A hybrid prediction model of improved bidirectional long short-term memory network for cooling load based on PCANet and attention mechanism
Accurate and reliable cooling load forecasting is a prerequisite for air-conditioning system control and the basis for building-side energy management. Therefore, a hybrid prediction model of an improved bidirectional long short-term memory (BiLSTM) network based on principal component analysis netw...
Uloženo v:
| Vydáno v: | Energy (Oxford) Ročník 292; s. 130388 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.04.2024
|
| Témata: | |
| ISSN: | 0360-5442 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Accurate and reliable cooling load forecasting is a prerequisite for air-conditioning system control and the basis for building-side energy management. Therefore, a hybrid prediction model of an improved bidirectional long short-term memory (BiLSTM) network based on principal component analysis network (PCANet) and attention mechanism (CNN-IBiLSTM-Attention) is proposed to predict the cooling load of large commercial buildings. First of all, the PCANet algorithm is used to analyze the sensitivity of the influencing factors. Then, the hybrid strategy improved whale optimization algorithm (HSIWOA) is used to optimize the hyperparameter of BiLSTM. At last, the performance of the proposed algorithm is verified by using the actual data of two commercial buildings in Xi'an. The results show that using the PCANet algorithm for sensitivity analysis avoids feature redundancy. HSIWOA is suitable for hyperparameter optimization of BiLSTM. Compared with the other three prediction models, CNN-IBiLSTM-Attention reduced the mean absolute percentage error (MAPE) of Building 1 and 2 test sets by 31.55 %, 55.59 %, and 60.58 % and 56.49 %, 60.3 %, and 67.37 %, respectively. The proposed prediction model has superior hyperparameter optimization ability, better model complexity, and stronger generalization ability. Therefore, the proposed prediction model becomes a reliable tool for predicting the cooling load of large commercial buildings.
•Comprehensive classification of factors affecting commercial building cooling load.•Feature extraction method based on the PCANet algorithm.•Combining PCANet, BiLSTM, and attention mechanism for cooling load forecasting.•Using the HSIWOA to optimize the hyperparameters of BiLSTM.•Verifying the validity of the CNN-IBiLSTM-Attention model using actual data. |
|---|---|
| AbstractList | Accurate and reliable cooling load forecasting is a prerequisite for air-conditioning system control and the basis for building-side energy management. Therefore, a hybrid prediction model of an improved bidirectional long short-term memory (BiLSTM) network based on principal component analysis network (PCANet) and attention mechanism (CNN-IBiLSTM-Attention) is proposed to predict the cooling load of large commercial buildings. First of all, the PCANet algorithm is used to analyze the sensitivity of the influencing factors. Then, the hybrid strategy improved whale optimization algorithm (HSIWOA) is used to optimize the hyperparameter of BiLSTM. At last, the performance of the proposed algorithm is verified by using the actual data of two commercial buildings in Xi'an. The results show that using the PCANet algorithm for sensitivity analysis avoids feature redundancy. HSIWOA is suitable for hyperparameter optimization of BiLSTM. Compared with the other three prediction models, CNN-IBiLSTM-Attention reduced the mean absolute percentage error (MAPE) of Building 1 and 2 test sets by 31.55 %, 55.59 %, and 60.58 % and 56.49 %, 60.3 %, and 67.37 %, respectively. The proposed prediction model has superior hyperparameter optimization ability, better model complexity, and stronger generalization ability. Therefore, the