Meta-learning strategy based on user preferences and a machine recommendation system for real-time cooling load and COP forecasting

•A new meta-learning recommendation system is proposed.•The new system concerned two-stage (subjective and objective) user preferences.•Multi-objective decision making algorithms (MODMA) are used in option optimization.•A new “walking slide method” aimed at some extremely special cases is proposed.•...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied energy Jg. 270; S. 115144
Hauptverfasser: Li, Wenqiang, Gong, Guangcai, Fan, Houhua, Peng, Pei, Chun, Liang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 15.07.2020
Schlagworte:
ISSN:0306-2619, 1872-9118
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •A new meta-learning recommendation system is proposed.•The new system concerned two-stage (subjective and objective) user preferences.•Multi-objective decision making algorithms (MODMA) are used in option optimization.•A new “walking slide method” aimed at some extremely special cases is proposed.•The new system is validated on real buildings, and its generalizability is proved. Building data forecasting plays an increasingly important role in building energy savings. However, the one-fits-all model cannot satisfy all the requirements of multiple application scenarios and user preferences. Motivated by the need to bridge the research gap between different user preferences (application scenarios) and energy prediction model recommendation systems, this paper proposes a novel meta-learning strategy based on an artificial neural network recommendation system. This strategy is employed for real-time cooling loads, coefficients of performance prediction and optimal prediction model recommendations. The data set is composed of 40 cases from five factory buildings. After the predictions and recommendations are obtained for all cases, the two-stage user preferences are considered based on multi-objective decision-making algorithms. Then, a new model termed the “walking slide method”, is proposed to predict some special cases. This study shows that the seasonal autoregressive integrated moving average model and random forest model achieve the best prediction accuracy and the minimum computation cost separately for most cases, while the long short-term memory is the best model when considering the two criteria. The variances between the different cases lead to a lower cross-validation score (approximately 65%), but a higher success rate (over 99%) for the recommendation performance. In addition, in the more complex application scenarios, a lower prediction accuracy and recommendation success rate will be obtained. In most cases, the use of a prediction combined with a monitoring system is the best choice. Last, the reliability of the results is verified by application studies. This work provides a scientific basis for energy prediction applications based on user preferences.
AbstractList •A new meta-learning recommendation system is proposed.•The new system concerned two-stage (subjective and objective) user preferences.•Multi-objective decision making algorithms (MODMA) are used in option optimization.•A new “walking slide method” aimed at some extremely special cases is proposed.•The new system is validated on real buildings, and its generalizability is proved. Building data forecasting plays an increasingly important role in building energy savings. However, the one-fits-all model cannot satisfy all the requirements of multiple application scenarios and user preferences. Motivated by the need to bridge the research gap between different user preferences (application scenarios) and energy prediction model recommendation systems, this paper proposes a novel meta-learning strategy based on an artificial neural network recommendation system. This strategy is employed for real-time cooling loads, coefficients of performance prediction and optimal prediction model recommendations. The data set is composed of 40 cases from five factory buildings. After the predictions and recommendations are obtained for all cases, the two-stage user preferences are considered based on multi-objective decision-making algorithms. Then, a new model termed the “walking slide method”, is proposed to predict some special cases. This study shows that the seasonal autoregressive integrated moving average model and random forest model achieve the best prediction accuracy and the minimum computation cost separately for most cases, while the long short-term memory is the best model when considering the two criteria. The variances between the different cases lead to a lower cross-validation score (approximately 65%), but a higher success rate (over 99%) for the recommendation performance. In addition, in the more complex application scenarios, a lower prediction accuracy and recommendation success rate will be obtained. In most cases, the use of a prediction combined with a monitoring system is the best choice. Last, the reliability of the results is verified by application studies. This work provides a scientific basis for energy prediction applications based on user preferences.
Building data forecasting plays an increasingly important role in building energy savings. However, the one-fits-all model cannot satisfy all the requirements of multiple application scenarios and user preferences. Motivated by the need to bridge the research gap between different user preferences (application scenarios) and energy prediction model recommendation systems, this paper proposes a novel meta-learning strategy based on an artificial neural network recommendation system. This strategy is employed for real-time cooling loads, coefficients of performance prediction and optimal prediction model recommendations. The data set is composed of 40 cases from five factory buildings. After the predictions and recommendations are obtained for all cases, the two-stage user preferences are considered based on multi-objective decision-making algorithms. Then, a new model termed the “walking slide method”, is proposed to predict some special cases. This study shows that the seasonal autoregressive integrated moving average model and random forest model achieve the best prediction accuracy and the minimum computation cost separately for most cases, while the long short-term memory is the best model when considering the two criteria. The variances between the different cases lead to a lower cross-validation score (approximately 65%), but a higher success rate (over 99%) for the recommendation performance. In addition, in the more complex application scenarios, a lower prediction accuracy and recommendation success rate will be obtained. In most cases, the use of a prediction combined with a monitoring system is the best choice. Last, the reliability of the results is verified by application studies. This work provides a scientific basis for energy prediction applications based on user preferences.
