A multi-step predictive deep reinforcement learning algorithm for HVAC control systems in smart buildings

The development of the building energy management systems (BEMS) enable users to intelligently control Heating, Ventilation, Air-conditioning and Cooling (HVAC) systems based on digital information. In order to reduce the power consumption cost of the HVAC system while ensuring user satisfaction, a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy (Oxford) Jg. 259; S. 124857
Hauptverfasser: Liu, Xiangfei, Ren, Mifeng, Yang, Zhile, Yan, Gaowei, Guo, Yuanjun, Cheng, Lan, Wu, Chengke
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 15.11.2022
Schlagworte:
ISSN:0360-5442
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The development of the building energy management systems (BEMS) enable users to intelligently control Heating, Ventilation, Air-conditioning and Cooling (HVAC) systems based on digital information. In order to reduce the power consumption cost of the HVAC system while ensuring user satisfaction, a novel HVAC control system for building system based on a multi-step predictive deep reinforcement learning (MSP-DRL) algorithm is proposed in this paper. In the proposed method, the outdoor ambient temperature is predicted first by a featured deep learning method named GC-LSTM, where the Long Short-term Memory (LSTM) is enhanced by the generalized correntropy (GC) loss function to deal with the non-Gaussian characteristics of the collected outdoor temperature. In addition, the proposed temperature prediction model is combined with a reinforcement learning algorithm named Deep Deterministic Policy Gradient (DDPG) aiming to flexibly adjust the output power of the HVAC system under the dynamic changing of electricity prices. Finally, comprehensive simulation based on real world data is delivered. Numerical results show that the GC-LSTM algorithm is more accurate than other counterparts prediction algorithms, and the proposed HVAC control system based on the multi-step prediction deep reinforcement learning algorithm is effective and could save over 12% cost compared to other approaches, where the user comfort is maintained simultaneously. •A multi-step predictive deep reinforcement learning algorithm is proposed.•A GC-LSTM algorithm is adopted in multi-step outdoor temperature prediction.•A model-free DDPG algorithm is adopted to manage HVAC system for building system.•The proposed method performs well in the HVAC system.
AbstractList The development of the building energy management systems (BEMS) enable users to intelligently control Heating, Ventilation, Air-conditioning and Cooling (HVAC) systems based on digital information. In order to reduce the power consumption cost of the HVAC system while ensuring user satisfaction, a novel HVAC control system for building system based on a multi-step predictive deep reinforcement learning (MSP-DRL) algorithm is proposed in this paper. In the proposed method, the outdoor ambient temperature is predicted first by a featured deep learning method named GC-LSTM, where the Long Short-term Memory (LSTM) is enhanced by the generalized correntropy (GC) loss function to deal with the non-Gaussian characteristics of the collected outdoor temperature. In addition, the proposed temperature prediction model is combined with a reinforcement learning algorithm named Deep Deterministic Policy Gradient (DDPG) aiming to flexibly adjust the output power of the HVAC system under the dynamic changing of electricity prices. Finally, comprehensive simulation based on real world data is delivered. Numerical results show that the GC-LSTM algorithm is more accurate than other counterparts prediction algorithms, and the proposed HVAC control system based on the multi-step prediction deep reinforcement learning algorithm is effective and could save over 12% cost compared to other approaches, where the user comfort is maintained simultaneously.
The development of the building energy management systems (BEMS) enable users to intelligently control Heating, Ventilation, Air-conditioning and Cooling (HVAC) systems based on digital information. In order to reduce the power consumption cost of the HVAC system while ensuring user satisfaction, a novel HVAC control system for building system based on a multi-step predictive deep reinforcement learning (MSP-DRL) algorithm is proposed in this paper. In the proposed method, the outdoor ambient temperature is predicted first by a featured deep learning method named GC-LSTM, where the Long Short-term Memory (LSTM) is enhanced by the generalized correntropy (GC) loss function to deal with the non-Gaussian characteristics of the collected outdoor temperature. In addition, the proposed temperature prediction model is combined with a reinforcement learning algorithm named Deep Deterministic Policy Gradient (DDPG) aiming to flexibly adjust the output power of the HVAC system under the dynamic changing of electricity prices. Finally, comprehensive simulation based on real world data is delivered. Numerical results show that the GC-LSTM algorithm is more accurate than other counterparts prediction algorithms, and the proposed HVAC control system based on the multi-step prediction deep reinforcement learning algorithm is effective and could save over 12% cost compared to other approaches, where the user comfort is maintained simultaneously. •A multi-step predictive deep reinforcement learning algorithm is proposed.•A GC-LSTM algorithm is adopted in multi-step outdoor temperature prediction.•A model-free DDPG algorithm is adopted to manage HVAC system for building system.•The proposed method performs well in the HVAC system.
