2017; 147
Fan (bib0160) 2018; 164
Ekici, Aksoy (bib0135) 2009; 40
Doshi-Velez, Kim (bib0130) 2017
Østergård (bib0260) 2018; 211
Østergård, Jensen, Maagaard (bib0265) 2018; 211
Chakraborty, Elzarka (bib0065) 2019; 185
Dietterich (bib0100) 2000
Reynolds, Rezgui, Hippolyte (bib0290) 2017; 35
Bergstra, Bengio (bib0035) 2012; 13
Li (bib0230) 2010; 10
Li (bib0220) 2009; 50
Li, Wen (bib0215) 2014; 37
Li, Wen, Reviews (bib0235) 2014; 37
Reid (bib0285) 2007
Haykin (bib0180) 1994; Vol. 2
Seyedzadeh (bib0315) 2019
Sun (bib0325) 2016; 119
Fan, Xiao, Wang (bib0150) 2014; 127
Vellido, Martin-Guerroro, Lisboa (bib0340) 2012; 12
Breiman (bib0050) 2001; 45
Ke (bib0200) 2017
Safa (bib0300) 2017; 29
Harrell (bib0175) 2015
Ditterrich (bib0115) 1997; 4
Zhao, Liu (bib0370) 2018; 174
Nicol (bib0255) 1998; 104
Chou, Bui (bib0090) 2014; 82
Esen (bib0140) 2008; 43
Wang, Srinivasan (bib0345) 2016; 75
Li (bib0225) 2009; 86
Bourdeau (bib0040) 2019
Chae (bib0060) 2016; 111
Fan (bib0155) 2018; 263
Fabi (bib0145) 2012; 58
Yu, Haghighat, Fung (bib0365) 2016; 25
Li (bib0245) 2019; 207
Scholkopf, Smola (bib0305) 2001
Chen, Guestrin (bib0080) 2016
Keshtkarbanaeemoghadam, Dehghanbanadaki, Kaboli (bib0205) 2018; 41
Ma, Cooper, Daly (bib0250) 2012; 55
Selakov (bib0310) 2014; 16
Hohman, Kahng, Pienta (bib0185) 2018
Awad, Khanna (bib0030) 2007; 11
Dong, Cao, Lee (bib0120) 2005; 37
Friedman (bib0165) 2001; 29
Yu (bib0360) 2010; 42
Wang, Srinivasan (bib0350) 2017; 75
Jiang (bib0190) 2009; 10
Palensky, Dietrich (bib0275) 2011; 7
Breiman (bib0045) 1996; 24
Parys, Saelens, Hens (bib0280) 2011; 4
Ahmad, Mourshed, Rezgui (bib0010) 2017; 147
Wang (bib0355) 2018; 171
Amasyali, El-Gohary (bib0025) 2018; 81
Ding, Zhang, Yuan (bib0105) 2017; 154
Hansen, Salamon (bib0170) 1990
Chou, Bui (bib0095) 2014; 82
China Building Energy Conservation Annual Development Research Report (bib0085) 2015
Li (bib0240) 2015; 108
Ahmad, Chen (bib0005) 2019; 45
Suryadevara (bib0330) 2014; 20
Chang (10.1016/j.scs.2019.101623_bib0070) 2006; 38
Østergård (10.1016/j.scs.2019.101623_bib0260) 2018; 211
Wang (10.1016/j.scs.2019.101623_bib0345) 2016; 75
Amasyali (10.1016/j.scs.2019.101623_bib0025) 2018; 81
Ding (10.1016/j.scs.2019.101623_bib0105) 2017; 154
Ditterrich (10.1016/j.scs.2019.101623_bib0115) 1997; 4
Kyrö (10.1016/j.scs.2019.101623_bib0210) 2011; 43
Ma (10.1016/j.scs.2019.101623_bib0250) 2012; 55
Chou (10.1016/j.scs.2019.101623_bib0090) 2014; 82
Zhao (10.1016/j.scs.2019.101623_bib0370) 2018; 174
Yu (10.1016/j.scs.2019.101623_bib0360) 2010; 42
Chen (10.1016/j.scs.2019.101623_bib0080) 2016
Keshtkarbanaeemoghadam (10.1016/j.scs.2019.101623_bib0205) 2018; 41
Doshi-Velez (10.1016/j.scs.2019.101623_bib0130) 2017
Suryadevara (10.1016/j.scs.2019.101623_bib0330) 2014; 20
Seyedzadeh (10.1016/j.scs.2019.101623_bib0315) 2019
Ahmad (10.1016/j.scs.2019.101623_bib0010) 2017; 147
Li (10.1016/j.scs.2019.101623_bib0235) 2014; 37
Shan (10.1016/j.scs.2019.101623_bib0320) 2010; 41
Bergstra (10.1016/j.scs.2019.101623_bib0035) 2012; 13
Ahmad (10.1016/j.scs.2019.101623_bib0020) 2018; 152
Jin (10.1016/j.scs.2019.101623_bib0195) 2001; 23
Friedman (10.1016/j.scs.2019.101623_bib0165) 2001; 29
Nicol (10.1016/j.scs.2019.101623_bib0255) 1998; 104
Hansen (10.1016/j.scs.2019.101623_bib0170) 1990
Fabi (10.1016/j.scs.2019.101623_bib0145) 2012; 58
Fan (10.1016/j.scs.2019.101623_bib0160) 2018; 164
Vellido (10.1016/j.scs.2019.101623_bib0340) 2012; 12
Reynolds (10.1016/j.scs.2019.101623_bib0290) 2017; 35
Ke (10.1016/j.scs.2019.101623_bib0200) 2017
China Building Energy Conservation Annual Development Research Report (10.1016/j.scs.2019.101623_bib0085) 2015
Jiang (10.1016/j.scs.2019.101623_bib0190) 2009; 10
Fan (10.1016/j.scs.2019.101623_bib0155) 2018; 263
Fan (10.1016/j.scs.2019.101623_bib0150) 2014; 127
Chae (10.1016/j.scs.2019.101623_bib0060) 2016; 111
Chen (10.1016/j.scs.2019.101623_bib0075) 2016
Ding (10.1016/j.scs.2019.101623_bib0110) 2018; 128
Wang (10.1016/j.scs.2019.101623_bib0355) 2018; 171
Wang (10.1016/j.scs.2019.101623_bib0350) 2017; 75
Haykin (10.1016/j.scs.2019.101623_bib0180) 1994; Vol. 2
Breiman (10.1016/j.scs.2019.101623_bib0045) 1996; 24
Li (10.1016/j.scs.2019.101623_bib0245) 2019; 207
Esen (10.1016/j.scs.2019.101623_bib0140) 2008; 43
Ahmad (10.1016/j.scs.2019.101623_bib0005) 2019; 45
Dormann (10.1016/j.scs.2019.101623_bib0125) 2013; 36
Safa (10.1016/j.scs.2019.101623_bib0295) 2017; 29
Awad (10.1016/j.scs.2019.101623_bib0030) 2007; 11
Parys (10.1016/j.scs.2019.101623_bib0280) 2011; 4
Candanedo (10.1016/j.scs.2019.101623_bib0055) 2017; 140
Chou (10.1016/j.scs.2019.101623_bib0095) 2014; 82
Palensky (10.1016/j.scs.2019.101623_bib0275) 2011; 7
Li (10.1016/j.scs.2019.101623_bib0215) 2014; 37
Yu (10.1016/j.scs.2019.101623_bib0365) 2016; 25
Hohman (10.1016/j.scs.2019.101623_bib0185) 2018
Li (10.1016/j.scs.2019.101623_bib0230) 2010; 10
Li (10.1016/j.scs.2019.101623_bib0225) 2009; 86
Reid (10.1016/j.scs.2019.101623_bib0285) 2007
Bourdeau (10.1016/j.scs.2019.101623_bib0040) 2019
Sun (10.1016/j.scs.2019.101623_bib0325) 2016; 119
Safa (10.1016/j.scs.2019.101623_bib0300) 2017; 29