proposed prediction model becomes a reliable tool for predicting the cooling load of large commercial buildings. Accurate and reliable cooling load forecasting is a prerequisite for air-conditioning system control and the basis for building-side energy management. Therefore, a hybrid prediction model of an improved bidirectional long short-term memory (BiLSTM) network based on principal component analysis network (PCANet) and attention mechanism (CNN-IBiLSTM-Attention) is proposed to predict the cooling load of large commercial buildings. First of all, the PCANet algorithm is used to analyze the sensitivity of the influencing factors. Then, the hybrid strategy improved whale optimization algorithm (HSIWOA) is used to optimize the hyperparameter of BiLSTM. At last, the performance of the proposed algorithm is verified by using the actual data of two commercial buildings in Xi'an. The results show that using the PCANet algorithm for sensitivity analysis avoids feature redundancy. HSIWOA is suitable for hyperparameter optimization of BiLSTM. Compared with the other three prediction models, CNN-IBiLSTM-Attention reduced the mean absolute percentage error (MAPE) of Building 1 and 2 test sets by 31.55 %, 55.59 %, and 60.58 % and 56.49 %, 60.3 %, and 67.37 %, respectively. The proposed prediction model has superior hyperparameter optimization ability, better model complexity, and stronger generalization ability. Therefore, the proposed prediction model becomes a reliable tool for predicting the cooling load of large commercial buildings. •Comprehensive classification of factors affecting commercial building cooling load.•Feature extraction method based on the PCANet algorithm.•Combining PCANet, BiLSTM, and attention mechanism for cooling load forecasting.•Using the HSIWOA to optimize the hyperparameters of BiLSTM.•Verifying the validity of the CNN-IBiLSTM-Attention model using actual data. |
| ArticleNumber | 130388 |
| Author | Sun, Hang Meng, Qinglong Ji, Xingxing Yan, Xiuying Lei, Yu |
| Author_xml | – sequence: 1 givenname: Xiuying surname: Yan fullname: Yan, Xiuying organization: School of Building Services Science and Engineering, Xi'an University of Architecture and Technology, Xi'an, 710055, China – sequence: 2 givenname: Xingxing surname: Ji fullname: Ji, Xingxing organization: School of Building Services Science and Engineering, Xi'an University of Architecture and Technology, Xi'an, 710055, China – sequence: 3 givenname: Qinglong surname: Meng fullname: Meng, Qinglong email: mengqinglong@chd.edu.cn organization: School of Civil Engineering, Chang'an University, Xi'an, 710061, China – sequence: 4 givenname: Hang surname: Sun fullname: Sun, Hang organization: China Construction Third Engineering Bureau Installation Engineering Co. Ltd, Wuhan, 430040, China – sequence: 5 givenname: Yu surname: Lei fullname: Lei, Yu organization: China Construction Third Engineering Bureau Installation Engineering Co. Ltd, Wuhan, 430040, China |
| BookMark | eNqFkb1OwzAURj0UiRZ4AwaPLCl27aQJA1JV8SdVwACz5Tg3rYtjF9st6jPw0riEiQHkwYO_813d4xEaWGcBoXNKxpTQ4nI9Bgt-uR9PyISPKSOsLAdoSFhBspzzyTEahbAmhORlVQ3R5wyv9rXXDd54aLSK2lncuQYMdi3W3ca7HTS41o328P0qDTbOLnFYOR-zCL7DHXTO77GF-OH8G26dx8o5o1PKOJloGVJHKn6ezx4hYmkbLGME208DtZJWh-4UHbXSBDj7uU_Q6-3Ny_w-WzzdPcxni0wxVsWsqIHLKdQlkbIsWkJpS6li01oWFbBasZKSuiCVLA4KWspUOmWjOCkZAM_ZCbroe9Ny71sIUXQ6KDBGWnDbIBjNWZ5POeMpyvuo8i4ED63YeN1JvxeUiINvsRa9b3EYJnrfCbv6hSkd5WHb6KU2_8HXPQzJwU6DF0FpsAr6LxCN038XfAFkj6UO |