ArticleNumber 124857
Author Guo, Yuanjun
Cheng, Lan
Yang, Zhile
Ren, Mifeng
Yan, Gaowei
Liu, Xiangfei
Wu, Chengke
Author_xml – sequence: 1
  givenname: Xiangfei
  surname: Liu
  fullname: Liu, Xiangfei
  email: xf.liu1@siat.ac.cn
  organization: Taiyuan University of Technology, Taiyuan, Shanxi, 030024, China
– sequence: 2
  givenname: Mifeng
  surname: Ren
  fullname: Ren, Mifeng
  email: renmifeng@126.com
  organization: Taiyuan University of Technology, Taiyuan, Shanxi, 030024, China
– sequence: 3
  givenname: Zhile
  orcidid: 0000-0001-8580-534X
  surname: Yang
  fullname: Yang, Zhile
  email: zyang07@qub.ac.uk
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, 518055, China
– sequence: 4
  givenname: Gaowei
  orcidid: 0000-0001-9714-0971
  surname: Yan
  fullname: Yan, Gaowei
  email: yangaowei@tyut.edu.cn
  organization: Taiyuan University of Technology, Taiyuan, Shanxi, 030024, China
– sequence: 5
  givenname: Yuanjun
  surname: Guo
  fullname: Guo, Yuanjun
  email: yj.guo@siat.ac.cn
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, 518055, China
– sequence: 6
  givenname: Lan
  surname: Cheng
  fullname: Cheng, Lan
  email: taolan_1983@126.com
  organization: Taiyuan University of Technology, Taiyuan, Shanxi, 030024, China
– sequence: 7
  givenname: Chengke
  surname: Wu
  fullname: Wu, Chengke
  email: chengke.wu@postgrad.curtin.edu.au
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, 518055, China
BookMark eNqFkLFu2zAQhjk4QG03b9CBYxY5JCVKVIcChtEmBQJ0abMSNHVyzqBIl6QN-O1LQ5k6tNPhcP_3A_etyMIHD4R84mzDGW8fjxvwEA_XjWBCbLholOwWZMnqllWyacQHskrpyBiTqu-XBLd0OruMVcpwoqcIA9qMF6ADlD0C-jFECxP4TB2Y6NEfqHGHEDG_TbQc6fPrdkdt8DkGR9O1FE2JoqdpMjHT_RndUKD0kdyNxiW4f59r8uvb15-75-rlx9P33falsnXd50p2e2Y7M0iopRGcKSN7MzaSta3iQ8vaphNKMssHJUbFa6iFgmbsGbAa2rKuycPce4rh9xlS1hMmC84ZD-GctOi4El3XKVWin-eojSGlCKO2mE3G2y8GneZM35zqo56d6ptTPTstcPMXfIpYXr7-D_syY1AcXBCiThbB2yI-gs16CPjvgj_hGZfz
CitedBy_id crossref_primary_10_1016_j_csite_2025_106874
crossref_primary_10_3390_app14031113
crossref_primary_10_1016_j_energy_2024_131460
crossref_primary_10_1016_j_engappai_2023_105995
crossref_primary_10_1016_j_jobe_2025_112936
crossref_primary_10_1016_j_jobe_2024_110013
crossref_primary_10_1016_j_buildenv_2025_113045
crossref_primary_10_1016_j_seta_2023_103271
crossref_primary_10_1016_j_rser_2025_115817
crossref_primary_10_1016_j_enbuild_2023_113436
crossref_primary_10_1016_j_enbuild_2024_114844
crossref_primary_10_1016_j_est_2025_115850
crossref_primary_10_1016_j_buildenv_2023_110766
crossref_primary_10_1016_j_energy_2025_138517
crossref_primary_10_37394_232015_2025_21_57
crossref_primary_10_1016_j_apenergy_2025_125339
crossref_primary_10_1016_j_enbuild_2025_115851
crossref_primary_10_1080_00038628_2025_2488522
crossref_primary_10_1016_j_enbuild_2025_115970
crossref_primary_10_3390_buildings15071008
crossref_primary_10_1016_j_energy_2023_126787
crossref_primary_10_1016_j_apenergy_2023_121996
crossref_primary_10_1016_j_buildenv_2023_110030
crossref_primary_10_1016_j_egyai_2025_100603
crossref_primary_10_1016_j_energy_2025_137130
crossref_primary_10_1016_j_energy_2024_132740
crossref_primary_10_1016_j_jobe_2024_109354
crossref_primary_10_1016_j_energy_2024_134089
crossref_primary_10_1016_j_energy_2024_132209
crossref_primary_10_1016_j_rineng_2024_103765
crossref_primary_10_1016_j_rser_2025_115387
crossref_primary_10_1038_s41598_025_99816_w
crossref_primary_10_1016_j_energy_2024_130505
crossref_primary_10_3390_buildings13081938
crossref_primary_10_3390_electronics14153122
crossref_primary_10_1016_j_energy_2025_137082
crossref_primary_10_1016_j_ecmx_2025_100901
crossref_primary_10_1016_j_enbuild_2025_116219
crossref_primary_10_1016_j_enbuild_2025_116439
crossref_primary_10_3390_en17174277
crossref_primary_10_1007_s11367_024_02390_y
crossref_primary_10_3390_systems11030136
crossref_primary_10_1016_j_enbuild_2024_115241
crossref_primary_10_1016_j_apenergy_2023_120936
crossref_primary_10_1016_j_enbuild_2025_116053
crossref_primary_10_1016_j_jobe_2024_111080
crossref_primary_10_3390_s25175265
Cites_doi 10.1007/s12517-020-06330-6
10.1016/j.epsr.2020.106959
10.1016/j.energy.2020.117052
10.1016/j.energy.2022.123437
10.3390/en11071900
10.1016/j.enconman.2014.12.025
10.1109/TSG.2012.2190114
10.1016/j.energy.2021.121035
10.1016/j.ijforecast.2020.03.001
10.1109/TPWRS.2009.2023259
10.1016/j.energy.2021.121568
10.1109/TSP.2016.2539127
10.1016/j.enconman.2019.111924
10.1109/3477.809023
10.1016/j.energy.2004.10.004
10.1109/COMST.2014.2341586
10.1016/j.energy.2021.122441
10.1109/TSG.2016.2529579
10.1109/TGRS.2019.2907932
10.17775/CSEEJPES.2018.00520
10.1016/0305-0548(91)90013-H
10.4028/www.scientific.net/AMR.383-390.4768
10.3182/20120403-3-DE-3010.00085
10.1016/j.enconman.2019.112078
10.3390/en11071852
10.1109/TSG.2017.2753802
10.1016/j.energy.2016.02.001
10.1016/j.energy.2021.121657
10.1016/j.buildenv.2019.106535
10.1016/j.energy.2020.117728
10.1109/ACCESS.2019.2955957
10.1016/j.energy.2022.123108
10.1109/TII.2018.2881543
10.1109/LGRS.2017.2733548
10.1109/JPROC.2021.3060483
10.1016/j.energy.2021.120741
10.1109/JIOT.2019.2957289
10.1109/ACCESS.2015.2507781
10.1016/j.energy.2021.122286
10.1016/j.energy.2021.121768
ContentType Journal Article
Copyright 2022
Copyright_xml – notice: 2022
DBID AAYXX
CITATION
7S9
L.6
DOI 10.1016/j.energy.2022.124857
DatabaseName CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList AGRICOLA

DeliveryMethod fulltext_linktorsrc
Discipline Economics
Environmental Sciences
ExternalDocumentID 10_1016_j_energy_2022_124857
S0360544222017601
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1RT
1~.