Dong (10.1016/j.scs.2019.101623_bib0120) 2005; 37
Scholkopf (10.1016/j.scs.2019.101623_bib0305) 2001
Ekici (10.1016/j.scs.2019.101623_bib0135) 2009; 40
Ürge-Vorsatz (10.1016/j.scs.2019.101623_bib0335) 2015; 41
Breiman (10.1016/j.scs.2019.101623_bib0050) 2001; 45
Li (10.1016/j.scs.2019.101623_bib0240) 2015; 108
Dietterich (10.1016/j.scs.2019.101623_bib0100) 2000
Ouyang (10.1016/j.scs.2019.101623_bib0270) 2017; 144
Selakov (10.1016/j.scs.2019.101623_bib0310) 2014; 16
Li (10.1016/j.scs.2019.101623_bib0220) 2009; 50
Ahmad (10.1016/j.scs.2019.101623_bib0015) 2017; 147
Harrell (10.1016/j.scs.2019.101623_bib0175) 2015
Chakraborty (10.1016/j.scs.2019.101623_bib0065) 2019; 185
Østergård (10.1016/j.scs.2019.101623_bib0265) 2018; 211
References_xml – volume: 111
  start-page: 184
  year: 2016
  end-page: 194
  ident: bib0060
  article-title: Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings
  publication-title: Energy and Buildings
– volume: 152
  start-page: 788
  year: 2018
  end-page: 803
  ident: bib0020
  article-title: Water source heat pump energy demand prognosticate using disparate data-mining based approaches
  publication-title: Energy
– year: 2015
  ident: bib0175
  article-title: Regression modeling strategies: With applications to linear models, logistic and ordinal regression, and survival analysis
– volume: 4
  start-page: 339
  year: 2011
  end-page: 358
  ident: bib0280
  article-title: Coupling of dynamic building simulation with stochastic modelling of occupant behaviour in offices–a review-based integrated methodology
  publication-title: Journal of Building Performance Simulation
– volume: 16
  start-page: 80
  year: 2014
  end-page: 88
  ident: bib0310
  article-title: Hybrid PSO–SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank
  publication-title: Applied Soft Computing
– volume: 43
  start-page: 2178
  year: 2008
  end-page: 2187
  ident: bib0140
  article-title: Predicting performance of a ground-source heat pump system using fuzzy weighted pre-processing-based ANFIS
  publication-title: Building and Environment
– volume: 45
  start-page: 5
  year: 2001
  end-page: 32
  ident: bib0050
  article-title: Random forest
  publication-title: Machine Learning
– volume: 211
  start-page: 89
  year: 2018
  end-page: 103
  ident: bib0265
  article-title: A comparison of six metamodeling techniques applied to building performance simulations
  publication-title: Applied Energy
– volume: 24
  start-page: 2350
  year: 1996
  end-page: 2383
  ident: bib0045
  article-title: Heuristics of instability and stabilization in model selection
  publication-title: Annals of Statistics
– volume: 86
  start-page: 2249
  year: 2009
  end-page: 2256
  ident: bib0225
  article-title: Applying support vector machine to predict hourly cooling load in the building
  publication-title: Applied Energy
– start-page: 993
  year: 1990
  end-page: 1001
  ident: bib0170
  article-title: Neural network ensembles
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 55
  start-page: 889
  year: 2012
  end-page: 902
  ident: bib0250
  article-title: Existing building retrofits: Methodology and state-of-the-art
  publication-title: Energy and Buildings
– volume: 263
  start-page: 225
  year: 2018
  end-page: 241
  ident: bib0155
  article-title: Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China
  publication-title: Agricultural and Forest Meteorology
– volume: 12
  start-page: 163
  year: 2012
  end-page: 172
  ident: bib0340
  article-title: Making machine learning models interpretable
  publication-title: ESANN
– year: 2016
  ident: bib0075
  article-title: Xgboost: A scalable tree boosting system
  publication-title: Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining
– year: 2017
  ident: bib0130
  article-title: Towards a rigorous science of interpretable machine learning
– volume: 144
  start-page: 361
  year: 2017
  end-page: 373
  ident: bib0270
  article-title: A combined multivariate model for wind power prediction
  publication-title: Energy Conversion and Management
– volume: 75
  start-page: 796
  year: 2017
  end-page: 808
  ident: bib0350
  article-title: A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models
  publication-title: Renewable and Sustainable Energy Reviews
– volume: 41
  start-page: 85
  year: 2015
  end-page: 98
  ident: bib0335
  article-title: Heating and cooling energy trends and drivers in buildings
  publication-title: Renewable and Sustainable Energy Reviews
– volume: 29
  start-page: 1189
  year: 2001
  end-page: 1232
  ident: bib0165
  article-title: Greedy function approximation: A gradient boosting machine
  publication-title: Annals of Statistics
– volume: 42
  start-page: 1637
  year: 2010
  end-page: 1646
  ident: bib0360
  article-title: A decision tree method for building energy demand modeling
  publication-title: Energy and Buildings
– volume: 171
  year: 2018
  ident: bib0355
  article-title: Random forest based hourly building energy prediction
  publication-title: Energy and Buildings
– volume: 154
  year: 2017