| CitedBy_id | crossref_primary_10_1016_j_ress_2025_111377 crossref_primary_10_1007_s12145_024_01524_y crossref_primary_10_1016_j_ijrefrig_2025_05_011 crossref_primary_10_1016_j_rineng_2024_103765 crossref_primary_10_1016_j_rineng_2025_105800 crossref_primary_10_1016_j_ijdrr_2024_105003 crossref_primary_10_1016_j_jobe_2025_113777 crossref_primary_10_1080_10589759_2025_2470340 crossref_primary_10_3390_su16062522 crossref_primary_10_1016_j_renene_2025_122629 crossref_primary_10_1109_ACCESS_2025_3525479 crossref_primary_10_3390_s24237492 crossref_primary_10_1016_j_applthermaleng_2024_124953 crossref_primary_10_1016_j_enbuild_2025_115580 crossref_primary_10_1016_j_energy_2025_137146 crossref_primary_10_1016_j_energy_2024_134197 |
| Cites_doi | 10.1016/j.enbuild.2021.111574 10.1016/j.ijrefrig.2022.07.020 10.1016/j.jclepro.2020.120082 10.1016/j.energy.2023.128569 10.1016/j.apenergy.2021.117238 10.1016/j.jclepro.2019.05.085 10.1016/j.rser.2017.02.023 10.1007/s13369-022-06655-2 10.1016/j.energy.2023.126660 10.1016/j.apenergy.2022.120144 10.1016/j.enbuild.2020.110372 10.1016/j.energy.2021.121084 10.1016/j.enbuild.2015.08.041 10.1016/j.energy.2021.121134 10.1016/j.chemosphere.2022.136525 10.1016/j.applthermaleng.2017.09.007 10.1016/j.enbuild.2019.05.043 10.1016/j.energy.2021.122073 10.1016/j.scs.2023.104679 10.1016/j.apenergy.2017.03.064 10.1016/j.energy.2022.126419 10.1016/j.enbuild.2022.112337 10.1016/j.enbuild.2017.08.077 10.1016/j.energy.2021.121127 10.1016/j.enconman.2018.08.053 10.1016/j.energy.2023.127865 10.1016/j.enbuild.2022.112478 10.1016/j.epsr.2023.109149 10.1016/j.rser.2017.09.108 10.1016/j.rser.2017.04.095 10.1016/j.energy.2021.122692 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Ltd |
| Copyright_xml | – notice: 2024 Elsevier Ltd |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.energy.2024.130388 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Economics Environmental Sciences |
| ExternalDocumentID | 10_1016_j_energy_2024_130388 S0360544224001592 |
| 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 AAHCO AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AARJD AAXUO ABJNI ABMAC ABMYL ABYKQ ACDAQ ACGFS ACIWK ACRLP ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFRAH AFTJW AGHFR AGUBO AGYEJ AHIDL AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BELTK BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG 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 RIG RNS ROL RPZ SDF SDG SES SEW SPC SPCBC SSR SSZ T5K TN5 XPP ZMT ~02 ~G- 29G 6TJ 9DU AAHBH AAQXK AATTM AAXKI AAYWO AAYXX ABDPE ABFNM ABWVN ABXDB ACLOT ACRPL ACVFH ADCNI ADMUD ADNMO ADXHL AEIPS AEUPX AFJKZ AFPUW AGQPQ AHHHB AIGII AIIUN AKBMS AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB G-2 HVGLF HZ~ R2- SAC WUQ ~HD 7S9 L.6 |
| ID | FETCH-LOGICAL-c339t-6be4a7eb80aa86f011f11c37ba69e3bc3810b609a62024f13c3c38dc4083ee453 |
| ISICitedReferencesCount | 18 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001171923500001&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 | Sun Nov 09 10:26:20 EST 2025 Tue Nov 18 22:12:19 EST 2025 Sat Nov 29 07:20:15 EST 2025 Sat Mar 23 16:41:00 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Improved whale optimization algorithm Prediction accuracy Cooling load forecasting Bidirectional long short-term memory Large commercial building |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c339t-6be4a7eb80aa86f011f11c37ba69e3bc3810b609a62024f13c3c38dc4083ee453 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 3153557434 |
| PQPubID | 24069 |
| ParticipantIDs | proquest_miscellaneous_3153557434 crossref_primary_10_1016_j_energy_2024_130388 crossref_citationtrail_10_1016_j_energy_2024_130388 elsevier_sciencedirect_doi_10_1016_j_energy_2024_130388 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-04-01 2024-04-00 20240401 |
| PublicationDateYYYYMMDD | 2024-04-01 |