1~5
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAHBH
AAHCO
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AARJD
AATTM
AAXKI
AAXUO
ABJNI
ABMAC
ACDAQ
ACGFS
ACIWK
ACRLP
ADBBV
ADEZE
AEBSH
AEIPS
AEKER
AENEX
AFRAH
AFTJW
AGHFR
AGUBO
AGYEJ
AHIDL
AIEXJ
AIKHN
AITUG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AXJTR
BELTK
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
JARJE
KOM
LY6
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SSH
SSR
SSZ
T5K
TN5
XPP
ZMT
~02
~G-
29G
6TJ
9DU
AAQXK
AAYWO
AAYXX
ABDPE
ABFNM
ABWVN
ABXDB
ACLOT
ACRPL
ACVFH
ADCNI
ADMUD
ADNMO
ADXHL
AEUPX
AFJKZ
AFPUW
AGQPQ
AHHHB
AIGII
AIIUN
AKBMS
AKYEP
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EFLBG
EJD
FEDTE
FGOYB
G-2
HVGLF
HZ~
R2-
SAC
SEW
WUQ
~HD
7S9
L.6
ID FETCH-LOGICAL-c339t-57b0c7ad5e35a2108a59af4506681d606472850c1d82f813e328e4f90e03e63e3
ISICitedReferencesCount 51
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000848270400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0360-5442
IngestDate Wed Oct 01 13:42:03 EDT 2025
Tue Nov 18 20:56:35 EST 2025
Sat Nov 29 07:22:57 EST 2025
Sun Apr 06 06:54:08 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Deep reinforcement learning
Multi-step prediction
HVAC system
Generalized correntropy
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c339t-57b0c7ad5e35a2108a59af4506681d606472850c1d82f813e328e4f90e03e63e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-8580-534X
0000-0001-9714-0971
PQID 2718277788
PQPubID 24069
ParticipantIDs proquest_miscellaneous_2718277788
crossref_citationtrail_10_1016_j_energy_2022_124857
crossref_primary_10_1016_j_energy_2022_124857
elsevier_sciencedirect_doi_10_1016_j_energy_2022_124857
PublicationCentury 2000
PublicationDate 2022-11-15
PublicationDateYYYYMMDD 2022-11-15
PublicationDate_xml – month: 11
  year: 2022
  text: 2022-11-15
  day: 15
PublicationDecade 2020
PublicationTitle Energy (Oxford)
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Almahdi, Tariq, Kevin (bib46) 2018
Yu, Xie, Xie, Zou, Zhang, Sun, Zhang, Zhang, Jiang (bib7) 2020; 7
Liu, Qi, Ren, Cheng (bib43) 2020
Yuan, Liu, Fang (bib24) 2016; 100
Wang, Jv (bib26) 2020; 95
Lee, Chung, Tsai, Chang (bib32) 1999; 29
Bouznad, Guastaldi, Zirulia, Brancale, Barbagli, Bengusmia (bib27) 2020; 13
Zhang, Zhang (bib18) 2011; 383–390
Saha, Santara, Mitra, Chakraborty, Nanjundiah (bib39) 2021; 37
Dupont, Carvalho, Jucá, Neto (bib45) 2019; 200
Tokic (bib52) 2010
Chen, Wang, Zuo, Zhang, Jia, Liu, Yang (bib33) 2022; 239
Zhou, Zhu, Luo (bib16) 2022; 247
Chen, Xing, Zhao, Zheng, Príncipe (bib42) 2016; 64
Toub, Reddy, Razmara, Shahbakhti, Robinett, Aniba (bib10) 2019; 199
Lillicrap, Hunt, Pritzel, Heess, Erez, Tassa, Silver, Wierstra (bib50) 2015
Jing, Duan, Liu (bib28) 2018; 11
Kotevska, Kurte, Munk, Johnston, Mckee, Perumalla, Zandi (bib19) 2020; 126
Lu, Lü, Leng, Zhang (bib3) 2020; 195
Al Haj Hassan, Pelov, Nuaymi (bib2) 2015; 3
Ciavarella, Joo, Silvestri (bib44) 2016; 7
Kong, Dong, Jia, Hill, Xu, Zhang (bib51) 2019; 10
Sun, Ma, Zhao, Tian, Yan, Chen (bib37) 2019; 15
Su, Kirschen (bib6) 2009; 24
Du, Li, Munk, Kurte, Kotevska, Amasyali, Zandi (bib22) 2021; 192
Ren, Zhao, Luo, Ma, Duan (bib38) 2020; 23
Yuan, Wang, Wang, Mizzi (bib34) 2020; 202
Zubair, Zhang (bib25) 2020; 31
Olama, Kuruganti, Nutaro, Dong (bib8) 2018; 11
Xiong, Shuai, Hu (bib17) 2022; 244
Han, Feng, Zhao, Sun, Hong, Liu (bib35) 2019; 7
Volodymyr, Koray, David, Rusu, Joel, Bellemare, Alex, Martin, Fidjeland, Georg (bib48) 2015
Zhang, Guo, Sun, Liu, Forrest (bib29) 2022; 239
Li, Song, Fang, Chen, Ghamisi, Benediktsson (bib31) 2019; 57
Samek, Montavon, Lapuschkin, Anders, Müller (bib30) 2021; 109
Cui, Wang, Yan, Xue (bib5) 2015; 102
Mnih, Kavukcuoglu, Silver, Graves, Antonoglou, Wierstra (bib21) 2013; 1
Tashtoush, Molhim, Al-Rousan (bib9) 2005; 30
Yin, Xie (bib40) 2022; 238
bib49
Wang, Wang (bib13) 2021; 230
Zou, Yu, Ergan (bib23) 2020; 168
Ferreira, Silva, Ruano (bib11) 2012; 45
Vardakas, Zorba, Verikoukis (bib4) 2015; 17
Zhang, Han, Deng (bib47) 2018; 4
Baniassadi, Heusinger, Gonzalez, Weber, Samuelson (bib1) 2022; 238
Zhang, Wang, Dong, Zhong, Sun (bib36) 2017; 14
Chen, Hua, Zhao (bib41) 2017; 278
Thatte, Xie (bib14) 2012; 3
Turhan, Simani, Gokcen Akkurt (bib12) 2021; 237
Constantopoulos, Schweppe, Larson, Estia (bib15) 1991; 18
Totaro, Boukas, Jonsson, Cornélusse (bib20) 2021; 232
Saha (10.1016/j.energy.2022.124857_bib39) 2021; 37
Wang (10.1016/j.energy.2022.124857_bib26) 2020; 95
Lu (10.1016/j.energy.2022.124857_bib3) 2020; 195
Zubair (10.1016/j.energy.2022.124857_bib25) 2020; 31
Olama (10.1016/j.energy.2022.124857_bib8) 2018; 11
Chen (10.1016/j.energy.2022.124857_bib41) 2017; 278
Zhou (10.1016/j.energy.2022.124857_bib16) 2022; 247
Du (10.1016/j.energy.2022.124857_bib22) 2021; 192
Al Haj Hassan (10.1016/j.energy.2022.124857_bib2) 2015; 3
Toub (10.1016/j.energy.2022.124857_bib10) 2019; 199
Tokic (10.1016/j.energy.2022.124857_bib52) 2010
Kotevska (10.1016/j.energy.2022.124857_bib19) 2020; 126
Bouznad (10.1016/j.energy.2022.124857_bib27) 2020; 13
Samek (10.1016/j.energy.2022.124857_bib30) 2021; 109
Tashtoush (10.1016/j.energy.2022.124857_bib9) 2005; 30
Wang (10.1016/j.energy.2022.124857_bib13) 2021; 230
Yin (10.1016/j.energy.2022.124857_bib40) 2022; 238
Constantopoulos (10.1016/j.energy.2022.124857_bib15) 1991; 18
Cui (10.1016/j.energy.2022.124857_bib5) 2015; 102
Jing (10.1016/j.energy.2022.124857_bib28) 2018; 11
Lee (10.1016/j.energy.2022.124857_bib32) 1999; 29
