MITP-Net: A deep-learning framework for short-term indoor temperature predictions in multi-zone buildings
Indoor temperature prediction is an essential component of building control and energy saving. Although existing indoor temperature prediction frameworks have achieved remarkable progress, they struggle to achieve high performance due to information, method, application, and sim-to-real gaps. Aiming...
Uloženo v:
| Vydáno v: | Building and environment Ročník 239; s. 110388 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.07.2023
|
| Témata: | |
| ISSN: | 0360-1323, 1873-684X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Indoor temperature prediction is an essential component of building control and energy saving. Although existing indoor temperature prediction frameworks have achieved remarkable progress, they struggle to achieve high performance due to information, method, application, and sim-to-real gaps. Aiming to fill these gaps, we propose a novel deep-learning framework for short-term indoor temperature prediction in multi-zone buildings. In particular, we expand the sensing information and formulate the multi-zone indoor temperature prediction (MITP) problem. To improve the prediction performance, we employ information fusion and encoder–decoder architecture to the MITP problem and propose MITP-Net. We set up 11 ablation experiments to compare the prediction performance of relative frameworks. To evaluate frameworks’ performance, we publicly release a dataset including 2-week real operating data in a multi-zone office with a 1-min sampling interval (829,440 digits in total). Compared with existing deep-learning frameworks, MITP-Net significantly raises the prediction accuracy and can flexibly adjust the lengths of input and prediction sequences for different requirements. We provide the usage steps of MITP-Net and publish the operating data and codes on the GitHub repository: https://github.com/XingTian1994/MITP-Net.
•We formulate the MITP problem and propose a novel deep-learning prediction framework.•MITP-Net utilizes a two-stage information fusion method for multi-modal data.•MITP-Net adopts the encoder–decoder architecture for variable sequences length.•We publicly release a real multi-zone office dataset and verify MITP-Net.•MITP-Net significantly improves the performance compared to existing methods. |
|---|---|
| AbstractList | Indoor temperature prediction is an essential component of building control and energy saving. Although existing indoor temperature prediction frameworks have achieved remarkable progress, they struggle to achieve high performance due to information, method, application, and sim-to-real gaps. Aiming to fill these gaps, we propose a novel deep-learning framework for short-term indoor temperature prediction in multi-zone buildings. In particular, we expand the sensing information and formulate the multi-zone indoor temperature prediction (MITP) problem. To improve the prediction performance, we employ information fusion and encoder–decoder architecture to the MITP problem and propose MITP-Net. We set up 11 ablation experiments to compare the prediction performance of relative frameworks. To evaluate frameworks’ performance, we publicly release a dataset including 2-week real operating data in a multi-zone office with a 1-min sampling interval (829,440 digits in total). Compared with existing deep-learning frameworks, MITP-Net significantly raises the prediction accuracy and can flexibly adjust the lengths of input and prediction sequences for different requirements. We provide the usage steps of MITP-Net and publish the operating data and codes on the GitHub repository: https://github.com/XingTian1994/MITP-Net.
•We formulate the MITP problem and propose a novel deep-learning prediction framework.•MITP-Net utilizes a two-stage information fusion method for multi-modal data.•MITP-Net adopts the encoder–decoder architecture for variable sequences length.•We publicly release a real multi-zone office dataset and verify MITP-Net.•MITP-Net significantly improves the performance compared to existing methods. |
| ArticleNumber | 110388 |
| Author | Sun, Kailai Zhao, Qianchuan Xing, Tian |
| Author_xml | – sequence: 1 givenname: Tian orcidid: 0000-0003-0528-2644 surname: Xing fullname: Xing, Tian email: xingt19@mails.tsinghua.edu.cn – sequence: 2 givenname: Kailai orcidid: 0000-0003-1648-3409 surname: Sun fullname: Sun, Kailai email: skl18@mails.tsinghua.edu.cn – sequence: 3 givenname: Qianchuan orcidid: 0000-0002-7952-5621 surname: Zhao fullname: Zhao, Qianchuan email: zhaoqc@mail.tsinghua.edu.cn |
| BookMark | eNqFkMtKAzEUhoNUsK2-guQFMiaT6UwqLizFS6FeFl24C5nkjKbOjSSt6NObWt24KRwInMP38-cboUHbtYDQOaMJoyy_WCflxtYG2m2S0pQnjFEuxBEaMlFwkovsZYCGlOeUMJ7yEzTyfk0jOOXZENmHxeqZPEK4xDNsAHpSg3KtbV9x5VQDH517x1XnsH_rXCABXINta7q4CdD04FTYOMC9A2N1sF3r4xk3mzpY8hV74p9uMc6fouNK1R7Oft8xWt3erOb3ZPl0t5jPlkSnaRGIKZjIsyKbTKZGM8FKwWhWpKYyWaGATkutdDxmZZysKlLNy1wIVuVQmiLnfIyu9rHadd47qKS2Qe2aBadsLRmVO2tyLf-syZ01ubcW8fwf3jvbKPd5GLzegxD_trXgpNcWWh29ONBBms4eivgGXiSPYg |
| CitedBy_id | crossref_primary_10_1016_j_jobe_2024_110411 crossref_primary_10_1016_j_buildenv_2025_112729 crossref_primary_10_1016_j_buildenv_2023_110807 crossref_primary_10_1016_j_buildenv_2025_113641 crossref_primary_10_3390_buildings13082002 crossref_primary_10_1016_j_jobe_2025_113714 crossref_primary_10_3390_jmse13030405 |