  ident: bib0105
  article-title: Research on short-term and ultra-short-term cooling load prediction models for office buildings
  publication-title: Energy and Buildings
– year: 2018
  ident: bib0185
  article-title: Visual analytics in deep learning: An interrogative survey for the next frontiers
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– volume: 50
  start-page: 90
  year: 2009
  end-page: 96
  ident: bib0220
  article-title: Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks
  publication-title: Energy Conversion and Management
– volume: 140
  year: 2017
  ident: bib0055
  article-title: Data driven prediction models of energy use of appliances in a low-energy house
  publication-title: Energy and Buildings
– volume: 108
  start-page: 106
  year: 2015
  end-page: 113
  ident: bib0240
  article-title: Building’s electricity consumption prediction using optimized artificial neural networks and principal component analysis
  publication-title: Energy and Buildings
– year: 2019
  ident: bib0040
  article-title: Modelling and forecasting building energy consumption: A review of data-driven techniques
  publication-title: Sustainable Cities and Society
– year: 2007
  ident: bib0285
  article-title: A review of heterogeneous ensemble methods
– volume: 13
  start-page: 281
  year: 2012
  end-page: 305
  ident: bib0035
  article-title: Random search for hyper-parameter optimization
  publication-title: Journal of Machine Learning Research
– volume: 164
  start-page: 102
  year: 2018
  end-page: 111
  ident: bib0160
  article-title: Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China
  publication-title: Energy Conversion and Management
– volume: 10
  start-page: 1257
  year: 2010
  end-page: 1273
  ident: bib0230
  article-title: A systematic comparison of metamodeling techniques for simulation optimization in decision support systems
  publication-title: Applied Soft Computing
– volume: 4
  start-page: 97
  year: 1997
  end-page: 136
  ident: bib0115
  article-title: Machine learning research: Four current direction
  publication-title: Artificial Intelligence Magzine
– volume: 40
  start-page: 356
  year: 2009
  end-page: 362
  ident: bib0135
  article-title: Prediction of building energy consumption by using artificial neural networks
  publication-title: Advances in Engineering Software
– volume: 29
  start-page: 107
  year: 2017
  end-page: 117
  ident: bib0295
  article-title: Improving sustainable office building operation by using historical data and linear models to predict energy usage
  publication-title: Sustainable Cities and Society
– volume: 58
  start-page: 188
  year: 2012
  end-page: 198
  ident: bib0145
  article-title: Occupants’ window opening behaviour: A literature review of factors influencing occupant behaviour and models
  publication-title: Building and Environment
– volume: 207
  start-page: 728
  year: 2019
  end-page: 742
  ident: bib0245
  article-title: Analysis of the impacts of heating emissions on the environment and human health in North China
  publication-title: Journal of Cleaner Production
– volume: 20
  start-page: 564
  year: 2014
  end-page: 571
  ident: bib0330
  article-title: WSN-based smart sensors and actuator for power management in intelligent buildings
  publication-title: IEEE/ASME Transactions on Mechatronics
– volume: 185
  start-page: 326
  year: 2019
  end-page: 344
  ident: bib0065
  article-title: Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold
  publication-title: Energy and Buildings
– volume: 37
  start-page: 517
  year: 2014
  end-page: 537
  ident: bib0215
  article-title: Review of building energy modeling for control and operation
  publication-title: Renewable and Sustainable Energy Reviews
– volume: 23
  start-page: 1
  year: 2001
  end-page: 13
  ident: bib0195
  article-title: Comparative studies of metamodelling techniques under multiple modelling criteria
  publication-title: Structural and Multidisciplinary Optimization
– volume: 119
  start-page: 121
  year: 2016
  end-page: 129
  ident: bib0325
  article-title: Assessing the potential of random forest method for estimating solar radiation using air pollution index
  publication-title: Energy Conversion and Management
– volume: 10
  start-page: 1
  year: 2009
  end-page: 12
  ident: bib0190
  article-title: A random forest approach to the detection of epistatic interactions in case-control studies
  publication-title: BMC Bioinformatics
– volume: 43
  start-page: 3484
  year: 2011
  end-page: 3490
  ident: bib0210
  article-title: Occupants have little influence on the overall energy consumption in district heated apartment buildings
  publication-title: Energy and Buildings
– volume: 29
  start-page: 107
  year: 2017
  end-page: 117
  ident: bib0300
  article-title: Improving sustainable office building operation by using historical data and linear models to predict energy usage
  publication-title: Sustainable Cities and Society
– volume: 147
  start-page: 77
  year: 2017
  end-page: 89
  ident: bib0010