ArticleNumber 115144
Author Li, Wenqiang
Fan, Houhua
Chun, Liang
Gong, Guangcai
Peng, Pei
Author_xml – sequence: 1
  givenname: Wenqiang
  surname: Li
  fullname: Li, Wenqiang
  organization: School of Civil Engineering, Hunan Univ., Changsha 410082, China
– sequence: 2
  givenname: Guangcai
  surname: Gong
  fullname: Gong, Guangcai
  email: gcgong@hnu.edu.cn
  organization: School of Civil Engineering, Hunan Univ., Changsha 410082, China
– sequence: 3
  givenname: Houhua
  surname: Fan
  fullname: Fan, Houhua
  organization: Hunan Tianyu Energy Technology Co., Ltd., Changsha 410082, China
– sequence: 4
  givenname: Pei
  surname: Peng
  fullname: Peng, Pei
  organization: School of Civil Engineering, Hunan Univ., Changsha 410082, China
– sequence: 5
  givenname: Liang
  surname: Chun
  fullname: Chun, Liang
  organization: School of Civil Engineering, Hunan Univ., Changsha 410082, China
BookMark eNqFkE1rGzEQhkVJoU7av1B0zGXdGe2HLcghwaQfkJAe2rPQSrOuzK7kSHLA5_7xauPmkktOAzPv88I85-zMB0-MfUZYImD3ZbfUe_IUt8elAFGW2GLTvGMLXK9EJRHXZ2wBNXSV6FB-YOcp7QBAoIAF-3tPWVcj6eid3_KUo860PfJeJ7I8eH5IFPk-0kCRvKHEtbdc80mbP84Tj2TCNJG3OruSTseUaeJDiOWixyq7ibgJYZzLx6DtM755-DlHyOiUy-Ejez_oMdGn__OC_f56-2vzvbp7-PZjc3NXmbppc9VDX5No1xJlX6OQYsC-QZK9AKBe2tVqkLITph9kZ6FuEIyQuu2GAXVLluoLdnnq3cfweKCU1eSSoXHUnsIhKdE0sAJRY12iV6eoiSGl8r0yLj-_WAS5USGo2b3aqRf3anavTu4L3r3C99FNOh7fBq9PIBUPT46iSsbN3q0rurKywb1V8Q_XcKbT
CitedBy_id crossref_primary_10_1016_j_enbuild_2021_111435
crossref_primary_10_1016_j_energy_2021_122809
crossref_primary_10_1016_j_energy_2025_135840
crossref_primary_10_1016_j_enbuild_2023_113513
crossref_primary_10_1016_j_buildenv_2024_111547
crossref_primary_10_1007_s11042_023_17948_5
crossref_primary_10_1016_j_energy_2022_123111
crossref_primary_10_1016_j_apenergy_2021_116991
crossref_primary_10_1016_j_jclepro_2023_139524
crossref_primary_10_1016_j_energy_2023_127518
crossref_primary_10_1016_j_apenergy_2020_116223
crossref_primary_10_1016_j_energy_2020_119208
crossref_primary_10_1016_j_jobe_2024_109657
crossref_primary_10_1109_ACCESS_2022_3161497
crossref_primary_10_1016_j_ijrefrig_2024_07_019
crossref_primary_10_3390_en16124721
crossref_primary_10_1016_j_enbuild_2023_113527
crossref_primary_10_1007_s12273_024_1136_3
crossref_primary_10_1016_j_enbuild_2024_115167
crossref_primary_10_1016_j_ifacol_2022_08_058
crossref_primary_10_1016_j_enbuild_2022_112278
crossref_primary_10_1016_j_enbuild_2022_112498
crossref_primary_10_1016_j_procs_2022_07_092
crossref_primary_10_1016_j_jobe_2022_105028
crossref_primary_10_1016_j_inffus_2024_102559
crossref_primary_10_1016_j_apenergy_2021_117694
Cites_doi 10.1016/j.enbuild.2019.06.016
10.1016/j.enbuild.2015.01.047
10.1023/A:1019956318069
10.1016/j.apenergy.2019.113759
10.1016/j.renene.2017.10.017
10.1016/j.energy.2017.05.126
10.1016/j.neucom.2005.02.006
10.1198/jasa.2003.s308
10.1016/j.apenergy.2017.03.034
10.1016/j.apenergy.2018.12.042
10.1016/j.energy.2018.01.180
10.1016/S0304-4076(00)00030-0
10.1016/j.cageo.2014.10.004
10.1016/S1364-0321(01)00006-5
10.1016/j.apenergy.2014.02.057
10.1016/j.apenergy.2019.01.055
10.1080/01621459.1970.10481180
10.1016/j.rser.2015.04.065
10.1016/j.apenergy.2014.07.104
10.5772/16004
10.1057/9781137291264_6
10.1007/978-3-319-53480-0_48
10.1016/j.enbuild.2004.01.035
10.1016/j.enbuild.2013.01.008
10.1016/j.buildenv.2018.11.017
10.1016/j.enbuild.2015.12.050
10.1016/j.apenergy.2016.03.112
10.1016/j.buildenv.2018.09.024
10.2139/ssrn.2417910
10.1016/j.enbuild.2017.03.010
10.1016/j.neucom.2009.09.020
10.1016/j.egypro.2012.01.229
10.1016/j.apenergy.2019.114396
10.1162/neco.1997.9.8.1735
10.1016/S0378-7796(01)00138-9
10.1016/j.enconman.2017.09.005
10.1016/j.enbuild.2016.05.084
10.1016/0167-9473(93)E0056-A
10.1109/UPEC.2007.4469121
10.1177/0278364904045481
10.1016/j.enbuild.2016.12.002
10.1016/j.buildenv.2006.06.025
10.1016/j.rser.2014.08.039
10.1016/j.apm.2013.08.016
10.1007/BFb0026683
10.1016/j.apenergy.2018.12.004
10.1109/TPWRS.2005.846054
10.1016/j.radonc.2014.11.015
10.1016/j.buildenv.2018.10.062
10.1016/j.energy.2015.11.037
10.1080/00031305.1990.10475704
10.1007/978-1-4612-0593-7
10.1016/j.apenergy.2017.03.064
10.1016/j.apenergy.2018.10.061
ContentType Journal Article
Copyright 2020 Elsevier Ltd
Copyright_xml – notice: 2020 Elsevier Ltd
DBID AAYXX
CITATION
7S9
L.6
DOI 10.1016/j.apenergy.2020.115144
DatabaseName CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList
AGRICOLA
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Environmental Sciences
EISSN 1872-9118
ExternalDocumentID 10_1016_j_apenergy_2020_115144
S0306261920306565
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
23M
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAHCO
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARJD
AAXUO
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHIDL
AHJVU
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BELTK
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
JARJE
JJJVA
KOM
LY6
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SSR
SST
SSZ
T5K
TN5
~02
~G-
9DU
AAHBH
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABEFU
ABFNM
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
G-2
HVGLF
HZ~
R2-
SAC
SEW
WUQ
ZY4
~HD
7S9
L.6
ID FETCH-LOGICAL-c345t-b0b3e258919b31292f1b41e9b200eb9d77f9962cbf96d03410c29a56ff1a5ede3
ISICitedReferencesCount 30
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000540433000021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0306-2619
IngestDate Sun Sep 28 10:05:21 EDT 2025
Sat Nov 29 07:18:46 EST 2025
Tue Nov 18 22:29:47 EST 2025
Fri Feb 23 02:47:23 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Artificial neural network (ANN)
User preferences
Cooling load prediction
Meta-learning
Recommendation system
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c345t-b0b3e258919b31292f1b41e9b200eb9d77f9962cbf96d03410c29a56ff1a5ede3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 2440702313
PQPubID 24069
ParticipantIDs proquest_miscellaneous_2440702313
crossref_citationtrail_10_1016_j_apenergy_2020_115144
crossref_primary_10_1016_j_apenergy_2020_115144
elsevier_sciencedirect_doi_10_1016_j_apenergy_2020_115144
PublicationCentury 2000
PublicationDate 2020-07-15
PublicationDateYYYYMMDD 2020-07-15
PublicationDate_xml – month: 07
  year: 2020
  text: 2020-07-15
  day: 15
PublicationDecade 2020
PublicationTitle Applied energy
PublicationYear 2020
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Kotzur, Markewitz, Robinius, Stolten (b0070) 2018; 117
Lavalle, Branicky (b0305) 2003; 23
Jolliffe (b0255) 2002; 87
Lauritzen SL. The EM algorithm for graphical association models with missing data; 1995.