Lillicrap (10.1016/j.energy.2022.124857_bib50) 2015
Sun (10.1016/j.energy.2022.124857_bib37) 2019; 15
Zhang (10.1016/j.energy.2022.124857_bib29) 2022; 239
Zhang (10.1016/j.energy.2022.124857_bib47) 2018; 4
Ferreira (10.1016/j.energy.2022.124857_bib11) 2012; 45
Zou (10.1016/j.energy.2022.124857_bib23) 2020; 168
Zhang (10.1016/j.energy.2022.124857_bib18) 2011; 383–390
Li (10.1016/j.energy.2022.124857_bib31) 2019; 57
Thatte (10.1016/j.energy.2022.124857_bib14) 2012; 3
Dupont (10.1016/j.energy.2022.124857_bib45) 2019; 200
Volodymyr (10.1016/j.energy.2022.124857_bib48) 2015
Mnih (10.1016/j.energy.2022.124857_bib21) 2013; 1
Turhan (10.1016/j.energy.2022.124857_bib12) 2021; 237
Yuan (10.1016/j.energy.2022.124857_bib24) 2016; 100
Baniassadi (10.1016/j.energy.2022.124857_bib1) 2022; 238
Chen (10.1016/j.energy.2022.124857_bib42) 2016; 64
Kong (10.1016/j.energy.2022.124857_bib51) 2019; 10
Han (10.1016/j.energy.2022.124857_bib35) 2019; 7
Totaro (10.1016/j.energy.2022.124857_bib20) 2021; 232
Zhang (10.1016/j.energy.2022.124857_bib36) 2017; 14
Yuan (10.1016/j.energy.2022.124857_bib34) 2020; 202
Xiong (10.1016/j.energy.2022.124857_bib17) 2022; 244
Ciavarella (10.1016/j.energy.2022.124857_bib44) 2016; 7
Yu (10.1016/j.energy.2022.124857_bib7) 2020; 7
Liu (10.1016/j.energy.2022.124857_bib43) 2020
Vardakas (10.1016/j.energy.2022.124857_bib4) 2015; 17
Su (10.1016/j.energy.2022.124857_bib6) 2009; 24
Chen (10.1016/j.energy.2022.124857_bib33) 2022; 239
Ren (10.1016/j.energy.2022.124857_bib38) 2020; 23
Almahdi (10.1016/j.energy.2022.124857_bib46) 2018
References_xml – volume: 238
  year: 2022
  ident: bib1
  article-title: Co-benefits of energy efficiency in residential buildings
  publication-title: Energy
– start-page: 3508
  year: 2020
  end-page: 3512
  ident: bib43
  article-title: A prediction method of nox in thermal power plants using gc-lstm neural network
  publication-title: 2020 Chinese automation congress (CAC)
– volume: 126
  year: 2020
  ident: bib19
  article-title: Rl-hems: reinforcement learning based home energy management system for hvac energy optimization
  publication-title: Build Eng
– volume: 239
  year: 2022
  ident: bib33
  article-title: A new prediction model of co
  publication-title: Energy
– volume: 7
  start-page: 2751
  year: 2020
  end-page: 2762
  ident: bib7
  article-title: Deep reinforcement learning for smart home energy management
  publication-title: IEEE Internet Things J
– year: 2015
  ident: bib50
  article-title: Continuous control with deep reinforcement learning
  publication-title: Comput Sci
– volume: 237
  year: 2021
  ident: bib12
  article-title: Development of a personalized thermal comfort driven controller for hvac systems
  publication-title: Energy
– volume: 4
  start-page: 362
  year: 2018
  end-page: 370
  ident: bib47
  article-title: Review on the research and practice of deep learning and reinforcement learning in smart grids
  publication-title: CSEE J Power Energy Syst
– volume: 14
  start-page: 1745
  year: 2017
  end-page: 1749
  ident: bib36
  article-title: Prediction of sea surface temperature using long short-term memory
  publication-title: Geosci Rem Sens Lett IEEE
– volume: 278
  start-page: 41
  year: 2017
  end-page: 50
  ident: bib41
  article-title: Generalized correntropy based deep learning in presence of non-Gaussian noises
  publication-title: Neurocomputing
– start-page: 529
  year: 2015
  end-page: 533
  ident: bib48
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
– volume: 30
  start-page: 1729
  year: 2005
  end-page: 1745
  ident: bib9
  article-title: Dynamic model of an hvac system for control analysis
  publication-title: Energy
– volume: 202
  year: 2020
  ident: bib34
  article-title: Combination of cuckoo search and wavelet neural network for midterm building energy forecast
  publication-title: Energy
– volume: 31
  year: 2020
  ident: bib25
  article-title: Explicit data-driven prediction model of annual energy consumed by elevators in residential buildings
  publication-title: J Build Eng
– start-page: 1
  year: 2018
  end-page: 11
  ident: bib46
  article-title: Modeling, analysis, and state feedback control design of a multizone hvac system
  publication-title: J Energy
– volume: 239
  year: 2022
  ident: bib29
  article-title: A novel flexible grey multivariable model and its application in forecasting energy consumption in China
  publication-title: Energy
– ident: bib49
– volume: 195
  year: 2020
  ident: bib3
  article-title: Optimal household energy management based on smart residential energy hub considering uncertain behaviors
  publication-title: Energy
– volume: 232
  year: 2021
  ident: bib20
  article-title: Lifelong control of off-grid microgrid with model-based reinforcement learning
  publication-title: Energy
– volume: 383–390
  start-page: 4768
  year: 2011
  end-page: 4774
  ident: bib18
  article-title: An improved particle swarm optimization approach for temperature control in hvac for the purpose of energy saving
  publication-title: Adv Mater Res
– volume: 109
  start-page: 247
  year: 2021
  end-page: 278
  ident: bib30
  article-title: Explaining deep neural networks and beyond: a review of methods and applications
  publication-title: Proc IEEE
– volume: 11
  start-page: 1852
  year: 2018
  ident: bib8
  article-title: Coordination and control of building hvac systems to provide frequency regulation to the electric grid
  publication-title: Energies
– volume: 230