| PublicationDate_xml | – month: 04 year: 2024 text: 2024-04-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Energy (Oxford) |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Guo, Yun, Meng, He, Ye, Zhao (bib35) 2023 Zhou, Moayedi, Bahiraei, Lyu (bib21) 2020; 254 Han, Li, Dong, Li (bib37) 2021; 233 Qiang, Zhe, Yan, Neng (bib17) 2015; 107 Zhao, Zhang, Zhang, Yang, Zhang (bib2) 2022; 144 Zhang, Tian, Ding, Lu, Niu (bib19) 2019; 230 Dong, Yu, Quan, Xiang, Li, Sun (bib3) 2022; 272 Wei, Zhang, Shi, Xia, Pan, Wu (bib10) 2018; 82 Fan, Liao, Zhou, Zhou, Ding (bib6) 2020; 226 Wang, Bai, Yang, Li (bib41) 2021 Wang, Han, Zhang, Wang, Zhang (bib27) 2023; 283 Fan, Xiao, Zhao (bib11) 2017; 195 Abdou, El Mghouchi, Jraida, Hamdaoui, Hajou, Mouqallid (bib18) 2022; 61 Ding, Zhang, Yuan, Yang (bib8) 2018; 128 Bian, Wang, Song, Zhou (bib24) 2023; 217 Yildiz, Bilbao, Sproul (bib12) 2017; 73 Lu, Gu, Lu (bib22) 2023; 96 Wan, Chang, Al-Bukhaiti, He (bib20) 2023 Xiong, Zhang, Shi, He (bib33) 2018; 174 Chen, Zhou, Zhou, Fan, Ding, Chen (bib5) 2022; 254 Fan, Ding (bib7) 2019; 197 Xiong, Peng, Tao, Zhang, Song, Nazir (bib31) 2023; 266 Sekhar, Dahiya (bib32) 2023; 268 Lu, Li, Reddy Penaka, Olofsson (bib15) 2023 Ding, Zhang, Yuan (bib13) 2017; 154 Li, Ding, Yin, Li, Zhao, Zhang (bib34) 2021 Singla, Duhan, Saroha (bib40) 2022; 44 Zhang, Sun, Gao, Zou, Fu, Ma (bib4) 2022; 327 Kang, Wang, An, Yan (bib1) 2022; 275 Li, Xiao, Zhang, Fan (bib14) 2021; 299 Li, Qu, Wang (bib28) 2023; vol. 124 Amasyali, El-Gohary (bib38) 2018; 81 Zhang, Wang (bib23) 2023; 278 Geng, Wang, Gao (bib30) 2023 Zhou, Wang, Liu, Yan, Ma (bib29) 2021; 233 Kavitha, Thiagarajan, Priya, Anand, Al-Ammar, Santhamoorthy (bib26) 2022; 309 Tian, Song, Lu, Lin, Niu (bib16) 2023 Gao, Yu, Zhao, Hu, Yang (bib9) 2022; 238 Xu, Li, Asgari (bib25) 2022; 240 Xiong, Hu, Guo (bib36) 2021; 234 Singla, Duhan, Saroha (bib39) 2022; 47 Zhao (10.1016/j.energy.2024.130388_bib2) 2022; 144 Fan (10.1016/j.energy.2024.130388_bib11) 2017; 195 Sekhar (10.1016/j.energy.2024.130388_bib32) 2023; 268 Fan (10.1016/j.energy.2024.130388_bib6) 2020; 226 Gao (10.1016/j.energy.2024.130388_bib9) 2022; 238 Zhang (10.1016/j.energy.2024.130388_bib19) 2019; 230 Zhou (10.1016/j.energy.2024.130388_bib21) 2020; 254 Wang (10.1016/j.energy.2024.130388_bib27) 2023; 283 Li (10.1016/j.energy.2024.130388_bib34) 2021 Wei (10.1016/j.energy.2024.130388_bib10) 2018; 82 Wang (10.1016/j.energy.2024.130388_bib41) 2021 Dong (10.1016/j.energy.2024.130388_bib3) 2022; 272 Lu (10.1016/j.energy.2024.130388_bib15) 2023 Tian (10.1016/j.energy.2024.130388_bib16) 2023 Chen (10.1016/j.energy.2024.130388_bib5) 2022; 254 Qiang (10.1016/j.energy.2024.130388_bib17) 2015; 107 Zhang (10.1016/j.energy.2024.130388_bib23) 2023; 278 Li (10.1016/j.energy.2024.130388_bib14) 2021; 299 Kang (10.1016/j.energy.2024.130388_bib1) 2022; 275 Wan (10.1016/j.energy.2024.130388_bib20) 2023 Kavitha (10.1016/j.energy.2024.130388_bib26) 2022; 309 Xu (10.1016/j.energy.2024.130388_bib25) 2022; 240 Fan (10.1016/j.energy.2024.130388_bib7) 2019; 197 Xiong (10.1016/j.energy.2024.130388_bib33) 2018; 174 Zhou (10.1016/j.energy.2024.130388_bib29) 2021; 233 Singla (10.1016/j.energy.2024.130388_bib40) 2022; 44 Abdou (10.1016/j.energy.2024.130388_bib18) 2022; 61 Geng (10.1016/j.energy.2024.130388_bib30) 2023 Amasyali (10.1016/j.energy.2024.130388_bib38) 2018; 81 Ding (10.1016/j.energy.2024.130388_bib8) 2018; 128 Bian (10.1016/j.energy.2024.130388_bib24) 2023; 217 Guo (10.1016/j.energy.2024.130388_bib35) 2023 Lu (10.1016/j.energy.2024.130388_bib22) 2023; 96 Li (10.1016/j.energy.2024.130388_bib28) 2023; vol. 124 Han (10.1016/j.energy.2024.130388_bib37) 2021; 233 Ding (10.1016/j.energy.2024.130388_bib13) 2017; 154 Singla (10.1016/j.energy.2024.130388_bib39) 2022; 47 Yildiz (10.1016/j.energy.2024.130388_bib12) 2017; 73 Xiong (10.1016/j.energy.2024.130388_bib31) 2023; 266 Xiong (10.1016/j.energy.2024.130388_bib36) 2021; 234 Zhang (10.1016/j.energy.2024.130388_bib4) 2022; 327 |