Nie, Liu, Liu, Yong (b0065) 2012; 16
Fan, Xiao, Zhao (b0080) 2017; 195
He, Zhou, Feng, Liu, Yang (b0140) 2019
Paliwal KK, Basu A. A speech enhancement method based on Kalman filtering. In: IEEE international conference on acoustics, speech, & signal processing; 1987.
Feng, Xiaozhong (b0130) 2014; 134
Wate, Iglesias, Coors, Robinson (b0150) 2020; 258
Racine (b0260) 2004; 99
Chinese standard. GB/T 50785-2012 Evaluation standard for indoor thermal environment in civil building. Beijing: China Architecture and Building Press; 2012.
Wang, Lee, Yuen, Feng (b0165) 2019; 198
May R, Dandy G, Maier H. Review of input variable selection methods for artificial neural networks. Artificial Neural Networks-Methodological Advances and Biomedical Applications; 2011:19–44.
Zhoua, Zheng (b0155) 2020; 262
Fu (b0115) 2018; 148
Conejo, Plazas, Espinola, Molina (b0055) 2005; 20
Cai, Pipattanasomporn, Rahman (b0280) 2019; 236
ürge-Vorsatz, Cabeza, Serrano, Barreneche, Petrichenko (b0010) 2015; 41
Chirarattananon Surapong, Taveekun Juntakan. An OTTV-based energy estimation model for commercial buildings in Thailand. Energy Build 2004;36:680–9.
Niu (b0240) 1999
Chan PML, Hu YF, Sheriff RE. Implementation of fuzzy multiple objective decision making algorithm in a heterogeneous mobile environment. In: Wireless Communications & networking conference; 2002.
Cosma, Simha (b0275) 2019; 148
Picard, Berk (b0285) 1990; 44
Joachims T. Text categorization with support vector machines: learning with many relevant features. In: Proc conference on machine learning; 1998.
Xu, Chen, Wang, Guo, Yuan (b0085) 2019; 148
Heidelberg SB. Meta-learning in computational intelligence; 2011.
Kalogirou (b0265) 2001; 5
Clark, Hussein, Tsang, Thomas, Nisbet (b0290) 2014; 113
Raza, Khosravi (b0110) 2015; 50
Naji, Keivani, Shamshirband, Alengaram, Jumaat, Mansor (b0095) 2016; 97
Box G. Box and Jenkins: Time Series Analysis, Forecasting and Control; 2013.
Fan, Wang, Gang, Li (b0090) 2019; 236
He, Zhou, Mo, Feng, Liu, He (b0145) 2020; 262
Markovic, Grintal, Woelki, Frisch, van Treeck (b0180) 2018; 145
Resnikoff HL, Jr ROW. Wavelet analysis; 1998.
Amral N, Ozveren CS, King D. Short term load forecasting using Multiple Linear Regression. In: International universities power engineering conference; 2007.
Hochreiter, Schmidhuber (b0330) 1997
Carranza, Laborte (b0295) 2015; 74
Deb, Eang, Yang, Santamouris (b0125) 2016; 121
Cui, Wu, Hu, Weir, Li (b0205) 2016; 172
He, Qin, Wang, Wang, Wang (b0160) 2019; 233
Dahanayake, Chow (b0015) 2017; 138
Chen, Peng, Chu, Li, Wu, Ni (b0100) 2017; 195
Box, Pierce (b0050) 1970; 65
Avci M. Demand response-enabled model predictive HVAC load control in buildings using real-time electricity pricing. Dissertations & Theses – Gradworks; 2013.
Kokogiannakis (b0025) 2008; 43
Baky (b0235) 2014; 38
Pankratz A. Forecasting with univariate Box-Jenkins models: concepts and cases; 2008.
Vilalta R, Drissi Y. A perspective view and survey of meta-learning; 2002.
Wang, Zhang, Peng, Wang, Liu, Jiang (b0005) 2017; 151
Jain, Smith, Culligan, Taylor (b0105) 2014; 123
Li, Liu (b0030) 2017; 142
Krichene E, Masmoudi Y, Alimi AM, Abraham A, Chabchoub H. Forecasting using Elman recurrent neural network; 2016.
Zhang, Dong (b0060) 2001; 59
Timmerman ME. Principal component analysis, 2nd ed. In: Jolliffe IT, editor. J Am Stat Assoc, vol. 98; 2003. p. 1082–3.
Tarsitano, Amerise (b0215) 2017; 133
Louangrath PI. Correlation coefficient according to data classification. Social Science Electronic Publishing; 2014.
He, Zhou, Feng, Liu, Yang (b0135) 2019; 237
Lemke, Gabrys (b0200) 2010; 73
Ludermir T. Using machine learning techniques to combine forecasting methods. In: Australian joint conference on advances in artificial intelligence; 2004.
Chen, Bo, Dong (b0325) 2006; 69
Platon, Dehkordi, Martel (b0120) 2015; 92
Alibabaei, Fung, Raahemifar (b0020) 2016; 128
Nguyen HT, Nguyen D, Le LB. Home energy management with generic thermal dynamics and user temperature preference. In: IEEE international conference on smart grid communications; 2013.
