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...
Gespeichert in:
| Veröffentlicht in: | Energy (Oxford) Jg. 259; S. 124857 |
|---|---|
| Hauptverfasser: | , , , , , , |
| 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 |