  article-title: Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption
  publication-title: Energy and Buildings
– year: 2001
  ident: bib0305
  article-title: Learning with kernels: Support vector machines, regularization, optimization, and beyond
– year: 2016
  ident: bib0080
  article-title: XGBoost: A scalable tree boosting system
  publication-title: ACM SIGKDD International Conference on knowledge discovery and data mining
– volume: 128
  year: 2018
  ident: bib0110
  article-title: Effect of input variables on cooling load prediction accuracy of an office building
  publication-title: Applied Thermal Engineering
– volume: 36
  start-page: 27
  year: 2013
  end-page: 46
  ident: bib0125
  article-title: Collinearity: A review of methods to deal with it and a simulation study evaluating their performance
  publication-title: Ecography
– volume: 75
  year: 2016
  ident: bib0345
  article-title: A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models
  publication-title: Renewable and Sustainable Energy Reviews
– volume: 35
  start-page: 816
  year: 2017
  end-page: 829
  ident: bib0290
  article-title: Upscaling energy control from building to districts: Current limitations and future perspectives
  publication-title: Sustainable Cities and Society
– year: 2019
  ident: bib0315
  article-title: Tuning machine learning models for prediction of building energy loads
  publication-title: Sustainable Cities and Society
– volume: 211
  start-page: 89
  year: 2018
  end-page: 103
  ident: bib0260
  article-title: A comparison of six metamodeling techniques applied to building performance simulations
  publication-title: Applied Energy
– volume: 82
  start-page: 437
  year: 2014
  end-page: 446
  ident: bib0090
  article-title: Modeling heating and cooling loads by artificial intelligence for energy-efficient building design
  publication-title: Energy and Buildings
– volume: 127
  start-page: 1
  year: 2014
  end-page: 10
  ident: bib0150
  article-title: Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques
  publication-title: Applied Energy
– volume: 37
  start-page: 517
  year: 2014
  end-page: 537
  ident: bib0235
  article-title: Review of building energy modeling for control and operation
  publication-title: Renewable and Sustainable Energy Reviews
– volume: 82
  start-page: 437
  year: 2014
  end-page: 446
  ident: bib0095
  article-title: Modeling heating and cooling loads by artificial intelligence for energy-efficient building design
  publication-title: Energy and Buildings
– volume: 11
  start-page: 203
  year: 2007
  end-page: 224
  ident: bib0030
  article-title: Support vector regression
  publication-title: Neural Information Processing Letters and Reviews
– volume: 38
  start-page: 1019
  year: 2006
  end-page: 1027
  ident: bib0070
  article-title: Analysis of traffic injury severity: An application of non-parametric classification tree techniques
  publication-title: Accident; Analysis and Prevention
– year: 2015
  ident: bib0085
  article-title: China building energy conservation annual development research report
– volume: 7
  start-page: 381
  year: 2011
  end-page: 388
  ident: bib0275
  article-title: Demand side management: Demand response, intelligent energy systems, and smart loads
  publication-title: IEEE Transactions on Industrial Informatics
– volume: 147
  year: 2017
  ident: bib0015
  article-title: Trees vs Neurons: Comparison between Random Forest and ANN for high-resolution prediction of building energy consumption
  publication-title: Energy and Buildings
– volume: Vol. 2
  year: 1994
  ident: bib0180
  publication-title: Neural networks
– volume: 45
  start-page: 460
  year: 2019
  end-page: 473
  ident: bib0005
  article-title: Nonlinear autoregressive and random forest approaches to forecasting electricity load for utility energy management systems
  publication-title: Sustainable Cities and Society
– volume: 174
  start-page: 293
  year: 2018
  end-page: 308
  ident: bib0370
  article-title: A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis
  publication-title: Energy and Buildings
– volume: 25
  start-page: 33
  year: 2016
  end-page: 38
  ident: bib0365
  article-title: Advances and challenges in building engineering and data mining applications for energy-efficient communities
  publication-title: Sustainable Cities and Society
– year: 2017
  ident: bib0200
  article-title: Lightgbm: A highly efficient gradient boosting decision tree
  publication-title: Advances in neural information processing systems
– volume: 41
  start-page: 219
  year: 2010
  end-page: 241
  ident: bib0320
  article-title: Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions
  publication-title: Structural and Multidisciplinary Optimization
– year: 2000
  ident: bib0100
  article-title: Ensemble methods in machine learning
  publication-title: International workshop on multiple classifier systems
– volume: 41
  start-page: 728
  year: 2018
  end-page: 748
  ident: bib0205
  article-title: Estimation and optimization of heating energy demand of a mountain shelter by soft computing techniques