Neyshabur, Salakhutdinov, Srebro (b0270) 2015
Chen (10.1016/j.apenergy.2020.115144_b0100) 2017; 195
Chen (10.1016/j.apenergy.2020.115144_b0325) 2006; 69
He (10.1016/j.apenergy.2020.115144_b0135) 2019; 237
Markovic (10.1016/j.apenergy.2020.115144_b0180) 2018; 145
Lemke (10.1016/j.apenergy.2020.115144_b0200) 2010; 73
Fan (10.1016/j.apenergy.2020.115144_b0090) 2019; 236
He (10.1016/j.apenergy.2020.115144_b0160) 2019; 233
Li (10.1016/j.apenergy.2020.115144_b0030) 2017; 142
Niu (10.1016/j.apenergy.2020.115144_b0240) 1999
10.1016/j.apenergy.2020.115144_b0185
10.1016/j.apenergy.2020.115144_b0220
10.1016/j.apenergy.2020.115144_b0300
10.1016/j.apenergy.2020.115144_b0225
Wang (10.1016/j.apenergy.2020.115144_b0005) 2017; 151
Jain (10.1016/j.apenergy.2020.115144_b0105) 2014; 123
Lavalle (10.1016/j.apenergy.2020.115144_b0305) 2003; 23
Kotzur (10.1016/j.apenergy.2020.115144_b0070) 2018; 117
10.1016/j.apenergy.2020.115144_b0170
10.1016/j.apenergy.2020.115144_b0250
He (10.1016/j.apenergy.2020.115144_b0145) 2020; 262
10.1016/j.apenergy.2020.115144_b0175
10.1016/j.apenergy.2020.115144_b0210
Jolliffe (10.1016/j.apenergy.2020.115144_b0255) 2002; 87
Wate (10.1016/j.apenergy.2020.115144_b0150) 2020; 258
Racine (10.1016/j.apenergy.2020.115144_b0260) 2004; 99
ürge-Vorsatz (10.1016/j.apenergy.2020.115144_b0010) 2015; 41
10.1016/j.apenergy.2020.115144_b0315
He (10.1016/j.apenergy.2020.115144_b0140) 2019
Xu (10.1016/j.apenergy.2020.115144_b0085) 2019; 148
Neyshabur (10.1016/j.apenergy.2020.115144_b0270) 2015
Naji (10.1016/j.apenergy.2020.115144_b0095) 2016; 97
Alibabaei (10.1016/j.apenergy.2020.115144_b0020) 2016; 128
Box (10.1016/j.apenergy.2020.115144_b0050) 1970; 65
Deb (10.1016/j.apenergy.2020.115144_b0125) 2016; 121
Kokogiannakis (10.1016/j.apenergy.2020.115144_b0025) 2008; 43
Cosma (10.1016/j.apenergy.2020.115144_b0275) 2019; 148
Raza (10.1016/j.apenergy.2020.115144_b0110) 2015; 50
Wang (10.1016/j.apenergy.2020.115144_b0165) 2019; 198
10.1016/j.apenergy.2020.115144_b0040
Cui (10.1016/j.apenergy.2020.115144_b0205) 2016; 172
10.1016/j.apenergy.2020.115144_b0045
10.1016/j.apenergy.2020.115144_b0320
10.1016/j.apenergy.2020.115144_b0245
Conejo (10.1016/j.apenergy.2020.115144_b0055) 2005; 20
Nie (10.1016/j.apenergy.2020.115144_b0065) 2012; 16
Platon (10.1016/j.apenergy.2020.115144_b0120) 2015; 92
Fu (10.1016/j.apenergy.2020.115144_b0115) 2018; 148
Zhoua (10.1016/j.apenergy.2020.115144_b0155) 2020; 262
Picard (10.1016/j.apenergy.2020.115144_b0285) 1990; 44
Fan (10.1016/j.apenergy.2020.115144_b0080) 2017; 195
Kalogirou (10.1016/j.apenergy.2020.115144_b0265) 2001; 5
Hochreiter (10.1016/j.apenergy.2020.115144_b0330) 1997
Tarsitano (10.1016/j.apenergy.2020.115144_b0215) 2017; 133
Feng (10.1016/j.apenergy.2020.115144_b0130) 2014; 134
Clark (10.1016/j.apenergy.2020.115144_b0290) 2014; 113
10.1016/j.apenergy.2020.115144_b0190
Baky (10.1016/j.apenergy.2020.115144_b0235) 2014; 38
Zhang (10.1016/j.apenergy.2020.115144_b0060) 2001; 59
10.1016/j.apenergy.2020.115144_b0195
Carranza (10.1016/j.apenergy.2020.115144_b0295) 2015; 74
Dahanayake (10.1016/j.apenergy.2020.115144_b0015) 2017; 138
10.1016/j.apenergy.2020.115144_b0230
10.1016/j.apenergy.2020.115144_b0075
Cai (10.1016/j.apenergy.2020.115144_b0280) 2019; 236
10.1016/j.apenergy.2020.115144_b0035
10.1016/j.apenergy.2020.115144_b0310
References_xml – volume: 38
  start-page: 1417
  year: 2014
  end-page: 1433
  ident: b0235
  article-title: Interactive TOPSIS algorithms for solving multi-level non-linear multi-objective decision-making problems
  publication-title: Appl Math Model
– reference: Ludermir T. Using machine learning techniques to combine forecasting methods. In: Australian joint conference on advances in artificial intelligence; 2004.
– reference: Pankratz A. Forecasting with univariate Box-Jenkins models: concepts and cases; 2008.
– volume: 142
  start-page: 56
  year: 2017
  end-page: 61
  ident: b0030
  article-title: Improved particle filter based soft sensing of room cooling load
  publication-title: Energy Build
– volume: 87
  start-page: 513
  year: 2002
  ident: b0255
  article-title: Principal component analysis
  publication-title: J Marketing Res
– volume: 99
  start-page: 39
  year: 2004
  end-page: 61
  ident: b0260
  article-title: Consistent cross-validatory model-selection for dependent data: hv -block cross-validation
  publication-title: J Economet
– reference: Vilalta R, Drissi Y. A perspective view and survey of meta-learning; 2002.
– volume: 44
  start-page: 140
  year: 1990
  end-page: 147
  ident: b0285
  article-title: Data splitting
  publication-title: Am Stat
– volume: 233
  start-page: 565
  year: 2019
  end-page: 575
  ident: b0160
  article-title: Electricity consumption probability density forecasting method based on LASSO-Quantile Regression Neural Network
  publication-title: Appl Energy
– volume: 123
  start-page: 168
  year: 2014
  end-page: 178
  ident: b0105
  article-title: Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy
  publication-title: Appl Energy
– volume: 121
  start-page: 284
  year: 2016
  end-page: 297
  ident: b0125
  article-title: Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks
  publication-title: Energy Build
– volume: 43
  start-page: 601
  year: 2008
  end-page: 609
  ident: b0025
  article-title: History and development of validation with the ESP-r simulation program
  publication-title: Build Enviro
– year: 2015
  ident: b0270
  article-title: Path-SGD: path-normalized optimization in deep neural Networks
  publication-title: International conference on neural information processing systems
– reference: Chinese standard. GB/T 50785-2012 Evaluation standard for indoor thermal environment in civil building. Beijing: China Architecture and Building Press; 2012.