  year: 2021
  ident: bib13
  article-title: A hierarchical optimal control strategy for continuous demand response of building hvac systems to provide frequency regulation service to smart power grids
  publication-title: Energy
– volume: 7
  start-page: 172816
  year: 2019
  end-page: 172829
  ident: bib35
  article-title: A convolutional neural network using surface data to predict subsurface temperatures in the pacific ocean
  publication-title: IEEE Access
– volume: 17
  start-page: 152
  year: 2015
  end-page: 178
  ident: bib4
  article-title: A survey on demand response programs in smart grids: pricing methods and optimization algorithms
  publication-title: IEEE Commun Surv Tutorials
– volume: 247
  year: 2022
  ident: bib16
  article-title: Location optimization of electric vehicle charging stations: based on cost model and genetic algorithm
  publication-title: Energy
– volume: 45
  start-page: 236
  year: 2012
  end-page: 241
  ident: bib11
  article-title: Model based predictive control of hvac systems for human thermal comfort and energy consumption minimisation
  publication-title: IFAC Proc Vol
– volume: 18
  start-page: 751
  year: 1991
  end-page: 765
  ident: bib15
  article-title: A real-time consumer control scheme for space conditioning usage under spot electricity pricing
  publication-title: Comput Oper Res
– volume: 244
  year: 2022
  ident: bib17
  article-title: Combined heat and power economic emission dispatch using improved bare-bone multi-objective particle swarm optimization
  publication-title: Energy
– year: 2010
  ident: bib52
  article-title: Adaptive
  publication-title: Annual conference on artificial intelligence
– volume: 100
  start-page: 384
  year: 2016
  end-page: 390
  ident: bib24
  article-title: Comparison of China's primary energy consumption forecasting by using arima (the autoregressive integrated moving average) model and gm(1,1) model
  publication-title: Energy
– volume: 102
  start-page: 227
  year: 2015
  end-page: 238
  ident: bib5
  article-title: Evaluation of a fast power demand response strategy using active and passive building cold storages for smart grid applications
  publication-title: Energy Convers Manag
– volume: 24
  start-page: 1199
  year: 2009
  end-page: 1207
  ident: bib6
  article-title: Quantifying the effect of demand response on electricity markets
  publication-title: IEEE Trans Power Syst
– volume: 3
  start-page: 1418
  year: 2012
  end-page: 1426
  ident: bib14
  article-title: Towards a unified operational value index of energy storage in smart grid environment
  publication-title: IEEE Trans Smart Grid
– volume: 192
  year: 2021
  ident: bib22
  article-title: Multi-task deep reinforcement learning for intelligent multi-zone residential hvac control
  publication-title: Elec Power Syst Res
– volume: 238
  year: 2022
  ident: bib40
  article-title: Multi-feature-scale fusion temporal convolution networks for metal temperature forecasting of ultra-supercritical coal-fired power plant reheater tubes
  publication-title: Energy
– volume: 168
  year: 2020
  ident: bib23
  article-title: Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network
  publication-title: Build Environ
– volume: 13
  start-page: 1
  year: 2020
  end-page: 17
  ident: bib27
  article-title: Trend analysis and spatiotemporal prediction of precipitation, temperature, and evapotranspiration values using the arima models: case of the algerian highlands
  publication-title: Arabian J Geosci
– volume: 64
  start-page: 3376
  year: 2016
  end-page: 3387
  ident: bib42
  article-title: Generalized correntropy for robust adaptive filtering
  publication-title: IEEE Trans Signal Process
– volume: 23
  start-page: 1
  year: 2020
  end-page: 7
  ident: bib38
  article-title: Global-local temporal convolutional network for traffic flow prediction
  publication-title: IEEE Trans Intell Transport Syst
– volume: 95
  year: 2020
  ident: bib26
  article-title: A novel grey prediction model based on quantile regression - sciencedirect
  publication-title: Commun Nonlinear Sci Numer Simulat
– volume: 29
  start-page: 674
  year: 1999
  end-page: 685
  ident: bib32
  article-title: Robust radial basis function neural networks
  publication-title: IEEE Trans Syst Man Cybernet Part B (Cybernet)
– volume: 37
  start-page: 58
  year: 2021
  end-page: 71
  ident: bib39
  article-title: Prediction of the indian summer monsoon using a stacked autoencoder and ensemble regression model
  publication-title: Int J Forecast
– volume: 15
  start-page: 2416
  year: 2019
  end-page: 2425
  ident: bib37
  article-title: Deep transfer learning based on sparse autoencoder for remaining useful life prediction of tool in manufacturing
  publication-title: IEEE Trans Ind Inf
– volume: 3
  start-page: 2755
  year: 2015
  end-page: 2770
  ident: bib2
  article-title: Integrating cellular networks, smart grid, and renewable energy: analysis, architecture, and challenges
  publication-title: IEEE Access
– volume: 7
  start-page: 2134
  year: 2016
  end-page: 2141
  ident: bib44
  article-title: Managing contingencies in smart grids via the internet of things
  publication-title: IEEE Trans Smart Grid
– volume: 200
  year: 2019
  ident: bib45
  article-title: Novel methodology for detecting non-ideal operating conditions for grid-connected photovoltaic plants using internet of things architecture
  publication-title: Energy Convers Manag
– volume: 57