| Cites_doi | 10.3390/w13081031 10.1016/j.apenergy.2018.09.052 10.1016/j.enbuild.2018.06.039 10.1016/j.enbuild.2020.109965 10.1016/j.buildenv.2022.109354 10.1016/j.buildenv.2022.109164 10.1016/j.enbuild.2016.03.046 10.1007/s00521-006-0047-9 10.1109/JSEN.2019.2923982 10.3390/en15072623 10.1007/s12273-013-0142-7 10.1016/j.enbuild.2016.03.054 10.1016/j.buildenv.2021.108633 10.1016/j.apenergy.2019.04.065 10.1016/j.enbuild.2004.09.009 10.1016/j.scs.2020.102328 10.1016/j.enbuild.2017.06.076 10.1016/j.buildenv.2019.03.062 10.1016/j.buildenv.2021.108164 10.1016/j.buildenv.2022.108938 10.1016/j.enbuild.2019.109473 10.1016/j.patter.2022.100605 10.1109/23.589532 10.1016/j.ins.2011.12.028 10.1016/j.buildenv.2021.108581 10.1016/j.enbuild.2021.111379 10.1016/j.enbuild.2010.04.006 10.1007/s00530-010-0182-0 10.1186/s40537-021-00444-8 10.3390/en12112122 10.1016/j.enbuild.2012.06.024 10.1016/j.energy.2021.121228 10.3390/s18113610 10.1016/j.enbuild.2019.109451 10.1016/j.future.2017.09.082 10.1016/j.enbuild.2018.03.082 10.1016/j.buildenv.2021.108327 10.1214/09-SS054 10.1109/JIOT.2017.2647881 10.1016/j.energy.2022.123856 10.1016/j.asoc.2018.03.043 10.1016/j.buildenv.2020.107432 10.1016/j.apenergy.2020.114683 10.1016/j.apenergy.2021.117486 10.1109/JSEN.2019.2922409 10.1016/j.enbuild.2019.06.029 10.1016/j.buildenv.2022.108964 10.1016/j.buildenv.2022.109511 10.1016/j.buildenv.2021.108355 10.1016/j.enpol.2021.112293 10.1016/j.buildenv.2018.10.062 10.1016/j.apenergy.2019.01.022 10.1016/j.enbuild.2021.111593 10.1016/j.apenergy.2020.116117 10.1016/j.buildenv.2022.109536 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.buildenv.2023.110388 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1873-684X |
| ExternalDocumentID | 10_1016_j_buildenv_2023_110388 S0360132323004158 |
| GroupedDBID | --K --M -~X .~1 0R~ 1B1 1RT 1~. 1~5 23N 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AAEDT AAEDW AAHCO AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AARJD AAXUO ABFNM ABFYP ABJNI ABLST ABMAC ABYKQ ACDAQ ACGFS ACIWK ACRLP ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFRAH AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHHHB AHIDL AHJVU AIEXJ AIKHN AITUG AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BELTK BJAXD BKOJK BLECG BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W JARJE JJJVA KCYFY KOM LY6 LY7 LY9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 PC. Q38 RNS ROL RPZ SDF SDG SDP SEN SES SEW SPC SPCBC SSJ SSR SST SSZ T5K ~G- 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADMUD ADNMO AEGFY AEIPS AEUPX AFJKZ AFPUW AGQPQ AI. AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB G-2 HMC HVGLF HZ~ R2- SAC SET VH1 WUQ ZMT ~HD |
| ID | FETCH-LOGICAL-c227t-d7186474559dc181b810472dfd47ae09bcac4554b54b4f72c3b6881f6ebd7633 |
| ISSN | 0360-1323 |
| IngestDate | Sat Nov 29 07:20:56 EST 2025 Tue Nov 18 22:20:49 EST 2025 Fri Feb 23 02:35:19 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Encoder–decoder architecture Multi-zone temperature prediction Multiple sensor information Gated recurrent unit network Information fusion |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c227t-d7186474559dc181b810472dfd47ae09bcac4554b54b4f72c3b6881f6ebd7633 |
| ORCID | 0000-0003-1648-3409 0000-0003-0528-2644 0000-0002-7952-5621 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_buildenv_2023_110388 crossref_primary_10_1016_j_buildenv_2023_110388 elsevier_sciencedirect_doi_10_1016_j_buildenv_2023_110388 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-07-01 2023-07-00 |
| PublicationDateYYYYMMDD | 2023-07-01 |
| PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Building and environment |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Lamb, Alias Parth Goyal, Zhang, Zhang, Courville, Bengio (b59) 2016; 29 Jung, Jeoung, Hong (b4) 2022; 208 Plageras, Psannis, Stergiou, Wang, Gupta (b42) 2018; 82 Liu, Luh, Sun (b49) 2022 Wu, Su, Cheng, Shao, Deng, Liu (b51) 2018; 68 Du, Zandi, Kotevska, Kurte, Munk, Amasyali, Mckee, Li (b65) 2021; 281 Yang, Wan, Ng, Dubey, Henze, Rai, Baskaran (b66) 2019; 203 Dong, Cao, Lee (b21) 2005; 37 Dey, Salem (b53) 2017 Gao, Liu, Cao, Hwang, Radermacher (b24) 2021; 301 Oliveira Panão, Santos, Mateus, Carrilho da Graça (b15) 2016; 121 Sun, Zhao, Zhang, Hu (b61) 2022; 254 Minoli, Sohraby, Occhiogrosso (b43) 2017; 4 Du, Narasimhan (b70) 2019 Alzubaidi, Zhang, Humaidi, Al-Dujaili, Duan, Al-Shamma, Santamaría, Fadhel, Al-Amidie, Farhan (b30) 2021; 8 Zhou, Guo, Han, Wang, Lu, Shi, Kou (b32) 2022; 215 Xue, Pan, Lin, Song, Qi, Wang (b34) 2019; 12 Sun, Zhao, Zou (b44) 2020; 216 Taheri, Razban (b37) 2021; 205 Dong, Lam (b67) 2014; 7 Qian, Tang, Gao, Dong, Liang, Liu (b36) 2022; 223 Masood, Gantassi, Ardiansyah, Choi (b47) 2022; 15 Xu, Wang, Lin, Xiao, Huang, Zhang (b48) 2021; 13 Arlot, Celisse (b63) 2010; 4 Li, Wang, Zhang, Mu (b1) 2022; 219 Gao, Ruan (b29) 2021; 252 Bergmeir, Benítez (b64) 2012; 191 Chaudhuri, Soh, Li, Xie (b7) 2019; 248 Thomas, Soleimani-Mohseni (b22) 2006; 16 Magalhães, Leal, Horta (b10) 2017; 151 Wang, Hong, Piette (b12) 2020; 263 Monteiro, Zanin, Menasalvas Ruiz, Pimentão, Alexandre da Costa Sousa (b13) 2018; 18 Verma, Prakash, Srivastava, Kumar, Mukhopadhyay (b40) 2019; 19 Al Dakheel, Del Pero, Aste, Leonforte (b41) 2020; 61 Sun, Ma, Liu, Zhao (b57) 2022; 222 Xing, Li, Zhang (b14) 2018; 174 Nsangou, Kenfack, Nzotcha, Ngohe Ekam, Voufo, Tamo (b18) 2022; 250 Jiang, Gong, Qin, Zhu (b28) 2022 Fu, Zhang, Li (b54) 2016 Atrey, Hossain, El Saddik, Kankanhalli (b56) 2010; 16 Xu, Chen, Wang, Guo, Yuan (b11) 2019; 148 Che, Tso, Sun, Ip, Lee, Chao, Lau (b8) 2019; 201 Han, Zhao, Leung, Ma, Wang (b25) 2021; 21 Sola, Sevilla (b62) 1997; 44 Yang, Wan, Ng, Zhang, Babu, Zhang, Chen, Dubey (b68) 2018; 170 Dmitrewski, Molina-Solana, Arcucci (b69) 2022; 215 Xing, Yan, Sun, Wang, Wang, Zhao (b60) 2022 Č.ović, Pandžić, Dvorkin (b16) 2022; 211 Tian, Cheng, Lin (b31) 2022; 208 Mba, Meukam, Kemajou (b23) 2016; 121 Elmaz, Eyckerman, Casteels, Latré, Hellinckx (b27) 2021; 206 Ren, Cao (b39) 2019 Park, Kim, Kang, Chung, Choi (b58) 2018 Sun, Chen, Cao, Gao, Xia, Qi, Wu (b5) 2021; 235 Cho, van Merrienboer, Gulcehre, Bahdanau, Bougares, Schwenk, Bengio (b45) 2014 Xu, Wang, Tang (b35) 2019; 237 Xu, Sun, Zhang, Zhao, Lin (b55) 2019; 32 Papadopoulos, Kontokosta, Vlachokostas, Azar (b3) 2019; 155 Heo, Zavala (b19) 2012; 53 Anand, Sekhar, Cheong, Santamouris, Kondepudi (b52) 2019; 204 Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio, Neural Machine Translation by Jointly Learning to Align and Translate, in: 3rd International Conference on Learning Representations, ICLR 2015, 2015. Fang, Crimier, Scanu, Midelet, Alyafi, Delinchant (b33) 2021 Liu, Xu, Zheng, Lin, Wu, Huang, Li (b38) 2021; 206 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b26) 