– reference: Box G. Box and Jenkins: Time Series Analysis, Forecasting and Control; 2013.
– volume: 236
  start-page: 700
  year: 2019
  end-page: 710
  ident: b0090
  article-title: Assessment of deep recurrent neural network-based strategies for short-term building energy predictions
  publication-title: Appl Energy
– reference: May R, Dandy G, Maier H. Review of input variable selection methods for artificial neural networks. Artificial Neural Networks-Methodological Advances and Biomedical Applications; 2011:19–44.
– start-page: 89
  year: 1999
  end-page: 92
  ident: b0240
  article-title: A study on wavelet neural network prediction model of time series
  publication-title: Syst Eng-Theory Practice
– volume: 262
  year: 2020
  ident: b0145
  article-title: Day-ahead short-term load probability density forecasting method with a decomposition-based quantile regression forest
  publication-title: Appl Energy
– reference: Resnikoff HL, Jr ROW. Wavelet analysis; 1998.
– volume: 50
  start-page: 1352
  year: 2015
  end-page: 1372
  ident: b0110
  article-title: A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings
  publication-title: Renew Sust Energy Rev
– volume: 198
  start-page: 261
  year: 2019
  end-page: 274
  ident: b0165
  article-title: Cooling load forecasting-based predictive optimisation for chiller plants
  publication-title: Energy Build
– reference: Joachims T. Text categorization with support vector machines: learning with many relevant features. In: Proc conference on machine learning; 1998.
– volume: 5
  start-page: 373
  year: 2001
  end-page: 401
  ident: b0265
  article-title: Artificial neural networks in renewable energy systems applications: a review
  publication-title: Renew Sust Energy Rev
– volume: 74
  start-page: 60
  year: 2015
  end-page: 70
  ident: b0295
  article-title: Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines)
  publication-title: Comput Geosci
– reference: Lauritzen SL. The EM algorithm for graphical association models with missing data; 1995.
– volume: 151
  start-page: 524
  year: 2017
  end-page: 537
  ident: b0005
  article-title: GPNBI-inspired MOSFA for Pareto operation optimization of integrated energy system
  publication-title: Energy Convers Manag
– volume: 138
  start-page: 47
  year: 2017
  end-page: 59
  ident: b0015
  article-title: Studying the potential of energy saving through vertical greenery systems: Using EnergyPlus simulation program
  publication-title: Energy Build
– reference: Louangrath PI. Correlation coefficient according to data classification. Social Science Electronic Publishing; 2014.
– reference: Avci M. Demand response-enabled model predictive HVAC load control in buildings using real-time electricity pricing. Dissertations & Theses – Gradworks; 2013.
– volume: 148
  start-page: 128
  year: 2019
  end-page: 135
  ident: b0085
  article-title: Improving prediction performance for indoor temperature in public buildings based on a novel deep learning method
  publication-title: Build Enviro
– volume: 195
  start-page: 659
  year: 2017
  end-page: 670
  ident: b0100
  article-title: Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings
  publication-title: Appl Energy
– volume: 133
  start-page: 108
  year: 2017
  end-page: 114
  ident: b0215
  article-title: Short-term load forecasting using a two-stage sarimax model
  publication-title: Energy
– reference: Chan PML, Hu YF, Sheriff RE. Implementation of fuzzy multiple objective decision making algorithm in a heterogeneous mobile environment. In: Wireless Communications & networking conference; 2002.
– volume: 236
  start-page: 1078
  year: 2019
  end-page: 1088
  ident: b0280
  article-title: Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques
  publication-title: Appl Energy
– reference: Chirarattananon Surapong, Taveekun Juntakan. An OTTV-based energy estimation model for commercial buildings in Thailand. Energy Build 2004;36:680–9.
– volume: 41
  start-page: 85
  year: 2015
  end-page: 98
  ident: b0010
  article-title: Heating and cooling energy trends and drivers in buildings
  publication-title: Renew Sust Energy Rev
– volume: 65
  start-page: 1509
  year: 1970
  end-page: 1526
  ident: b0050
  article-title: Distribution of residual autocorrelations in autoregressive-integrated moving average time series models
  publication-title: Publ Am Stat Assoc
– reference: Amral N, Ozveren CS, King D. Short term load forecasting using Multiple Linear Regression. In: International universities power engineering conference; 2007.
– reference: Paliwal KK, Basu A. A speech enhancement method based on Kalman filtering. In: IEEE international conference on acoustics, speech, & signal processing; 1987.