  publication-title: Sustainable Cities and Society
– volume: 81
  start-page: 1192
  year: 2018
  end-page: 1205
  ident: bib0025
  article-title: A review of data-driven building energy consumption prediction studies
  publication-title: Renewable and Sustainable Energy Reviews
– volume: 37
  start-page: 545
  year: 2005
  end-page: 553
  ident: bib0120
  article-title: Applying support vector machines to predict building energy consumption in tropical region
  publication-title: Energy and Buildings
– volume: 104
  start-page: 991
  year: 1998
  end-page: 1004
  ident: bib0255
  article-title: Understanding the adaptive approach to thermal comfort
  publication-title: ASHRAE Transactions
– volume: 37
  start-page: 517
  year: 2014
  ident: 10.1016/j.scs.2019.101623_bib0235
  article-title: Review of building energy modeling for control and operation
  publication-title: Renewable and Sustainable Energy Reviews
  doi: 10.1016/j.rser.2014.05.056
– volume: 75
  start-page: 796
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0350
  article-title: A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models
  publication-title: Renewable and Sustainable Energy Reviews
  doi: 10.1016/j.rser.2016.10.079
– year: 2015
  ident: 10.1016/j.scs.2019.101623_bib0085
– volume: 35
  start-page: 816
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0290
  article-title: Upscaling energy control from building to districts: Current limitations and future perspectives
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2017.05.012
– volume: 211
  start-page: 89
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0260
  article-title: A comparison of six metamodeling techniques applied to building performance simulations
  publication-title: Applied Energy
  doi: 10.1016/j.apenergy.2017.10.102
– volume: 82
  start-page: 437
  year: 2014
  ident: 10.1016/j.scs.2019.101623_bib0090
  article-title: Modeling heating and cooling loads by artificial intelligence for energy-efficient building design
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2014.07.036
– volume: 128
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0110
  article-title: Effect of input variables on cooling load prediction accuracy of an office building
  publication-title: Applied Thermal Engineering
  doi: 10.1016/j.applthermaleng.2017.09.007
– volume: 41
  start-page: 85
  issue: 41
  year: 2015
  ident: 10.1016/j.scs.2019.101623_bib0335
  article-title: Heating and cooling energy trends and drivers in buildings
  publication-title: Renewable and Sustainable Energy Reviews
  doi: 10.1016/j.rser.2014.08.039
– volume: 45
  start-page: 5
  year: 2001
  ident: 10.1016/j.scs.2019.101623_bib0050
  article-title: Random forest
  publication-title: Machine Learning
  doi: 10.1023/A:1010933404324
– volume: 55
  start-page: 889
  year: 2012
  ident: 10.1016/j.scs.2019.101623_bib0250
  article-title: Existing building retrofits: Methodology and state-of-the-art
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2012.08.018
– year: 2007
  ident: 10.1016/j.scs.2019.101623_bib0285
– volume: 104
  start-page: 991
  year: 1998
  ident: 10.1016/j.scs.2019.101623_bib0255
  article-title: Understanding the adaptive approach to thermal comfort
  publication-title: ASHRAE Transactions
– volume: 154
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0105
  article-title: Research on short-term and ultra-short-term cooling load prediction models for office buildings
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2017.08.077
– year: 2016
  ident: 10.1016/j.scs.2019.101623_bib0075
  article-title: Xgboost: A scalable tree boosting system
  publication-title: Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining
  doi: 10.1145/2939672.2939785
– volume: Vol. 2
  year: 1994
  ident: 10.1016/j.scs.2019.101623_bib0180
– volume: 7
  start-page: 381
  issue: 3
  year: 2011
  ident: 10.1016/j.scs.2019.101623_bib0275
  article-title: Demand side management: Demand response, intelligent energy systems, and smart loads
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2011.2158841
– volume: 152
  start-page: 788
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0020
  article-title: Water source heat pump energy demand prognosticate using disparate data-mining based approaches
  publication-title: Energy
  doi: 10.1016/j.energy.2018.03.169
– volume: 43
  start-page: 2178
  issue: 12
  year: 2008
  ident: 10.1016/j.scs.2019.101623_bib0140
  article-title: Predicting performance of a ground-source heat pump system using fuzzy weighted pre-processing-based ANFIS
  publication-title: Building and Environment
  doi: 10.1016/j.buildenv.2008.01.002
– volume: 147
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0015
  article-title: Trees vs Neurons: Comparison between Random Forest and ANN for high-resolution prediction of building energy consumption
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2017.04.038
– volume: 16
  start-page: 80
  year: 2014
  ident: 10.1016/j.scs.2019.101623_bib0310