| References_xml | – volume: 299 year: 2021 ident: bib14 article-title: Attention-based interpretable neural network for building cooling load prediction publication-title: Appl Energy – volume: 144 start-page: 211 year: 2022 end-page: 221 ident: bib2 article-title: Prediction of functional zones cooling load for shopping mall using dual attention based LSTM: a case study publication-title: Int J Refrig – volume: 195 start-page: 222 year: 2017 end-page: 233 ident: bib11 article-title: A short-term building cooling load prediction method using deep learning algorithms publication-title: Appl Energy – volume: 268 year: 2023 ident: bib32 article-title: Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand publication-title: Energy – volume: 107 start-page: 445 year: 2015 end-page: 455 ident: bib17 article-title: An improved office building cooling load prediction model based on multivariable linear regression publication-title: Energy Build – volume: 44 start-page: 1583 year: 2022 end-page: 1607 ident: bib40 article-title: A dual decomposition with error correction strategy based improved hybrid deep learning model to forecast solar irradiance publication-title: Energy Sources, Part A Recovery, Util Environ Eff – start-page: 168 year: 2021 ident: bib34 article-title: Optimized neural network combined model based on the induced ordered weighted averaging operator for vegetable price forecasting publication-title: Expert Syst Appl – volume: 47 start-page: 14185 year: 2022 end-page: 14211 ident: bib39 article-title: A hybrid solar irradiance forecasting using full wavelet packet decomposition and Bi-directional long short-term memory (BiLSTM) publication-title: Arabian J Sci Eng – volume: 230 start-page: 622 year: 2019 end-page: 633 ident: bib19 article-title: Development and evaluation of cooling load prediction models for a factory workshop publication-title: J Clean Prod – volume: 272 year: 2022 ident: bib3 article-title: Short-term building cooling load prediction model based on DwdAdam-ILSTM algorithm: a case study of a commercial building publication-title: Energy Build – volume: 327 year: 2022 ident: bib4 article-title: Similarity-based grouping method for evaluation and optimization of dataset structure in machine-learning based short-term building cooling load prediction without measurable occupancy information publication-title: Appl Energy – volume: 233 year: 2021 ident: bib37 article-title: Determination of HVAC meteorological parameters for floating nuclear power stations (FNPSs) in the area of China sea and its vicinity publication-title: Energy – volume: 283 year: 2023 ident: bib27 article-title: Electrical load forecasting based on variable T-distribution and dual attention mechanism publication-title: Energy – start-page: 274 year: 2023 ident: bib15 article-title: Automated machine learning-based framework of heating and cooling load prediction for quick residential building design publication-title: Energy – volume: 278 year: 2023 ident: bib23 article-title: Multi-head attention-based probabilistic CNN-BiLSTM for day-ahead wind speed forecasting publication-title: Energy – volume: 266 year: 2023 ident: bib31 article-title: A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction publication-title: Energy – volume: 73 start-page: 1104 year: 2017 end-page: 1122 ident: bib12 article-title: A review and analysis of regression and machine learning models on commercial building electricity load forecasting publication-title: Renew Sustain Energy Rev – volume: vol. 124 year: 2023 ident: bib28 publication-title: A method of knowledge distillation based on feature fusion and attention mechanism for complex traffic scenes – volume: 309 year: 2022 ident: bib26 article-title: Improved harris hawks optimization with hybrid deep learning based heating and cooling load prediction on residential buildings publication-title: Chemosphere – volume: 275 