  start-page: 6690
  year: 2019
  end-page: 6709
  ident: bib31
  article-title: Deep learning for hyperspectral image classification: an overview
  publication-title: IEEE Trans Geosci Rem Sens
– volume: 11
  start-page: 1900
  year: 2018
  ident: bib28
  article-title: Uncertainty analysis of weather forecast data for cooling load forecasting based on the Monte Carlo method
  publication-title: Energies
– volume: 10
  start-page: 841
  year: 2019
  end-page: 851
  ident: bib51
  article-title: Short-term residential load forecasting based on lstm recurrent neural network
  publication-title: IEEE Trans Smart Grid
– volume: 1
  year: 2013
  ident: bib21
  article-title: Playing atari with deep reinforcement learning
  publication-title: Comput Sci
– volume: 199
  year: 2019
  ident: bib10
  article-title: Model-based predictive control for optimal microcsp operation integrated with building hvac systems
  publication-title: Energy Convers Manag
– volume: 31
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib25
  article-title: Explicit data-driven prediction model of annual energy consumed by elevators in residential buildings
  publication-title: J Build Eng
– start-page: 1
  year: 2018
  ident: 10.1016/j.energy.2022.124857_bib46
  article-title: Modeling, analysis, and state feedback control design of a multizone hvac system
  publication-title: J Energy
– volume: 13
  start-page: 1
  issue: 24
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib27
  article-title: Trend analysis and spatiotemporal prediction of precipitation, temperature, and evapotranspiration values using the arima models: case of the algerian highlands
  publication-title: Arabian J Geosci
  doi: 10.1007/s12517-020-06330-6
– volume: 192
  year: 2021
  ident: 10.1016/j.energy.2022.124857_bib22
  article-title: Multi-task deep reinforcement learning for intelligent multi-zone residential hvac control
  publication-title: Elec Power Syst Res
  doi: 10.1016/j.epsr.2020.106959
– volume: 195
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib3
  article-title: Optimal household energy management based on smart residential energy hub considering uncertain behaviors
  publication-title: Energy
  doi: 10.1016/j.energy.2020.117052
– volume: 247
  year: 2022
  ident: 10.1016/j.energy.2022.124857_bib16
  article-title: Location optimization of electric vehicle charging stations: based on cost model and genetic algorithm
  publication-title: Energy
  doi: 10.1016/j.energy.2022.123437
– volume: 11
  start-page: 1900
  issue: 7
  year: 2018
  ident: 10.1016/j.energy.2022.124857_bib28
  article-title: Uncertainty analysis of weather forecast data for cooling load forecasting based on the Monte Carlo method
  publication-title: Energies
  doi: 10.3390/en11071900
– volume: 102
  start-page: 227
  year: 2015
  ident: 10.1016/j.energy.2022.124857_bib5
  article-title: Evaluation of a fast power demand response strategy using active and passive building cold storages for smart grid applications
  publication-title: Energy Convers Manag
  doi: 10.1016/j.enconman.2014.12.025
– volume: 3
  start-page: 1418
  issue: 3
  year: 2012
  ident: 10.1016/j.energy.2022.124857_bib14
  article-title: Towards a unified operational value index of energy storage in smart grid environment
  publication-title: IEEE Trans Smart Grid
  doi: 10.1109/TSG.2012.2190114
– volume: 232
  year: 2021
  ident: 10.1016/j.energy.2022.124857_bib20
  article-title: Lifelong control of off-grid microgrid with model-based reinforcement learning
  publication-title: Energy
  doi: 10.1016/j.energy.2021.121035
– volume: 37
  start-page: 58
  issue: 1
  year: 2021
  ident: 10.1016/j.energy.2022.124857_bib39
  article-title: Prediction of the indian summer monsoon using a stacked autoencoder and ensemble regression model
  publication-title: Int J Forecast
  doi: 10.1016/j.ijforecast.2020.03.001
– volume: 24
  start-page: 1199
  issue: 3
  year: 2009
  ident: 10.1016/j.energy.2022.124857_bib6
  article-title: Quantifying the effect of demand response on electricity markets
  publication-title: IEEE Trans Power Syst
  doi: 10.1109/TPWRS.2009.2023259
– volume: 237
  year: 2021
  ident: 10.1016/j.energy.2022.124857_bib12
  article-title: Development of a personalized thermal comfort driven controller for hvac systems
  publication-title: Energy
  doi: 10.1016/j.energy.2021.121568
– volume: 64
  start-page: 3376
  issue: 13
  year: 2016
  ident: 10.1016/j.energy.2022.124857_bib42
  article-title: Generalized correntropy for robust adaptive filtering
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2016.2539127
– year: 2015
  ident: 10.1016/j.energy.2022.124857_bib50
  article-title: Continuous control with deep reinforcement learning
  publication-title: Comput Sci
– volume: 199
  year: 2019
  ident: 10.1016/j.energy.2022.124857_bib10
  article-title: Model-based predictive control for optimal microcsp operation integrated with building hvac systems
  publication-title: Energy Convers Manag
  doi: 10.1016/j.enconman.2019.111924
– volume: 278
  start-page: 41
  issue: FEB.22
  year: 2017
  ident: 10.1016/j.energy.2022.124857_bib41
  article-title: Generalized correntropy based deep learning in presence of non-Gaussian noises
  publication-title: Neurocomputing
– volume: 29
  start-page: 674
  issue: 6
  year: 1999
  ident: 10.1016/j.energy.2022.124857_bib32
  article-title: Robust radial basis function neural networks