  article-title: Hybrid PSO–SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank
  publication-title: Applied Soft Computing
  doi: 10.1016/j.asoc.2013.12.001
– volume: 86
  start-page: 2249
  issue: 10
  year: 2009
  ident: 10.1016/j.scs.2019.101623_bib0225
  article-title: Applying support vector machine to predict hourly cooling load in the building
  publication-title: Applied Energy
  doi: 10.1016/j.apenergy.2008.11.035
– volume: 43
  start-page: 3484
  issue: 12
  year: 2011
  ident: 10.1016/j.scs.2019.101623_bib0210
  article-title: Occupants have little influence on the overall energy consumption in district heated apartment buildings
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2011.09.012
– volume: 42
  start-page: 1637
  issue: 10
  year: 2010
  ident: 10.1016/j.scs.2019.101623_bib0360
  article-title: A decision tree method for building energy demand modeling
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2010.04.006
– volume: 45
  start-page: 460
  year: 2019
  ident: 10.1016/j.scs.2019.101623_bib0005
  article-title: Nonlinear autoregressive and random forest approaches to forecasting electricity load for utility energy management systems
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2018.12.013
– volume: 185
  start-page: 326
  year: 2019
  ident: 10.1016/j.scs.2019.101623_bib0065
  article-title: Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2018.12.032
– year: 2000
  ident: 10.1016/j.scs.2019.101623_bib0100
  article-title: Ensemble methods in machine learning
– volume: 23
  start-page: 1
  issue: 1
  year: 2001
  ident: 10.1016/j.scs.2019.101623_bib0195
  article-title: Comparative studies of metamodelling techniques under multiple modelling criteria
  publication-title: Structural and Multidisciplinary Optimization
  doi: 10.1007/s00158-001-0160-4
– year: 2019
  ident: 10.1016/j.scs.2019.101623_bib0040
  article-title: Modelling and forecasting building energy consumption: A review of data-driven techniques
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2019.101533
– volume: 82
  start-page: 437
  year: 2014
  ident: 10.1016/j.scs.2019.101623_bib0095
  article-title: Modeling heating and cooling loads by artificial intelligence for energy-efficient building design
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2014.07.036
– volume: 29
  start-page: 1189
  issue: 5
  year: 2001
  ident: 10.1016/j.scs.2019.101623_bib0165
  article-title: Greedy function approximation: A gradient boosting machine
  publication-title: Annals of Statistics
  doi: 10.1214/aos/1013203451
– year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0200
  article-title: Lightgbm: A highly efficient gradient boosting decision tree
– volume: 20
  start-page: 564
  issue: 2
  year: 2014
  ident: 10.1016/j.scs.2019.101623_bib0330
  article-title: WSN-based smart sensors and actuator for power management in intelligent buildings
  publication-title: IEEE/ASME Transactions on Mechatronics
  doi: 10.1109/TMECH.2014.2301716
– volume: 29
  start-page: 107
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0300
  article-title: Improving sustainable office building operation by using historical data and linear models to predict energy usage
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2016.12.001
– volume: 81
  start-page: 1192
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0025
  article-title: A review of data-driven building energy consumption prediction studies
  publication-title: Renewable and Sustainable Energy Reviews
  doi: 10.1016/j.rser.2017.04.095
– volume: 4
  start-page: 97
  year: 1997
  ident: 10.1016/j.scs.2019.101623_bib0115
  article-title: Machine learning research: Four current direction
  publication-title: Artificial Intelligence Magzine
– volume: 144
  start-page: 361
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0270
  article-title: A combined multivariate model for wind power prediction
  publication-title: Energy Conversion and Management
  doi: 10.1016/j.enconman.2017.04.077
– volume: 164
  start-page: 102
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0160
  article-title: Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China
  publication-title: Energy Conversion and Management
  doi: 10.1016/j.enconman.2018.02.087
– volume: 11
  start-page: 203
  issue: 10
  year: 2007
  ident: 10.1016/j.scs.2019.101623_bib0030
  article-title: Support vector regression
  publication-title: Neural Information Processing Letters and Reviews
– volume: 40
  start-page: 356
  issue: 5
  year: 2009
  ident: 10.1016/j.scs.2019.101623_bib0135
  article-title: Prediction of building energy consumption by using artificial neural networks
  publication-title: Advances in Engineering Software
  doi: 10.1016/j.advengsoft.2008.05.003
– volume: 119
  start-page: 121
  year: 2016
  ident: 10.1016/j.scs.2019.101623_bib0325
  article-title: Assessing the potential of random forest method for estimating solar radiation using air pollution index
  publication-title: Energy Conversion and Management
  doi: 10.1016/j.enconman.2016.04.051