– volume: 145
  start-page: 319
  year: 2018
  end-page: 329
  ident: b0180
  article-title: Window opening model using deep learning methods
  publication-title: Build Enviro
– volume: 97
  start-page: 506
  year: 2016
  end-page: 516
  ident: b0095
  article-title: Estimating building energy consumption using extreme learning machine method
  publication-title: Energy
– volume: 69
  start-page: 449
  year: 2006
  end-page: 465
  ident: b0325
  article-title: Time-series prediction using a local linear wavelet neural network
  publication-title: Neurocomputing
– volume: 117
  start-page: 474
  year: 2018
  end-page: 487
  ident: b0070
  article-title: Impact of different time series aggregation methods on optimal energy system design
  publication-title: Renew Energ
– volume: 113
  year: 2014
  ident: b0290
  article-title: A multi-institutional dosimetry audit of rotational intensity-modulated radiotherapy
  publication-title: Radiother Oncol
– volume: 172
  start-page: 251
  year: 2016
  end-page: 263
  ident: b0205
  article-title: Short-term building energy model recommendation system: a meta-learning approach
  publication-title: Appl Energy
– volume: 59
  start-page: 121
  year: 2001
  end-page: 129
  ident: b0060
  article-title: An adaptive neural-wavelet model for short term load forecasting
  publication-title: Electr Pow Syst Res
– volume: 148
  start-page: 372
  year: 2019
  end-page: 383
  ident: b0275
  article-title: Machine learning method for real-time non-invasive prediction of individual thermal preference in transient conditions
  publication-title: Build Enviro
– volume: 20
  start-page: 1035
  year: 2005
  end-page: 1042
  ident: b0055
  article-title: Day-ahead electricity price forecasting using the wavelet transform and ARIMA models
  publication-title: IEEE T Power Syst
– volume: 195
  start-page: 222
  year: 2017
  end-page: 233
  ident: b0080
  article-title: A short-term building cooling load prediction method using deep learning algorithms
  publication-title: Appl Energy
– year: 2019
  ident: b0140
  article-title: A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm
  publication-title: Appl Energy
– volume: 16
  start-page: 1455
  year: 2012
  end-page: 1460
  ident: b0065
  article-title: Hybrid of ARIMA and SVMs for short-term load forecasting
  publication-title: Energy Procedia
– volume: 92
  start-page: 10
  year: 2015
  end-page: 18
  ident: b0120
  article-title: Hourly prediction of a building's electricity consumption using case-based reasoning, artificial neural networks and principal component analysis
  publication-title: Energy Build
– volume: 262
  year: 2020
  ident: b0155
  article-title: Machine-learning based hybrid demand-side controller for high-rise office buildings with high energy flexibilities
  publication-title: Appl Energy
– volume: 258
  year: 2020
  ident: b0150
  article-title: Framework for emulation and uncertainty quantification of a stochastic building performance simulator
  publication-title: Appl Energy
– volume: 148
  year: 2018
  ident: b0115
  article-title: Deep belief network based ensemble approach for cooling load forecasting of air-conditioning system
  publication-title: Energy
– reference: Krichene E, Masmoudi Y, Alimi AM, Abraham A, Chabchoub H. Forecasting using Elman recurrent neural network; 2016.
– reference: Timmerman ME. Principal component analysis, 2nd ed. In: Jolliffe IT, editor. J Am Stat Assoc, vol. 98; 2003. p. 1082–3.
– start-page: 1735
  year: 1997
  end-page: 1780
  ident: b0330
  article-title: Long short-term memory
  publication-title: Neural Comput
– volume: 134
  start-page: 102
  year: 2014
  end-page: 113
  ident: b0130
  article-title: A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network
  publication-title: Appl Energy
– reference: Heidelberg SB. Meta-learning in computational intelligence; 2011.
– reference: Nguyen HT, Nguyen D, Le LB. Home energy management with generic thermal dynamics and user temperature preference. In: IEEE international conference on smart grid communications; 2013.
– volume: 237
  start-page: 103
  year: 2019
  end-page: 116
  ident: b0135
  article-title: A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm
  publication-title: Appl Energy
– volume: 23
  start-page: 673
  year: 2003
  end-page: 692
  ident: b0305
  article-title: On the relationship between classical grid search and probabilistic roadmaps
  publication-title: Int J Robot Res
– volume: 128
  start-page: 81
  year: 2016
  end-page: 98
  ident: b0020
  article-title: Development of Matlab-TRNSYS co-simulator for applying predictive strategy planning models on residential house HVAC system
  publication-title: Energy Build
– volume: 73
  start-page: 2006
  year: 2010
  end-page: 2016
  ident: b0200
  article-title: Meta-learning for time series forecasting and forecast combination
  publication-title: Neurocomputing
– volume: 198
  start-page: 261
  year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0165
  article-title: Cooling load forecasting-based predictive optimisation for chiller plants
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2019.06.016
– volume: 92
  start-page: 10
  year: 2015
  ident: 10.1016/j.apenergy.2020.115144_b0120
  article-title: Hourly prediction of a building's electricity consumption using case-based reasoning, artificial neural networks and principal component analysis
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2015.01.047
– ident: 10.1016/j.apenergy.2020.115144_b0195
  doi: 10.1023/A:1019956318069
– volume: 258
  year: 2020
  ident: 10.1016/j.apenergy.2020.115144_b0150
  article-title: Framework for emulation and uncertainty quantification of a stochastic building performance simulator
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2019.113759
– volume: 117
  start-page: 474
  year: 2018
  ident: 10.1016/j.apenergy.2020.115144_b0070
  article-title: Impact of different time series aggregation methods on optimal energy system design
  publication-title: Renew Energ
  doi: 10.1016/j.renene.2017.10.017
– volume: 133
  start-page: 108
  year: 2017
  ident: 10.1016/j.apenergy.2020.115144_b0215
  article-title: Short-term load forecasting using a two-stage sarimax model
  publication-title: Energy
  doi: 10.1016/j.energy.2017.05.126
– volume: 69
  start-page: 449
  year: 2006
  ident: 10.1016/j.apenergy.2020.115144_b0325
  article-title: Time-series prediction using a local linear wavelet neural network
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2005.02.006
– start-page: 89
  year: 1999
  ident: 10.1016/j.apenergy.2020.115144_b0240
  article-title: A study on wavelet neural network prediction model of time series