  publication-title: IEEE Trans Syst Man Cybernet Part B (Cybernet)
  doi: 10.1109/3477.809023
– volume: 30
  start-page: 1729
  issue: 10
  year: 2005
  ident: 10.1016/j.energy.2022.124857_bib9
  article-title: Dynamic model of an hvac system for control analysis
  publication-title: Energy
  doi: 10.1016/j.energy.2004.10.004
– volume: 17
  start-page: 152
  issue: 1
  year: 2015
  ident: 10.1016/j.energy.2022.124857_bib4
  article-title: A survey on demand response programs in smart grids: pricing methods and optimization algorithms
  publication-title: IEEE Commun Surv Tutorials
  doi: 10.1109/COMST.2014.2341586
– volume: 239
  year: 2022
  ident: 10.1016/j.energy.2022.124857_bib29
  article-title: A novel flexible grey multivariable model and its application in forecasting energy consumption in China
  publication-title: Energy
  doi: 10.1016/j.energy.2021.122441
– volume: 7
  start-page: 2134
  issue: 4
  year: 2016
  ident: 10.1016/j.energy.2022.124857_bib44
  article-title: Managing contingencies in smart grids via the internet of things
  publication-title: IEEE Trans Smart Grid
  doi: 10.1109/TSG.2016.2529579
– volume: 95
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib26
  article-title: A novel grey prediction model based on quantile regression - sciencedirect
  publication-title: Commun Nonlinear Sci Numer Simulat
– volume: 57
  start-page: 6690
  issue: 9
  year: 2019
  ident: 10.1016/j.energy.2022.124857_bib31
  article-title: Deep learning for hyperspectral image classification: an overview
  publication-title: IEEE Trans Geosci Rem Sens
  doi: 10.1109/TGRS.2019.2907932
– volume: 126
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib19
  article-title: Rl-hems: reinforcement learning based home energy management system for hvac energy optimization
  publication-title: Build Eng
– volume: 4
  start-page: 362
  issue: 3
  year: 2018
  ident: 10.1016/j.energy.2022.124857_bib47
  article-title: Review on the research and practice of deep learning and reinforcement learning in smart grids
  publication-title: CSEE J Power Energy Syst
  doi: 10.17775/CSEEJPES.2018.00520
– volume: 18
  start-page: 751
  issue: 8
  year: 1991
  ident: 10.1016/j.energy.2022.124857_bib15
  article-title: A real-time consumer control scheme for space conditioning usage under spot electricity pricing
  publication-title: Comput Oper Res
  doi: 10.1016/0305-0548(91)90013-H
– volume: 383–390
  start-page: 4768
  year: 2011
  ident: 10.1016/j.energy.2022.124857_bib18
  article-title: An improved particle swarm optimization approach for temperature control in hvac for the purpose of energy saving
  publication-title: Adv Mater Res
  doi: 10.4028/www.scientific.net/AMR.383-390.4768
– volume: 45
  start-page: 236
  issue: 4
  year: 2012
  ident: 10.1016/j.energy.2022.124857_bib11
  article-title: Model based predictive control of hvac systems for human thermal comfort and energy consumption minimisation
  publication-title: IFAC Proc Vol
  doi: 10.3182/20120403-3-DE-3010.00085
– volume: 200
  year: 2019
  ident: 10.1016/j.energy.2022.124857_bib45
  article-title: Novel methodology for detecting non-ideal operating conditions for grid-connected photovoltaic plants using internet of things architecture
  publication-title: Energy Convers Manag
  doi: 10.1016/j.enconman.2019.112078
– volume: 11
  start-page: 1852
  issue: 7
  year: 2018
  ident: 10.1016/j.energy.2022.124857_bib8
  article-title: Coordination and control of building hvac systems to provide frequency regulation to the electric grid
  publication-title: Energies
  doi: 10.3390/en11071852
– volume: 10
  start-page: 841
  issue: 1
  year: 2019
  ident: 10.1016/j.energy.2022.124857_bib51
  article-title: Short-term residential load forecasting based on lstm recurrent neural network
  publication-title: IEEE Trans Smart Grid
  doi: 10.1109/TSG.2017.2753802
– volume: 1
  issue: 1
  year: 2013
  ident: 10.1016/j.energy.2022.124857_bib21
  article-title: Playing atari with deep reinforcement learning
  publication-title: Comput Sci
– volume: 100
  start-page: 384
  year: 2016
  ident: 10.1016/j.energy.2022.124857_bib24
  article-title: Comparison of China's primary energy consumption forecasting by using arima (the autoregressive integrated moving average) model and gm(1,1) model
  publication-title: Energy
  doi: 10.1016/j.energy.2016.02.001
– volume: 238
  year: 2022
  ident: 10.1016/j.energy.2022.124857_bib40
  article-title: Multi-feature-scale fusion temporal convolution networks for metal temperature forecasting of ultra-supercritical coal-fired power plant reheater tubes
  publication-title: Energy
  doi: 10.1016/j.energy.2021.121657
– volume: 168
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib23
  article-title: Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network
  publication-title: Build Environ
  doi: 10.1016/j.buildenv.2019.106535
– year: 2010
  ident: 10.1016/j.energy.2022.124857_bib52
  article-title: Adaptive ϵ-greedy exploration in reinforcement learning based on value differences
– volume: 202
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib34
  article-title: Combination of cuckoo search and wavelet neural network for midterm building energy forecast
  publication-title: Energy
  doi: 10.1016/j.energy.2020.117728
– start-page: 529
  issue: 7540
  year: 2015
  ident: 10.1016/j.energy.2022.124857_bib48
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
– volume: 7
  start-page: 172816
  year: 2019