2017; 30 Afroz, Urmee, Shafiullah, Higgins (b9) 2018; 231 Li, Zhang, Zhao, Ren (b6) 2021; 187 Idahosa, Akotey (b2) 2021; 154 Yu, Haghighat, Fung, Yoshino (b17) 2010; 42 Martínez-Comesaña (b20) 2022 Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, Andrew Y. Ng, Multimodal Deep Learning, in: ICML, 2011, pp. 689–696. Xu (10.1016/j.buildenv.2023.110388_b48) 2021; 13 Lamb (10.1016/j.buildenv.2023.110388_b59) 2016; 29 Xu (10.1016/j.buildenv.2023.110388_b55) 2019; 32 Ren (10.1016/j.buildenv.2023.110388_b39) 2019 Han (10.1016/j.buildenv.2023.110388_b25) 2021; 21 Minoli (10.1016/j.buildenv.2023.110388_b43) 2017; 4 10.1016/j.buildenv.2023.110388_b50 Č.ović (10.1016/j.buildenv.2023.110388_b16) 2022; 211 Verma (10.1016/j.buildenv.2023.110388_b40) 2019; 19 Fu (10.1016/j.buildenv.2023.110388_b54) 2016 Li (10.1016/j.buildenv.2023.110388_b6) 2021; 187 Yang (10.1016/j.buildenv.2023.110388_b68) 2018; 170 Masood (10.1016/j.buildenv.2023.110388_b47) 2022; 15 Dey (10.1016/j.buildenv.2023.110388_b53) 2017 Sun (10.1016/j.buildenv.2023.110388_b57) 2022; 222 Wu (10.1016/j.buildenv.2023.110388_b51) 2018; 68 Bergmeir (10.1016/j.buildenv.2023.110388_b64) 2012; 191 Xu (10.1016/j.buildenv.2023.110388_b35) 2019; 237 Elmaz (10.1016/j.buildenv.2023.110388_b27) 2021; 206 Chaudhuri (10.1016/j.buildenv.2023.110388_b7) 2019; 248 Alzubaidi (10.1016/j.buildenv.2023.110388_b30) 2021; 8 Li (10.1016/j.buildenv.2023.110388_b1) 2022; 219 Che (10.1016/j.buildenv.2023.110388_b8) 2019; 201 10.1016/j.buildenv.2023.110388_b46 Liu (10.1016/j.buildenv.2023.110388_b49) 2022 Xing (10.1016/j.buildenv.2023.110388_b60) 2022 Xing (10.1016/j.buildenv.2023.110388_b14) 2018; 174 Anand (10.1016/j.buildenv.2023.110388_b52) 2019; 204 Jung (10.1016/j.buildenv.2023.110388_b4) 2022; 208 Fang (10.1016/j.buildenv.2023.110388_b33) 2021 Heo (10.1016/j.buildenv.2023.110388_b19) 2012; 53 Du (10.1016/j.buildenv.2023.110388_b65) 2021; 281 Monteiro (10.1016/j.buildenv.2023.110388_b13) 2018; 18 Nsangou (10.1016/j.buildenv.2023.110388_b18) 2022; 250 Papadopoulos (10.1016/j.buildenv.2023.110388_b3) 2019; 155 Yang (10.1016/j.buildenv.2023.110388_b66) 2019; 203 Gao (10.1016/j.buildenv.2023.110388_b24) 2021; 301 Atrey (10.1016/j.buildenv.2023.110388_b56) 2010; 16 Dong (10.1016/j.buildenv.2023.110388_b67) 2014; 7 Dong (10.1016/j.buildenv.2023.110388_b21) 2005; 37 Wang (10.1016/j.buildenv.2023.110388_b12) 2020; 263 Sun (10.1016/j.buildenv.2023.110388_b5) 2021; 235 Tian (10.1016/j.buildenv.2023.110388_b31) 2022; 208 Oliveira Panão (10.1016/j.buildenv.2023.110388_b15) 2016; 121 Qian (10.1016/j.buildenv.2023.110388_b36) 2022; 223 Taheri (10.1016/j.buildenv.2023.110388_b37) 2021; 205 Martínez-Comesaña (10.1016/j.buildenv.2023.110388_b20) 2022 Thomas (10.1016/j.buildenv.2023.110388_b22) 2006; 16 Dmitrewski (10.1016/j.buildenv.2023.110388_b69) 2022; 215 Cho (10.1016/j.buildenv.2023.110388_b45) 2014 Arlot (10.1016/j.buildenv.2023.110388_b63) 2010; 4 Mba (10.1016/j.buildenv.2023.110388_b23) 2016; 121 Yu (10.1016/j.buildenv.2023.110388_b17) 2010; 42 Sun (10.1016/j.buildenv.2023.110388_b44) 2020; 216 Sun (10.1016/j.buildenv.2023.110388_b61) 2022; 254 Liu (10.1016/j.buildenv.2023.110388_b38) 2021; 206 Idahosa (10.1016/j.buildenv.2023.110388_b2) 2021; 154 Jiang (10.1016/j.buildenv.2023.110388_b28) 2022 Gao (10.1016/j.buildenv.2023.110388_b29) 2021; 252 Vaswani (10.1016/j.buildenv.2023.110388_b26) 2017; 30 Plageras (10.1016/j.buildenv.2023.110388_b42) 2018; 82 Magalhães (10.1016/j.buildenv.2023.110388_b10) 2017; 151 Zhou (10.1016/j.buildenv.2023.110388_b32) 2022; 215 Al Dakheel (10.1016/j.buildenv.2023.110388_b41) 2020; 61 Xu (10.1016/j.buildenv.2023.110388_b11) 2019; 148 Xue (10.1016/j.buildenv.2023.110388_b34) 2019; 12 Park (10.1016/j.buildenv.2023.110388_b58) 2018 Afroz (10.1016/j.buildenv.2023.110388_b9) 2018; 231 Du (10.1016/j.buildenv.2023.110388_b70) 2019 Sola (10.1016/j.buildenv.2023.110388_b62) 1997; 44 |
| References_xml | – start-page: 1672 year: 2018 end-page: 1678 ident: b58 article-title: Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture publication-title: 2018 IEEE Intelligent Vehicles Symposium – volume: 82 start-page: 349 year: 2018 end-page: 357 ident: b42 article-title: Efficient IoT-based sensor BIG data collection–processing and analysis in smart buildings publication-title: Future Gener. Comput. Syst. – reference: Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, Andrew Y. Ng, Multimodal Deep Learning, in: ICML, 2011, pp. 689–696. – start-page: 21 year: 2021 ident: b33 article-title: Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model publication-title: Energy Build. – volume: 53 start-page: 7 year: 2012 end-page: 18 ident: b19 article-title: Gaussian process modeling for measurement and verification of building energy savings publication-title: Energy Build. – volume: 252 year: 2021 ident: b29 article-title: Interpretable deep learning model for building energy consumption prediction based on attention mechanism publication-title: Energy Build. – volume: 208 year: 2022 ident: b31 article-title: Modelling indoor environment indicators using artificial neural network in the stratified environments publication-title: Build. Environ. – volume: 151 start-page: 332 year: 2017 end-page: 343 ident: b10 article-title: Modelling the relationship between heating energy use and indoor temperatures in residential buildings through artificial neural networks considering occupant behavior publication-title: Energy Build. – volume: 208 year: 2022 ident: b4 article-title: Occupant-centered real-time control of indoor temperature using deep learning algorithms publication-title: Build. Environ. – reference: Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio, Neural Machine Translation by Jointly Learning to Align and Translate, in: 3rd International Conference on Learning Representations, ICLR 2015, 2015. – volume: 32 year: 2019 ident: b55 article-title: Understanding and improving layer normalization publication-title: Advances in Neural Information Processing Systems – volume: 263 year: 2020 ident: b12 article-title: Building thermal load prediction