  publication-title: Syst Eng-Theory Practice
– ident: 10.1016/j.apenergy.2020.115144_b0175
  doi: 10.1198/jasa.2003.s308
– volume: 195
  start-page: 659
  year: 2017
  ident: 10.1016/j.apenergy.2020.115144_b0100
  article-title: Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2017.03.034
– volume: 236
  start-page: 1078
  year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0280
  article-title: Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2018.12.042
– volume: 148
  year: 2018
  ident: 10.1016/j.apenergy.2020.115144_b0115
  article-title: Deep belief network based ensemble approach for cooling load forecasting of air-conditioning system
  publication-title: Energy
  doi: 10.1016/j.energy.2018.01.180
– volume: 99
  start-page: 39
  year: 2004
  ident: 10.1016/j.apenergy.2020.115144_b0260
  article-title: Consistent cross-validatory model-selection for dependent data: hv -block cross-validation
  publication-title: J Economet
  doi: 10.1016/S0304-4076(00)00030-0
– ident: 10.1016/j.apenergy.2020.115144_b0185
– year: 2015
  ident: 10.1016/j.apenergy.2020.115144_b0270
  article-title: Path-SGD: path-normalized optimization in deep neural Networks
– volume: 74
  start-page: 60
  year: 2015
  ident: 10.1016/j.apenergy.2020.115144_b0295
  article-title: Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines)
  publication-title: Comput Geosci
  doi: 10.1016/j.cageo.2014.10.004
– volume: 5
  start-page: 373
  year: 2001
  ident: 10.1016/j.apenergy.2020.115144_b0265
  article-title: Artificial neural networks in renewable energy systems applications: a review
  publication-title: Renew Sust Energy Rev
  doi: 10.1016/S1364-0321(01)00006-5
– volume: 123
  start-page: 168
  year: 2014
  ident: 10.1016/j.apenergy.2020.115144_b0105
  article-title: Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2014.02.057
– year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0140
  article-title: A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2019.01.055
– volume: 65
  start-page: 1509
  year: 1970
  ident: 10.1016/j.apenergy.2020.115144_b0050
  article-title: Distribution of residual autocorrelations in autoregressive-integrated moving average time series models
  publication-title: Publ Am Stat Assoc
  doi: 10.1080/01621459.1970.10481180
– volume: 50
  start-page: 1352
  year: 2015
  ident: 10.1016/j.apenergy.2020.115144_b0110
  article-title: A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings
  publication-title: Renew Sust Energy Rev
  doi: 10.1016/j.rser.2015.04.065
– volume: 134
  start-page: 102
  year: 2014
  ident: 10.1016/j.apenergy.2020.115144_b0130
  article-title: A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2014.07.104
– ident: 10.1016/j.apenergy.2020.115144_b0310
– ident: 10.1016/j.apenergy.2020.115144_b0170
  doi: 10.5772/16004
– ident: 10.1016/j.apenergy.2020.115144_b0075
  doi: 10.1057/9781137291264_6
– ident: 10.1016/j.apenergy.2020.115144_b0245
  doi: 10.1007/978-3-319-53480-0_48
– ident: 10.1016/j.apenergy.2020.115144_b0210
  doi: 10.1016/j.enbuild.2004.01.035
– ident: 10.1016/j.apenergy.2020.115144_b0220
  doi: 10.1016/j.enbuild.2013.01.008
– volume: 148
  start-page: 372
  year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0275
  article-title: Machine learning method for real-time non-invasive prediction of individual thermal preference in transient conditions
  publication-title: Build Enviro
  doi: 10.1016/j.buildenv.2018.11.017
– volume: 121
  start-page: 284
  year: 2016
  ident: 10.1016/j.apenergy.2020.115144_b0125
  article-title: Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2015.12.050
– volume: 172
  start-page: 251
  year: 2016
  ident: 10.1016/j.apenergy.2020.115144_b0205
  article-title: Short-term building energy model recommendation system: a meta-learning approach
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2016.03.112
– volume: 145
  start-page: 319
  year: 2018
  ident: 10.1016/j.apenergy.2020.115144_b0180
  article-title: Window opening model using deep learning methods
  publication-title: Build Enviro
  doi: 10.1016/j.buildenv.2018.09.024
– volume: 262
  year: 2020
  ident: 10.1016/j.apenergy.2020.115144_b0155
  article-title: Machine-learning based hybrid demand-side controller for high-rise office buildings with high energy flexibilities
  publication-title: Appl Energy
– ident: 10.1016/j.apenergy.2020.115144_b0250
  doi: 10.2139/ssrn.2417910
– volume: 142
  start-page: 56
  year: 2017
  ident: 10.1016/j.apenergy.2020.115144_b0030
  article-title: Improved particle filter based soft sensing of room cooling load
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2017.03.010
– volume: 73
  start-page: 2006
  year: 2010
  ident: 10.1016/j.apenergy.2020.115144_b0200
  article-title: Meta-learning for time series forecasting and forecast combination
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2009.09.020
– volume: 16
  start-page: 1455
  year: 2012
  ident: 10.1016/j.apenergy.2020.115144_b0065
  article-title: Hybrid of ARIMA and SVMs for short-term load forecasting
  publication-title: Energy Procedia
  doi: 10.1016/j.egypro.2012.01.229
– volume: 262
  year: 2020
  ident: 10.1016/j.apenergy.2020.115144_b0145
  article-title: Day-ahead short-term load probability density forecasting method with a decomposition-based quantile regression forest
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2019.114396
– start-page: 1735
  year: 1997
  ident: 10.1016/j.apenergy.2020.115144_b0330
  article-title: Long short-term memory
  publication-title: Neural Comput
  doi: 10.1162/neco.1997.9.8.1735
– volume: 59
  start-page: 121
  year: 2001
  ident: 10.1016/j.apenergy.2020.115144_b0060
  article-title: An adaptive neural-wavelet model for short term load forecasting
  publication-title: Electr Pow Syst Res
  doi: 10.1016/S0378-7796(01)00138-9
– volume: 151
  start-page: 524
  year: 2017
  ident: 10.1016/j.apenergy.2020.115144_b0005
  article-title: GPNBI-inspired MOSFA for Pareto operation optimization of integrated energy system
  publication-title: Energy Convers Manag
  doi: 10.1016/j.enconman.2017.09.005
– volume: 128
  start-page: 81
  year: 2016
  ident: 10.1016/j.apenergy.2020.115144_b0020
  article-title: Development of Matlab-TRNSYS co-simulator for applying predictive strategy planning models on residential house HVAC system
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2016.05.084
– ident: 10.1016/j.apenergy.2020.115144_b0300
  doi: 10.1016/0167-9473(93)E0056-A
– ident: 10.1016/j.apenergy.2020.115144_b0035
  doi: 10.1109/UPEC.2007.4469121
– volume: 23
  start-page: 673
  year: 2003
  ident: 10.1016/j.apenergy.2020.115144_b0305