– volume: 37
  start-page: 545
  issue: 5
  year: 2005
  ident: 10.1016/j.scs.2019.101623_bib0120
  article-title: Applying support vector machines to predict building energy consumption in tropical region
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2004.09.009
– volume: 263
  start-page: 225
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0155
  article-title: Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China
  publication-title: Agricultural and Forest Meteorology
  doi: 10.1016/j.agrformet.2018.08.019
– year: 2019
  ident: 10.1016/j.scs.2019.101623_bib0315
  article-title: Tuning machine learning models for prediction of building energy loads
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2019.101484
– volume: 207
  start-page: 728
  year: 2019
  ident: 10.1016/j.scs.2019.101623_bib0245
  article-title: Analysis of the impacts of heating emissions on the environment and human health in North China
  publication-title: Journal of Cleaner Production
  doi: 10.1016/j.jclepro.2018.10.013
– volume: 25
  start-page: 33
  year: 2016
  ident: 10.1016/j.scs.2019.101623_bib0365
  article-title: Advances and challenges in building engineering and data mining applications for energy-efficient communities
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2015.12.001
– volume: 24
  start-page: 2350
  issue: 6
  year: 1996
  ident: 10.1016/j.scs.2019.101623_bib0045
  article-title: Heuristics of instability and stabilization in model selection
  publication-title: Annals of Statistics
  doi: 10.1214/aos/1032181158
– volume: 37
  start-page: 517
  year: 2014
  ident: 10.1016/j.scs.2019.101623_bib0215
  article-title: Review of building energy modeling for control and operation
  publication-title: Renewable and Sustainable Energy Reviews
  doi: 10.1016/j.rser.2014.05.056
– volume: 10
  start-page: 1257
  issue: 4
  year: 2010
  ident: 10.1016/j.scs.2019.101623_bib0230
  article-title: A systematic comparison of metamodeling techniques for simulation optimization in decision support systems
  publication-title: Applied Soft Computing
  doi: 10.1016/j.asoc.2009.11.034
– volume: 140
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0055
  article-title: Data driven prediction models of energy use of appliances in a low-energy house
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2017.01.083
– start-page: 993
  issue: 10
  year: 1990
  ident: 10.1016/j.scs.2019.101623_bib0170
  article-title: Neural network ensembles
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/34.58871
– volume: 4
  start-page: 339
  issue: 4
  year: 2011
  ident: 10.1016/j.scs.2019.101623_bib0280
  article-title: Coupling of dynamic building simulation with stochastic modelling of occupant behaviour in offices–a review-based integrated methodology
  publication-title: Journal of Building Performance Simulation
  doi: 10.1080/19401493.2010.524711
– volume: 41
  start-page: 219
  issue: 2
  year: 2010
  ident: 10.1016/j.scs.2019.101623_bib0320
  article-title: Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions
  publication-title: Structural and Multidisciplinary Optimization
  doi: 10.1007/s00158-009-0420-2
– volume: 38
  start-page: 1019
  issue: 5
  year: 2006
  ident: 10.1016/j.scs.2019.101623_bib0070
  article-title: Analysis of traffic injury severity: An application of non-parametric classification tree techniques
  publication-title: Accident; Analysis and Prevention
  doi: 10.1016/j.aap.2006.04.009
– year: 2016
  ident: 10.1016/j.scs.2019.101623_bib0080
  article-title: XGBoost: A scalable tree boosting system
– volume: 75
  year: 2016
  ident: 10.1016/j.scs.2019.101623_bib0345
  article-title: A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models
  publication-title: Renewable and Sustainable Energy Reviews
– volume: 171
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0355
  article-title: Random forest based hourly building energy prediction
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2018.04.008
– volume: 41
  start-page: 728
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0205
  article-title: Estimation and optimization of heating energy demand of a mountain shelter by soft computing techniques
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2018.06.008
– volume: 111
  start-page: 184
  year: 2016
  ident: 10.1016/j.scs.2019.101623_bib0060
  article-title: Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2015.11.045
– year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0185
  article-title: Visual analytics in deep learning: An interrogative survey for the next frontiers
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– volume: 36
  start-page: 27
  issue: 1
  year: 2013
  ident: 10.1016/j.scs.2019.101623_bib0125
  article-title: Collinearity: A review of methods to deal with it and a simulation study evaluating their performance
  publication-title: Ecography
  doi: 10.1111/j.1600-0587.2012.07348.x
– volume: 147
  start-page: 77
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0010