through shallow machine learning and deep learning publication-title: Appl. Energy – start-page: 17 year: 2019 ident: b39 article-title: Development and application of linear ventilation and temperature models for indoor environmental prediction and HVAC systems control publication-title: Sustainable Cities Soc. – start-page: 12 year: 2022 ident: b20 article-title: Optimisation of thermal comfort and indoor air quality estimations applied to in-use buildings combining NSGA-III and XGBoost publication-title: Sustainable Cities Soc. – volume: 121 start-page: 32 year: 2016 end-page: 42 ident: b23 article-title: Application of artificial neural network for predicting hourly indoor air temperature and relative humidity in modern building in humid region publication-title: Energy Build. – volume: 16 start-page: 81 year: 2006 end-page: 89 ident: b22 article-title: Artificial neural network models for indoor temperature prediction: Investigations in two buildings publication-title: Neural Comput. Appl. – volume: 281 year: 2021 ident: b65 article-title: Intelligent multi-zone residential HVAC control strategy based on deep reinforcement learning publication-title: Appl. Energy – volume: 222 year: 2022 ident: b57 article-title: MPSN: Motion-aware pseudo-siamese network for indoor video head detection in buildings publication-title: Build. Environ. – volume: 206 year: 2021 ident: b27 article-title: CNN-LSTM architecture for predictive indoor temperature modeling publication-title: Build. Environ. – start-page: 324 year: 2016 end-page: 328 ident: b54 article-title: Using LSTM and GRU neural network methods for traffic flow prediction publication-title: 2016 31st Youth Academic Annual Conference of Chinese Association of Automation – volume: 187 year: 2021 ident: b6 article-title: Experimental study of an indoor temperature fuzzy control method for thermal comfort and energy saving using wristband device publication-title: Build. Environ. – volume: 12 start-page: 2122 year: 2019 ident: b34 article-title: District heating load prediction algorithm based on feature fusion LSTM model publication-title: Energies – volume: 21 start-page: 7833 year: 2021 end-page: 7848 ident: b25 article-title: A review of deep learning models for time series prediction publication-title: IEEE Sens. J. – volume: 61 year: 2020 ident: b41 article-title: Smart buildings features and key performance indicators: A review publication-title: Sustainable Cities Soc. – volume: 4 start-page: 269 year: 2017 end-page: 283 ident: b43 article-title: IoT considerations, requirements, and architectures for smart buildings—energy optimization and next-generation building management systems publication-title: IEEE Internet Things J. – volume: 68 start-page: 13 year: 2018 end-page: 23 ident: b51 article-title: Multi-sensor information fusion for remaining useful life prediction of machining tools by adaptive network based fuzzy inference system publication-title: Appl. Soft Comput. – volume: 4 start-page: 40 year: 2010 end-page: 79 ident: b63 article-title: A survey of cross-validation procedures for model selection publication-title: Stat. Surv. – volume: 203 year: 2019 ident: b66 article-title: Experimental study of a model predictive control system for active chilled beam (ACB) air-conditioning system publication-title: Energy Build. – volume: 174 start-page: 134 year: 2018 end-page: 146 ident: b14 article-title: An identification method for room temperature dynamic model based on analytical solution in VAV system publication-title: Energy Build. – year: 2022 ident: b28 article-title: Attention-LSTM architecture combined with Bayesian hyperparameter optimization for indoor temperature prediction publication-title: Build. Environ. – volume: 8 start-page: 53 year: 2021 ident: b30 article-title: Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions publication-title: J. Big Data – volume: 237 start-page: 180 year: 2019 end-page: 195 ident: b35 article-title: Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load publication-title: Appl. Energy – volume: 18 start-page: 3610 year: 2018 ident: b13 article-title: Indoor temperature prediction in an IoT scenario publication-title: Sensors – volume: 16 start-page: 345 year: 2010 end-page: 379 ident: b56 article-title: Multimodal fusion for multimedia analysis: A survey publication-title: Multimedia Syst. – volume: 219 year: 2022 ident: b1 article-title: A strategy of improving indoor air temperature prediction in HVAC system based on multivariate transfer entropy publication-title: Build. Environ. – volume: 148 start-page: 128 year: 2019 end-page: 135 ident: b11 article-title: Improving prediction performance for indoor temperature in public buildings based on a novel deep learning method publication-title: Build. Environ. – volume: 30 start-page: 11 year: 2017 ident: b26 article-title: Attention is all you need publication-title: 31st Conference on Neural Information Processing Systems – volume: 191 start-page: 192 year: 2012 end-page: 213 ident: b64 article-title: On the use of cross-validation for time series predictor evaluation publication-title: Inform. Sci. – volume: 7 start-page: 89 year: 2014 end-page: 106 ident: b67 article-title: A real-time model predictive control for building heating and cooling systems based on the occupancy behavior pattern detection and local weather forecasting publication-title: Build. Simul. – volume: 13 start-page: 1031 year: 2021 ident: b48 article-title: FM-GRU: A time series prediction method for water quality based on seq2seq framework publication-title: Water – volume: 29 year: 2016 ident: b59 article-title: Professor forcing: A new algorithm for training recurrent networks publication-title: Advances in Neural Information Processing Systems – volume: 254 year: 2022 ident: b61 article-title: Indoor occupancy measurement by the fusion of motion detection and static estimation publication-title: Energy and Buildings – volume: 154 year: 2021 ident: b2 article-title: A social constructionist approach to managing HVAC energy consumption using