  ident: 10.1016/j.energy.2022.124857_bib35
  article-title: A convolutional neural network using surface data to predict subsurface temperatures in the pacific ocean
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2955957
– volume: 244
  year: 2022
  ident: 10.1016/j.energy.2022.124857_bib17
  article-title: Combined heat and power economic emission dispatch using improved bare-bone multi-objective particle swarm optimization
  publication-title: Energy
  doi: 10.1016/j.energy.2022.123108
– volume: 15
  start-page: 2416
  issue: 4
  year: 2019
  ident: 10.1016/j.energy.2022.124857_bib37
  article-title: Deep transfer learning based on sparse autoencoder for remaining useful life prediction of tool in manufacturing
  publication-title: IEEE Trans Ind Inf
  doi: 10.1109/TII.2018.2881543
– volume: 14
  start-page: 1745
  issue: 10
  year: 2017
  ident: 10.1016/j.energy.2022.124857_bib36
  article-title: Prediction of sea surface temperature using long short-term memory
  publication-title: Geosci Rem Sens Lett IEEE
  doi: 10.1109/LGRS.2017.2733548
– volume: 109
  start-page: 247
  issue: 3
  year: 2021
  ident: 10.1016/j.energy.2022.124857_bib30
  article-title: Explaining deep neural networks and beyond: a review of methods and applications
  publication-title: Proc IEEE
  doi: 10.1109/JPROC.2021.3060483
– start-page: 3508
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib43
  article-title: A prediction method of nox in thermal power plants using gc-lstm neural network
– volume: 230
  year: 2021
  ident: 10.1016/j.energy.2022.124857_bib13
  article-title: A hierarchical optimal control strategy for continuous demand response of building hvac systems to provide frequency regulation service to smart power grids
  publication-title: Energy
  doi: 10.1016/j.energy.2021.120741
– volume: 7
  start-page: 2751
  issue: 4
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib7
  article-title: Deep reinforcement learning for smart home energy management
  publication-title: IEEE Internet Things J
  doi: 10.1109/JIOT.2019.2957289
– volume: 3
  start-page: 2755
  year: 2015
  ident: 10.1016/j.energy.2022.124857_bib2
  article-title: Integrating cellular networks, smart grid, and renewable energy: analysis, architecture, and challenges
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2015.2507781
– volume: 23
  start-page: 1
  issue: 99
  year: 2020
  ident: 10.1016/j.energy.2022.124857_bib38
  article-title: Global-local temporal convolutional network for traffic flow prediction
  publication-title: IEEE Trans Intell Transport Syst
– volume: 239
  year: 2022
  ident: 10.1016/j.energy.2022.124857_bib33
  article-title: A new prediction model of co2 diffusion coefficient in crude oil under reservoir conditions based on bp neural network
  publication-title: Energy
  doi: 10.1016/j.energy.2021.122286
– volume: 238
  year: 2022
  ident: 10.1016/j.energy.2022.124857_bib1
  article-title: Co-benefits of energy efficiency in residential buildings
  publication-title: Energy
  doi: 10.1016/j.energy.2021.121768
SSID ssj0005899
Score 2.5726454
Snippet The development of the building energy management systems (BEMS) enable users to intelligently control Heating, Ventilation, Air-conditioning and Cooling...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 124857
SubjectTerms algorithms
ambient temperature
consumer satisfaction
Deep reinforcement learning
electricity
energy
energy use and consumption
Generalized correntropy
heat
HVAC system
issues and policy
Multi-step prediction
neural networks
prediction
Title A multi-step predictive deep reinforcement learning algorithm for HVAC control systems in smart buildings
URI https://dx.doi.org/10.1016/j.energy.2022.124857
https://www.proquest.com/docview/2718277788
Volume 259
WOSCitedRecordID wos000848270400003&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
  issn: 0360-5442
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0005899
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLdKhwQXBIOJ8SUjcatc5cuxc4ymooGmicOYKi6R4zhdpi6tmnb0xN_O80eSdXyMHbhEjWs7Tn6_PD-_vPeM0AcWxEUug4LEShYkigUlXOSMKOrLSMkk5CaO-_yEnZ7y6TT5Mhj8aGNhruesrvl2myz_K9RQBmDr0Nl7wN11CgXwG0CHI8AOx38CPrVOggTgW-oUAEVlRNqoUHC-UiZTqjRGwXbLiNlIzGeLVbW-uDJeh8fn6VHnw25TPRuv2eYKLjfK3UbazY5R34YQ6tylW-su3xkYTqqNxnEKPJyVquq-8Cjntl8qN3lq2eOs198uqrm6UWis92Lx3TV3VgpY4GpPOXpDmIWxR2gU7UjewCUDt7LT19nV2G_FurUwXI6VuZmxvsC4r76bRfvW7Nb5HLbubJeZ7SXTvWS2lwdoL2A04UO0l36aTD_3TkLc7EDajb4NvjQegr-O5k_Kza1p3uguZ0_RE7fowKklyzM0UPU-etTGpDf76GDSxztCRSfwm-eoSnHPJtyzCWs24R024ZZNuGMThj-xZhN2bMKOTbiqsWET7tj0An39ODk7OiZudw4iwzBZE8pyTzJRUBVSEfgeFzQRZURBh4U1UKyDmANOPekXPCi5NrYHXEVl4ikvVDGcHqBhvajVS4RpImUheewJUG5FnIi4LIqI5iLmHsuFf4jC9rFm0qWu1zuozLO_gXqISNdqaVO33FGftYhlTv20amUGNLyj5fsW4Ayks_7kJmq12DRZAKpfwBjj_NU9R_MaPe7fozdouF5t1Fv0UF6vq2b1zvH0J_6xtmU
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=A+multi-step+predictive+deep+reinforcement+learning+algorithm+for+HVAC+control+systems+in+smart+buildings&rft.jtitle=Energy+%28Oxford%29&rft.au=Liu%2C+Xiangfei&rft.au=Ren%2C+Mifeng&rft.au=Yang%2C+Zhile&rft.au=Yan%2C+Gaowei&rft.date=2022-11-15&rft.issn=0360-5442&rft.volume=259&rft.spage=124857&rft_id=info:doi/10.1016%2Fj.energy.2022.124857&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_energy_2022_124857
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-5442&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-5442&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-5442&client=summon