  article-title: On the relationship between classical grid search and probabilistic roadmaps
  publication-title: Int J Robot Res
  doi: 10.1177/0278364904045481
– ident: 10.1016/j.apenergy.2020.115144_b0045
– volume: 138
  start-page: 47
  year: 2017
  ident: 10.1016/j.apenergy.2020.115144_b0015
  article-title: Studying the potential of energy saving through vertical greenery systems: Using EnergyPlus simulation program
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2016.12.002
– volume: 43
  start-page: 601
  year: 2008
  ident: 10.1016/j.apenergy.2020.115144_b0025
  article-title: History and development of validation with the ESP-r simulation program
  publication-title: Build Enviro
  doi: 10.1016/j.buildenv.2006.06.025
– volume: 41
  start-page: 85
  year: 2015
  ident: 10.1016/j.apenergy.2020.115144_b0010
  article-title: Heating and cooling energy trends and drivers in buildings
  publication-title: Renew Sust Energy Rev
  doi: 10.1016/j.rser.2014.08.039
– volume: 38
  start-page: 1417
  year: 2014
  ident: 10.1016/j.apenergy.2020.115144_b0235
  article-title: Interactive TOPSIS algorithms for solving multi-level non-linear multi-objective decision-making problems
  publication-title: Appl Math Model
  doi: 10.1016/j.apm.2013.08.016
– ident: 10.1016/j.apenergy.2020.115144_b0315
  doi: 10.1007/BFb0026683
– volume: 236
  start-page: 700
  year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0090
  article-title: Assessment of deep recurrent neural network-based strategies for short-term building energy predictions
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2018.12.004
– ident: 10.1016/j.apenergy.2020.115144_b0225
– ident: 10.1016/j.apenergy.2020.115144_b0190
– volume: 87
  start-page: 513
  year: 2002
  ident: 10.1016/j.apenergy.2020.115144_b0255
  article-title: Principal component analysis
  publication-title: J Marketing Res
– volume: 20
  start-page: 1035
  year: 2005
  ident: 10.1016/j.apenergy.2020.115144_b0055
  article-title: Day-ahead electricity price forecasting using the wavelet transform and ARIMA models
  publication-title: IEEE T Power Syst
  doi: 10.1109/TPWRS.2005.846054
– volume: 113
  year: 2014
  ident: 10.1016/j.apenergy.2020.115144_b0290
  article-title: A multi-institutional dosimetry audit of rotational intensity-modulated radiotherapy
  publication-title: Radiother Oncol
  doi: 10.1016/j.radonc.2014.11.015
– volume: 237
  start-page: 103
  year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0135
  article-title: A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2019.01.055
– volume: 148
  start-page: 128
  year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0085
  article-title: Improving prediction performance for indoor temperature in public buildings based on a novel deep learning method
  publication-title: Build Enviro
  doi: 10.1016/j.buildenv.2018.10.062
– volume: 97
  start-page: 506
  year: 2016
  ident: 10.1016/j.apenergy.2020.115144_b0095
  article-title: Estimating building energy consumption using extreme learning machine method
  publication-title: Energy
  doi: 10.1016/j.energy.2015.11.037
– ident: 10.1016/j.apenergy.2020.115144_b0230
– volume: 44
  start-page: 140
  year: 1990
  ident: 10.1016/j.apenergy.2020.115144_b0285
  article-title: Data splitting
  publication-title: Am Stat
  doi: 10.1080/00031305.1990.10475704
– ident: 10.1016/j.apenergy.2020.115144_b0320
  doi: 10.1007/978-1-4612-0593-7
– ident: 10.1016/j.apenergy.2020.115144_b0040
– volume: 195
  start-page: 222
  year: 2017
  ident: 10.1016/j.apenergy.2020.115144_b0080
  article-title: A short-term building cooling load prediction method using deep learning algorithms
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2017.03.064
– volume: 233
  start-page: 565
  year: 2019
  ident: 10.1016/j.apenergy.2020.115144_b0160
  article-title: Electricity consumption probability density forecasting method based on LASSO-Quantile Regression Neural Network
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2018.10.061
SSID ssj0002120
Score 2.4548025
Snippet •A new meta-learning recommendation system is proposed.•The new system concerned two-stage (subjective and objective) user preferences.•Multi-objective...
Building data forecasting plays an increasingly important role in building energy savings. However, the one-fits-all model cannot satisfy all the requirements...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 115144
SubjectTerms algorithms
Artificial neural network (ANN)
buildings
cooling
Cooling load prediction
data collection
energy
energy conservation
Meta-learning
monitoring
neural networks
prediction
Recommendation system
User preferences
Title Meta-learning strategy based on user preferences and a machine recommendation system for real-time cooling load and COP forecasting
URI https://dx.doi.org/10.1016/j.apenergy.2020.115144
https://www.proquest.com/docview/2440702313
Volume 270
WOSCitedRecordID wos000540433000021&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: 1872-9118
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002120
  issn: 0306-2619
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLZKxwM8IBhMbFxkJN4ql-bipn6cpqKBYPRhiL5FjuOMTplTlnTanvkR_F2Ob2k6LmMPqFJURbHr9Hw5_uyc8x2EXvO4gA8NyDgG-hZLkRMgRzFhGWcTKWheWEt_SI6OJvM5m_V6P3wuzEWZKDW5vGTL_2pqOAfG1qmztzB32ymcgO9gdDiC2eH4T4b_KBtOSr_jUVv12auBnq5y_WpAb0toaQCX6Gc1mvngzERV6iIqMKgz6WotOaVnE4wI9LIkuhb9QFSVyWIvK26UXgcHn2b6Eil43fi50EvbOporTZJhG_9jggi-SPUN4HnSBgG5-GDArToRfNGCy-7SHlarryu-dub24plcdLcuYJ2qBSlpx8PBeoXoJVzXHYe2kIhzqEBYAysQ-Yuvt9sOp0O-tHcw1D8xXDfYFNe-Num1oYg-yu009f2kup_U9nMHbYUJZZM-2tp_N52_byf50Cl--jvoJJ__fkR_4j3XGIChNccP0QO3HsH7FkePUE-qbXS_o1K5jXam62RIuNTNBvVj9H0DathDDRuo4UphDTXcgRoGrGCOHdTwJtSwhRoGHOEWathBDWuomeYANdyB2hP0-e30-OCQuKIeREQxbUg2yiIZ6lqWLIuAbIYFuIZAsgyeYZmxPEkKWIKHIivYOB8BxxqJkHE6LoqAU5nLaAf1VaXkU4R5FLE84AlPhH7dnzE6ioskiLKIMl5Qvouo_8tT4RTvdeGVMv270XfRm7bd0mq-3NiCeYumjrlaRpoCWG9s-8pDIAXXrt_XcSWrVZ0C84YJGRZg0d6tR_QM3Vs_cc9RvzlfyRforrhoFvX5S4fmnxQczkI
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=Meta-learning+strategy+based+on+user+preferences+and+a+machine+recommendation+system+for+real-time+cooling+load+and+COP+forecasting&rft.jtitle=Applied+energy&rft.au=Li%2C+Wenqiang&rft.au=Gong%2C+Guangcai&rft.au=Fan%2C+Houhua&rft.au=Peng%2C+Pei&rft.date=2020-07-15&rft.issn=0306-2619&rft.volume=270&rft.spage=115144&rft_id=info:doi/10.1016%2Fj.apenergy.2020.115144&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_apenergy_2020_115144
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-2619&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-2619&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-2619&client=summon