social norms – a randomised field experiment publication-title: Energy Policy – volume: 205 year: 2021 ident: b37 article-title: Learning-based CO2 concentration prediction: Application to indoor air quality control using demand-controlled ventilation publication-title: Build. Environ. – start-page: 1597 year: 2017 end-page: 1600 ident: b53 article-title: Gate-variants of gated recurrent unit (GRU) neural networks publication-title: 2017 IEEE 60th International Midwest Symposium on Circuits and Systems – volume: 223 year: 2022 ident: b36 article-title: Improving indoor air flow and temperature prediction with local measurements based on CFD-EnKF data assimilation publication-title: Build. Environ. – volume: 170 start-page: 25 year: 2018 end-page: 39 ident: b68 article-title: A state-space thermal model incorporating humidity and thermal comfort for model predictive control in buildings publication-title: Energy Build. – start-page: 1696 year: 2019 end-page: 1705 ident: b70 article-title: Task-agnostic dynamics priors for deep reinforcement learning publication-title: International Conference on Machine Learning – volume: 44 start-page: 1464 year: 1997 end-page: 1468 ident: b62 article-title: Importance of input data normalization for the application of neural networks to complex industrial problems publication-title: IEEE Trans. Nucl. Sci. – volume: 155 start-page: 350 year: 2019 end-page: 359 ident: b3 article-title: Rethinking HVAC temperature setpoints in commercial buildings: The potential for zero-cost energy savings and comfort improvement in different climates publication-title: Build. Environ. – volume: 250 year: 2022 ident: b18 article-title: Explaining household electricity consumption using quantile regression, decision tree and artificial neural network publication-title: Energy – volume: 215 year: 2022 ident: b32 article-title: Real-time prediction of indoor humidity with limited sensors using cross-sample learning publication-title: Build. Environ. – year: 2022 ident: b49 article-title: Integrating machine learning and mathematical optimization for job shop scheduling – volume: 37 start-page: 545 year: 2005 end-page: 553 ident: b21 article-title: Applying support vector machines to predict building energy consumption in tropical region publication-title: Energy Build. – volume: 206 year: 2021 ident: b38 article-title: Thermal preference prediction based on occupants’ adaptive behavior in indoor environments- a study of an air-conditioned multi-occupancy office in China publication-title: Build. Environ. – volume: 201 start-page: 202 year: 2019 end-page: 215 ident: b8 article-title: Energy consumption, indoor thermal comfort and air quality in a commercial office with retrofitted heat, ventilation and air conditioning (HVAC) system publication-title: Energy Build. – volume: 301 year: 2021 ident: b24 article-title: Comparing deep learning models for multi energy vectors prediction on multiple types of building publication-title: Appl. Energy – volume: 211 year: 2022 ident: b16 article-title: Learning indoor temperature predictions for optimal load ensemble control publication-title: Electr. Power Syst. Res. – volume: 204 year: 2019 ident: b52 article-title: Occupancy-based zone-level VAV system control implications on thermal comfort, ventilation, indoor air quality and building energy efficiency publication-title: Energy Build. – volume: 216 year: 2020 ident: b44 article-title: A review of building occupancy measurement systems publication-title: Energy Build. – year: 2022 ident: b60 article-title: Honeycomb: An open-source distributed system for smart buildings publication-title: Patterns – volume: 248 start-page: 44 year: 2019 end-page: 53 ident: b7 article-title: A feedforward neural network based indoor-climate control framework for thermal comfort and energy saving in buildings publication-title: Appl. Energy – volume: 231 start-page: 29 year: 2018 end-page: 53 ident: b9 article-title: Real-time prediction model for indoor temperature in a commercial building publication-title: Appl. Energy – volume: 19 start-page: 9036 year: 2019 end-page: 9046 ident: b40 article-title: Sensing, controlling, and IoT infrastructure in smart building: A review publication-title: IEEE Sens. J. – volume: 215 year: 2022 ident: b69 article-title: Cntrlda: A building energy management control system with real-time adjustments. Application to indoor temperature publication-title: Build. Environ. – volume: 235 year: 2021 ident: b5 article-title: A dynamic control strategy of district heating substations based on online prediction and indoor temperature feedback publication-title: Energy – volume: 15 start-page: 2623 year: 2022 ident: b47 article-title: A multi-step time-series clustering-based Seq2Seq LSTM learning for a single household electricity load forecasting publication-title: Energies – volume: 42 start-page: 1637 year: 2010 end-page: 1646 ident: b17 article-title: A decision tree method for building energy demand modeling publication-title: Energy Build. – volume: 121 start-page: 92 year: 2016 end-page: 103 ident: b15 article-title: Validation of a lumped RC model for thermal simulation of a double skin natural and mechanical ventilated test cell publication-title: Energy Build. – start-page: 1724 year: 2014 end-page: 1734 ident: b45 article-title: Learning phrase representations using RNN encoder–decoder for statistical machine translation publication-title: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing – volume: 29 year: 2016 ident: 10.1016/j.buildenv.2023.110388_b59 article-title: Professor forcing: A new algorithm for training recurrent networks – volume: 13 start-page: 1031 issue: 8 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b48 article-title: FM-GRU: A time series prediction method for water quality based on seq2seq framework publication-title: Water doi: 10.3390/w13081031 – volume: 231 start-page: 29 year: 2018 ident: 10.1016/j.buildenv.2023.110388_b9 article-title: Real-time prediction model for indoor temperature in a commercial building publication-title: Appl. Energy doi: 10.1016/j.apenergy.2018.09.052 – volume: 174 start-page: 134 year: 2018 ident: 10.1016/j.buildenv.2023.110388_b14 article-title: An identification method for room temperature dynamic model based on analytical solution in VAV system publication-title: Energy Build. doi: 10.1016/j.enbuild.2018.06.039 – volume: 216 year: 2020 ident: 10.1016/j.buildenv.2023.110388_b44 article-title: A review of building occupancy measurement systems publication-title: Energy Build. doi: 10.1016/j.enbuild.2020.109965 – volume: 222 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b57 article-title: MPSN: Motion-aware pseudo-siamese network for indoor video head detection in buildings publication-title: Build. Environ. doi: 10.1016/j.buildenv.2022.109354 – volume: 219 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b1 article-title: A strategy of improving indoor air temperature prediction in HVAC system based on multivariate transfer entropy publication-title: Build. Environ. doi: 10.1016/j.buildenv.2022.109164 – volume: 211 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b16 article-title: Learning indoor temperature predictions for optimal load ensemble control publication-title: Electr. Power Syst. Res. – year: 2022 ident: 10.1016/j.buildenv.2023.110388_b49 – volume: 121 start-page: 32 year: 2016 ident: 10.1016/j.buildenv.2023.110388_b23 article-title: Application of artificial neural network for predicting hourly indoor air temperature and relative humidity in modern building in humid region publication-title: Energy Build. doi: 10.1016/j.enbuild.2016.03.046 – volume: 16 start-page: 81 issue: 1 year: 2006 ident: 10.1016/j.buildenv.2023.110388_b22 article-title: Artificial neural network models for indoor temperature prediction: Investigations in two buildings publication-title: Neural Comput. Appl. doi: 10.1007/s00521-006-0047-9 – start-page: 12 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b20 article-title: Optimisation of thermal comfort and indoor air quality estimations applied to in-use buildings combining NSGA-III and XGBoost publication-title: Sustainable Cities Soc. – ident: 10.1016/j.buildenv.2023.110388_b50 – volume: 21 start-page: 7833 issue: 6 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b25 article-title: A review of deep learning models for time series prediction publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2019.2923982 – volume: 15 start-page: 2623 issue: 7 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b47 article-title: A multi-step time-series clustering-based Seq2Seq LSTM learning for a single household electricity load forecasting publication-title: Energies doi: 10.3390/en15072623 – volume: 7 start-page: 89 issue: 1 year: 2014 ident: 10.1016/j.buildenv.2023.110388_b67 article-title: A real-time model predictive control for building heating and cooling systems based on the occupancy behavior pattern detection and local weather forecasting publication-title: Build. Simul. doi: 10.1007/s12273-013-0142-7 – volume: 121 start-page: 92 year: 2016 ident: 10.1016/j.buildenv.2023.110388_b15 article-title: Validation of a lumped RC model for thermal simulation of a double skin natural and mechanical ventilated test cell publication-title: Energy Build. doi: 10.1016/j.enbuild.2016.03.054 – volume: 208 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b4 article-title: Occupant-centered real-time control of indoor temperature using deep learning algorithms publication-title: Build. Environ. doi: 10.1016/j.buildenv.2021.108633 – volume: 248 start-page: 44 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b7 article-title: A feedforward neural network based indoor-climate control framework for thermal comfort and energy saving in buildings publication-title: Appl. Energy doi: 10.1016/j.apenergy.2019.04.065 – volume: 37 start-page: 545 issue: 5 year: 2005 ident: 10.1016/j.buildenv.2023.110388_b21 article-title: Applying support vector machines to predict building energy consumption in tropical region publication-title: Energy Build. doi: 10.1016/j.enbuild.2004.09.009 – volume: 61 year: 2020 ident: 10.1016/j.buildenv.2023.110388_b41 article-title: Smart buildings features and key performance indicators: A review publication-title: Sustainable Cities Soc. doi: 10.1016/j.scs.2020.102328 – volume: 151 start-page: 332 year: 2017 ident: 10.1016/j.buildenv.2023.110388_b10 article-title: Modelling the relationship between heating energy use and indoor temperatures in residential buildings through artificial neural networks considering occupant behavior publication-title: Energy Build. doi: 10.1016/j.enbuild.2017.06.076 – volume: 155 start-page: 350 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b3 article-title: Rethinking HVAC temperature setpoints in commercial buildings: The potential for zero-cost energy savings and comfort improvement in different climates publication-title: Build. Environ. doi: 10.1016/j.buildenv.2019.03.062 – volume: 205 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b37 article-title: Learning-based CO2 concentration prediction: Application to indoor air quality control using demand-controlled ventilation publication-title: Build. Environ. doi: 10.1016/j.buildenv.2021.108164 – start-page: 1724 year: 2014 ident: 10.1016/j.buildenv.2023.110388_b45 article-title: Learning phrase representations using RNN encoder–decoder for statistical machine translation – volume: 215 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b69 article-title: Cntrlda: A building energy management control system with real-time adjustments. Application to indoor temperature publication-title: Build. Environ. doi: 10.1016/j.buildenv.2022.108938 – volume: 204 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b52 article-title: Occupancy-based zone-level VAV system control implications on thermal comfort, ventilation, indoor air quality and building energy efficiency publication-title: Energy Build. doi: 10.1016/j.enbuild.2019.109473 – volume: 30 start-page: 11 year: 2017 ident: 10.1016/j.buildenv.2023.110388_b26 article-title: Attention is all you need – volume: 32 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b55 article-title: Understanding and improving layer normalization – year: 2022 ident: 10.1016/j.buildenv.2023.110388_b60 article-title: Honeycomb: An open-source distributed system for smart buildings publication-title: Patterns doi: 10.1016/j.patter.2022.100605 – volume: 44 start-page: 1464 issue: 3 year: 1997 ident: 10.1016/j.buildenv.2023.110388_b62 article-title: Importance of input data normalization for the application of neural networks to complex industrial problems publication-title: IEEE Trans. Nucl. Sci. doi: 10.1109/23.589532 – start-page: 324 year: 2016 ident: 10.1016/j.buildenv.2023.110388_b54 article-title: Using LSTM and GRU neural network methods for traffic flow prediction – volume: 191 start-page: 192 year: 2012 ident: 10.1016/j.buildenv.2023.110388_b64 article-title: On the use of cross-validation for time series predictor evaluation publication-title: Inform. Sci. doi: 10.1016/j.ins.2011.12.028 – volume: 208 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b31 article-title: Modelling indoor environment indicators using artificial neural network in the stratified environments publication-title: Build. Environ. doi: 10.1016/j.buildenv.2021.108581 – volume: 252 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b29 article-title: Interpretable deep learning model for building energy consumption prediction based on attention mechanism publication-title: Energy Build. doi: 10.1016/j.enbuild.2021.111379 – volume: 42 start-page: 1637 issue: 10 year: 2010 ident: 10.1016/j.buildenv.2023.110388_b17 article-title: A decision tree method for building energy demand modeling publication-title: Energy Build. doi: 10.1016/j.enbuild.2010.04.006 – volume: 16 start-page: 345 issue: 6 year: 2010 ident: 10.1016/j.buildenv.2023.110388_b56 article-title: Multimodal fusion for multimedia analysis: A survey publication-title: Multimedia Syst. doi: 10.1007/s00530-010-0182-0 – volume: 8 start-page: 53 issue: 1 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b30 article-title: Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions publication-title: J. Big Data doi: 10.1186/s40537-021-00444-8 – volume: 12 start-page: 2122 issue: 11 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b34 article-title: District heating load prediction algorithm based on feature fusion LSTM model publication-title: Energies doi: 10.3390/en12112122 – volume: 53 start-page: 7 year: 2012 ident: 10.1016/j.buildenv.2023.110388_b19 article-title: Gaussian process modeling for measurement and verification of building energy savings publication-title: Energy Build. doi: 10.1016/j.enbuild.2012.06.024 – volume: 235 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b5 article-title: A dynamic control strategy of district heating substations based on online prediction and indoor temperature feedback publication-title: Energy doi: 10.1016/j.energy.2021.121228 – start-page: 1672 year: 2018 ident: 10.1016/j.buildenv.2023.110388_b58 article-title: Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture – ident: 10.1016/j.buildenv.2023.110388_b46 – volume: 18 start-page: 3610 issue: 11 year: 2018 ident: 10.1016/j.buildenv.2023.110388_b13 article-title: Indoor temperature prediction in an IoT scenario publication-title: Sensors doi: 10.3390/s18113610 – volume: 203 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b66 article-title: Experimental study of a model predictive control system for active chilled beam (ACB) air-conditioning system publication-title: Energy Build. doi: 10.1016/j.enbuild.2019.109451 – volume: 82 start-page: 349 year: 2018 ident: 10.1016/j.buildenv.2023.110388_b42 article-title: Efficient IoT-based sensor BIG data collection–processing and analysis in smart buildings publication-title: Future Gener. Comput. Syst. doi: 10.1016/j.future.2017.09.082 – volume: 170 start-page: 25 year: 2018 ident: 10.1016/j.buildenv.2023.110388_b68 article-title: A state-space thermal model incorporating humidity and thermal comfort for model predictive control in buildings publication-title: Energy Build. doi: 10.1016/j.enbuild.2018.03.082 – volume: 206 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b27 article-title: CNN-LSTM architecture for predictive indoor temperature modeling publication-title: Build. Environ. doi: 10.1016/j.buildenv.2021.108327 – volume: 4 start-page: 40 year: 2010 ident: 10.1016/j.buildenv.2023.110388_b63 article-title: A survey of cross-validation procedures for model selection publication-title: Stat. Surv. doi: 10.1214/09-SS054 – volume: 4 start-page: 269 issue: 1 year: 2017 ident: 10.1016/j.buildenv.2023.110388_b43 article-title: IoT considerations, requirements, and architectures for smart buildings—energy optimization and next-generation building management systems publication-title: IEEE Internet Things J. doi: 10.1109/JIOT.2017.2647881 – volume: 250 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b18 article-title: Explaining household electricity consumption using quantile regression, decision tree and artificial neural network publication-title: Energy doi: 10.1016/j.energy.2022.123856 – start-page: 21 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b33 article-title: Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model publication-title: Energy Build. – volume: 68 start-page: 13 year: 2018 ident: 10.1016/j.buildenv.2023.110388_b51 article-title: Multi-sensor information fusion for remaining useful life prediction of machining tools by adaptive network based fuzzy inference system publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2018.03.043 – volume: 187 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b6 article-title: Experimental study of an indoor temperature fuzzy control method for thermal comfort and energy saving using wristband device publication-title: Build. Environ. doi: 10.1016/j.buildenv.2020.107432 – volume: 263 year: 2020 ident: 10.1016/j.buildenv.2023.110388_b12 article-title: Building thermal load prediction through shallow