  article-title: Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2017.04.038
– volume: 108
  start-page: 106
  year: 2015
  ident: 10.1016/j.scs.2019.101623_bib0240
  article-title: Building’s electricity consumption prediction using optimized artificial neural networks and principal component analysis
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2015.09.002
– volume: 10
  start-page: 1
  issue: Suppl 1
  year: 2009
  ident: 10.1016/j.scs.2019.101623_bib0190
  article-title: A random forest approach to the detection of epistatic interactions in case-control studies
  publication-title: BMC Bioinformatics
– volume: 174
  start-page: 293
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0370
  article-title: A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis
  publication-title: Energy and Buildings
  doi: 10.1016/j.enbuild.2018.06.050
– volume: 50
  start-page: 90
  issue: 1
  year: 2009
  ident: 10.1016/j.scs.2019.101623_bib0220
  article-title: Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks
  publication-title: Energy Conversion and Management
  doi: 10.1016/j.enconman.2008.08.033
– volume: 12
  start-page: 163
  year: 2012
  ident: 10.1016/j.scs.2019.101623_bib0340
  article-title: Making machine learning models interpretable
  publication-title: ESANN
– volume: 58
  start-page: 188
  year: 2012
  ident: 10.1016/j.scs.2019.101623_bib0145
  article-title: Occupants’ window opening behaviour: A literature review of factors influencing occupant behaviour and models
  publication-title: Building and Environment
  doi: 10.1016/j.buildenv.2012.07.009
– volume: 29
  start-page: 107
  year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0295
  article-title: Improving sustainable office building operation by using historical data and linear models to predict energy usage
  publication-title: Sustainable Cities and Society
  doi: 10.1016/j.scs.2016.12.001
– year: 2001
  ident: 10.1016/j.scs.2019.101623_bib0305
– year: 2015
  ident: 10.1016/j.scs.2019.101623_bib0175
– volume: 127
  start-page: 1
  issue: 6
  year: 2014
  ident: 10.1016/j.scs.2019.101623_bib0150
  article-title: Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques
  publication-title: Applied Energy
  doi: 10.1016/j.apenergy.2014.04.016
– volume: 13
  start-page: 281
  issue: February
  year: 2012
  ident: 10.1016/j.scs.2019.101623_bib0035
  article-title: Random search for hyper-parameter optimization
  publication-title: Journal of Machine Learning Research
– year: 2017
  ident: 10.1016/j.scs.2019.101623_bib0130
– volume: 211
  start-page: 89
  year: 2018
  ident: 10.1016/j.scs.2019.101623_bib0265
  article-title: A comparison of six metamodeling techniques applied to building performance simulations
  publication-title: Applied Energy
  doi: 10.1016/j.apenergy.2017.10.102
SSID ssj0000561945
Score 2.4766128
Snippet •Compared five models with respect to interpretability, accuracy, robustness, and efficiency.•Studied the influence of the training dataset on the prediction...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 101623
SubjectTerms Accuracy
Building energy prediction
Efficiency
Extreme gradient boosting
Interpretability
Robustness
Title Multi-criteria comprehensive study on predictive algorithm of hourly heating energy consumption for residential buildings
URI https://dx.doi.org/10.1016/j.scs.2019.101623
Volume 49
WOSCitedRecordID wos000475860700036&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 2210-6715
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000561945
  issn: 2210-6707
  databaseCode: AIEXJ
  dateStart: 20110201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELYo9NAeqj5V6EM-9FRk5ARvbB9RBaI9oFJA2ltkO97uom12tVkq-PeMH_EaWlBbqZcosuw48nwejcffzCD0oeDUwE7TRKhSEtiJiigpFKGWUmUazilrfLEJfnQkhkP5NV4XdL6cAG9bcXkp5_9V1NAGwnahs38h7vRRaIB3EDo8Qezw_CPB-5BaAsrAZWFWnjO-sOPIU-9CDmnHy3I3NJ43pKbfZ9B7_MMbjjDF9MrZj54PbUNooPGBmvPES4Qz-sRH-IKAdSys3eV27kkWl2V80tbt3kMfE48EL37QNN8yYtCF98eOQVlNUptnHBxPlA_uyv0ULjRK5H6KFECzYiuBjivhxEkqHgrf7ti8LUR59ko65DX9Rd8H18P5Tmdc6vVC-pYQwHwrjfaJ-6ybCSxWMCtL_gBtlHwgQZlv7H3eH35Jnjl3ppK-unX6u_463BMDb831e4MmM1JOn6In8XSB9wIqnqE12z5Hj7Ocky_Q1U184Bv4wB4feNbiFT5wwgeejXDAB474wAEfOMMHBnzgDB844eMlOjvYP_10SGL9DWJKyZdEFQ0TUoliYBgduVR9XAimHLVTalaVuhBNowvFJKPcmMpo2OHGVhoO6YIqu_sKrbez1r5GeCQ43-VcG6lhpFUSOrOK8cYOzADGbCLaL2JtYnJ6VyNlWvcsxPMa1r12616Hdd9EH9OQecjMcl9n1kumjqZlMBlrQNLdw7b-bdgb9Gi1A96i9eXiwr5DD83P5aRbvI94uwZL-KOh
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multi-criteria+comprehensive+study+on+predictive+algorithm+of+hourly+heating+energy+consumption+for+residential+buildings&rft.jtitle=Sustainable+cities+and+society&rft.au=Wang%2C+Ran&rft.au=Lu%2C+Shilei&rft.au=Li%2C+Qiaoping&rft.date=2019-08-01&rft.pub=Elsevier+Ltd&rft.issn=2210-6707&rft.eissn=2210-6715&rft.volume=49&rft_id=info:doi/10.1016%2Fj.scs.2019.101623&rft.externalDocID=S2210670719309527
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2210-6707&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2210-6707&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2210-6707&client=summon