year: 2022 ident: bib1 article-title: A novel approach of day-ahead cooling load prediction and optimal control for ice-based thermal energy storage (TES) system in commercial buildings publication-title: Energy Build – start-page: 291 year: 2023 ident: bib30 article-title: A hybrid photovoltaic/wind power prediction model based on Time2Vec, WDCNN and BiLSTM – volume: 81 start-page: 1192 year: 2018 end-page: 1205 ident: bib38 article-title: A review of data-driven building energy consumption prediction studies publication-title: Renew Sustain Energy Rev – volume: 226 year: 2020 ident: bib6 article-title: Improving cooling load prediction reliability for HVAC system using Monte-Carlo simulation to deal with uncertainties in input variables publication-title: Energy Build – volume: 217 year: 2023 ident: bib24 article-title: Feature extraction and classification of time-varying power load characteristics based on PCANet and CNN+Bi-LSTM algorithms publication-title: Elec Power Syst Res – volume: 128 start-page: 225 year: 2018 end-page: 234 ident: bib8 article-title: Effect of input variables on cooling load prediction accuracy of an office building publication-title: Appl Therm Eng – start-page: 282 year: 2023 ident: bib20 article-title: Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism publication-title: Energy – volume: 234 year: 2021 ident: bib36 article-title: A hybrid optimized grey seasonal variation index model improved by whale optimization algorithm for forecasting the residential electricity consumption publication-title: Energy – volume: 240 year: 2022 ident: bib25 article-title: Prediction and optimization of heating and cooling loads in a residential building based on multi-layer perceptron neural network and different optimization algorithms publication-title: Energy – start-page: 244 year: 2021 ident: bib41 article-title: Short time air temperature prediction using pattern approximate matching publication-title: Energy Build – volume: 96 year: 2023 ident: bib22 article-title: An improved attention-based deep learning approach for robust cooling load prediction: public building cases under diverse occupancy schedules publication-title: Sustain Cities Soc – volume: 174 start-page: 388 year: 2018 end-page: 405 ident: bib33 article-title: Parameter extraction of solar photovoltaic models using an improved whale optimization algorithm publication-title: Energy Convers Manag – start-page: 236 year: 2023 ident: bib35 article-title: Prediction of heating and cooling loads based on light gradient boosting machine algorithms publication-title: Build Environ – volume: 197 start-page: 7 year: 2019 end-page: 17 ident: bib7 article-title: Cooling load prediction and optimal operation of HVAC systems using a multiple nonlinear regression model publication-title: Energy Build – volume: 233 year: 2021 ident: bib29 article-title: Incorporating deep learning of load predictions to enhance the optimal active energy management of combined cooling, heating and power system publication-title: Energy – volume: 238 year: 2022 ident: bib9 article-title: A hybrid method of cooling load forecasting for large commercial building based on extreme learning machine publication-title: Energy – volume: 254 year: 2022 ident: bib5 article-title: An online physical-based multiple linear regression model for building's hourly cooling load prediction publication-title: Energy Build – start-page: 296 year: 2023 ident: bib16 article-title: Load extraction from actual operation data for data-driven ultra-short-term room air-conditioning load prediction publication-title: Energy Build – volume: 61 year: 2022 ident: bib18 article-title: Prediction and optimization of heating and cooling loads for low energy buildings in Morocco: an application of hybrid machine learning