machine learning and deep learning publication-title: Appl. Energy doi: 10.1016/j.apenergy.2020.114683 – volume: 301 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b24 article-title: Comparing deep learning models for multi energy vectors prediction on multiple types of building publication-title: Appl. Energy doi: 10.1016/j.apenergy.2021.117486 – volume: 19 start-page: 9036 issue: 20 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b40 article-title: Sensing, controlling, and IoT infrastructure in smart building: A review publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2019.2922409 – volume: 201 start-page: 202 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b8 article-title: Energy consumption, indoor thermal comfort and air quality in a commercial office with retrofitted heat, ventilation and air conditioning (HVAC) system publication-title: Energy Build. doi: 10.1016/j.enbuild.2019.06.029 – start-page: 1597 year: 2017 ident: 10.1016/j.buildenv.2023.110388_b53 article-title: Gate-variants of gated recurrent unit (GRU) neural networks – volume: 215 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b32 article-title: Real-time prediction of indoor humidity with limited sensors using cross-sample learning publication-title: Build. Environ. doi: 10.1016/j.buildenv.2022.108964 – volume: 223 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b36 article-title: Improving indoor air flow and temperature prediction with local measurements based on CFD-EnKF data assimilation publication-title: Build. Environ. doi: 10.1016/j.buildenv.2022.109511 – volume: 206 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b38 article-title: Thermal preference prediction based on occupants’ adaptive behavior in indoor environments- a study of an air-conditioned multi-occupancy office in China publication-title: Build. Environ. doi: 10.1016/j.buildenv.2021.108355 – volume: 154 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b2 article-title: A social constructionist approach to managing HVAC energy consumption using social norms – a randomised field experiment publication-title: Energy Policy doi: 10.1016/j.enpol.2021.112293 – volume: 148 start-page: 128 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b11 article-title: Improving prediction performance for indoor temperature in public buildings based on a novel deep learning method publication-title: Build. Environ. doi: 10.1016/j.buildenv.2018.10.062 – volume: 237 start-page: 180 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b35 article-title: Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load publication-title: Appl. Energy doi: 10.1016/j.apenergy.2019.01.022 – start-page: 17 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b39 article-title: Development and application of linear ventilation and temperature models for indoor environmental prediction and HVAC systems control publication-title: Sustainable Cities Soc. – start-page: 1696 year: 2019 ident: 10.1016/j.buildenv.2023.110388_b70 article-title: Task-agnostic dynamics priors for deep reinforcement learning – volume: 254 year: 2022 ident: 10.1016/j.buildenv.2023.110388_b61 article-title: Indoor occupancy measurement by the fusion of motion detection and static estimation publication-title: Energy and Buildings doi: 10.1016/j.enbuild.2021.111593 – volume: 281 year: 2021 ident: 10.1016/j.buildenv.2023.110388_b65 article-title: Intelligent multi-zone residential HVAC control strategy based on deep reinforcement learning publication-title: Appl. Energy doi: 10.1016/j.apenergy.2020.116117 – year: 2022 ident: 10.1016/j.buildenv.2023.110388_b28 article-title: Attention-LSTM architecture combined with Bayesian hyperparameter optimization for indoor temperature prediction publication-title: Build. Environ. doi: 10.1016/j.buildenv.2022.109536 |
| SSID | ssj0016934 |
| Score | 2.465332 |
| Snippet | Indoor temperature prediction is an essential component of building control and energy saving. Although existing indoor temperature prediction frameworks have... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 110388 |
| SubjectTerms | Encoder–decoder architecture Gated recurrent unit network Information fusion Multi-zone temperature prediction Multiple sensor information |
| Title | MITP-Net: A deep-learning framework for short-term indoor temperature predictions in multi-zone buildings |
| URI | https://dx.doi.org/10.1016/j.buildenv.2023.110388 |
| Volume | 239 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect database customDbUrl: eissn: 1873-684X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0016934 issn: 0360-1323 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT-MwELagcIDDanmsYF_ygRsytLYbJ3urViDgULGih94i23FEUBUq2iK0v37HrzRlkQCtVqqiyonrxvNlMh7PfIPQUcZLW1M7IRJeX4RLo4jU3ZJIWvaE7iaWBs0VmxDDYToeZ3FHd-bKCYi6Tp-esul_FTW0gbBt6uw7xN38KDTAdxA6HEHscHyT4EEZXZOh8S6_48KYKZlE_0cZQ7FcdOHsFmxvYnXzMazM7228oQEr2rMsW_aAotJNqLmLPCS_78EoVaGU9mxlRzg0ut2IVvpclOg4FE8ZtfB4s6h9REc1kVXLhe3ct7-su-V2Ea4OjgnKmiDW4C2LGTPL8CSfpdUlsAL2Ss14pZsKRpLUR2pGrUw9x9FfGt47G-5O3K3C3ZzYoW0yA_PlAZ-xZ9_YAe141FGL9dN1tEFFPwMFuDG4PBtfNVtOScYC15j_g6108pdHe9mSaVkno4_oQ1hW4IGHww5aM_Uu2m6RTe6hKgLjBx7gFVjgBhYYYIGXsMAeFrgFC9yCBZzGS1jgBhb7aHR-Nvp5QUKhDaIpFXNSgIGScMFhdVloMPlUagk8aFEWXEjTzZSWGk5yBR9eCqqZStK0VyZGFfB-Yp9Qp4ZxDhCGNiVd2XowDRUtZV_1WEGZMZwpKfgh6sc5y3Ugobe1UCZ5jDa8y-Nc53aucz_Xh-i06Tf1NCyv9siiSPJgTHojMQckvdL38z_0_YK2lg_DV9SZPyzMN7SpH-fV7OF7AN0futyfOg |
| 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=MITP-Net%3A+A+deep-learning+framework+for+short-term+indoor+temperature+predictions+in+multi-zone+buildings&rft.jtitle=Building+and+environment&rft.au=Xing%2C+Tian&rft.au=Sun%2C+Kailai&rft.au=Zhao%2C+Qianchuan&rft.date=2023-07-01&rft.pub=Elsevier+Ltd&rft.issn=0360-1323&rft.eissn=1873-684X&rft.volume=239&rft_id=info:doi/10.1016%2Fj.buildenv.2023.110388&rft.externalDocID=S0360132323004158 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-1323&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-1323&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-1323&client=summon |