methods publication-title: J Build Eng – volume: 154 start-page: 254 year: 2017 end-page: 267 ident: bib13 article-title: Research on short-term and ultra-short-term cooling load prediction models for office buildings publication-title: Energy Build – volume: 254 year: 2020 ident: bib21 article-title: Employing artificial bee colony and particle swarm techniques for optimizing a neural network in prediction of heating and cooling loads of residential buildings publication-title: J Clean Prod – volume: 82 start-page: 1027 year: 2018 end-page: 1047 ident: bib10 article-title: A review of data-driven approaches for prediction and classification of building energy consumption publication-title: Renew Sustain Energy Rev – volume: 254 year: 2022 ident: 10.1016/j.energy.2024.130388_bib5 article-title: An online physical-based multiple linear regression model for building's hourly cooling load prediction publication-title: Energy Build doi: 10.1016/j.enbuild.2021.111574 – volume: 144 start-page: 211 year: 2022 ident: 10.1016/j.energy.2024.130388_bib2 article-title: Prediction of functional zones cooling load for shopping mall using dual attention based LSTM: a case study publication-title: Int J Refrig doi: 10.1016/j.ijrefrig.2022.07.020 – volume: 254 year: 2020 ident: 10.1016/j.energy.2024.130388_bib21 article-title: Employing artificial bee colony and particle swarm techniques for optimizing a neural network in prediction of heating and cooling loads of residential buildings publication-title: J Clean Prod doi: 10.1016/j.jclepro.2020.120082 – start-page: 291 year: 2023 ident: 10.1016/j.energy.2024.130388_bib30 – volume: 283 year: 2023 ident: 10.1016/j.energy.2024.130388_bib27 article-title: Electrical load forecasting based on variable T-distribution and dual attention mechanism publication-title: Energy doi: 10.1016/j.energy.2023.128569 – volume: 299 year: 2021 ident: 10.1016/j.energy.2024.130388_bib14 article-title: Attention-based interpretable neural network for building cooling load prediction publication-title: Appl Energy doi: 10.1016/j.apenergy.2021.117238 – volume: 230 start-page: 622 year: 2019 ident: 10.1016/j.energy.2024.130388_bib19 article-title: Development and evaluation of cooling load prediction models for a factory workshop publication-title: J Clean Prod doi: 10.1016/j.jclepro.2019.05.085 – volume: 73 start-page: 1104 year: 2017 ident: 10.1016/j.energy.2024.130388_bib12 article-title: A review and analysis of regression and machine learning models on commercial building electricity load forecasting publication-title: Renew Sustain Energy Rev doi: 10.1016/j.rser.2017.02.023 – volume: 47 start-page: 14185 issue: 11 year: 2022 ident: 10.1016/j.energy.2024.130388_bib39 article-title: A hybrid solar irradiance forecasting using full wavelet packet decomposition and Bi-directional long short-term memory (BiLSTM) publication-title: Arabian J Sci Eng doi: 10.1007/s13369-022-06655-2 – volume: 268 year: 2023 ident: 10.1016/j.energy.2024.130388_bib32 article-title: Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand publication-title: Energy doi: 10.1016/j.energy.2023.126660 – volume: 327 year: 2022 ident: 10.1016/j.energy.2024.130388_bib4 article-title: Similarity-based grouping method for evaluation and optimization of dataset structure in machine-learning based short-term building cooling load prediction without measurable occupancy information publication-title: Appl Energy doi: 10.1016/j.apenergy.2022.120144 – volume: 226 year: 2020 ident: 10.1016/j.energy.2024.130388_bib6 article-title: Improving cooling load prediction reliability for HVAC system using Monte-Carlo simulation to deal with uncertainties in input variables publication-title: Energy Build doi: 10.1016/j.enbuild.2020.110372 – volume: 233 year: 2021 ident: 10.1016/j.energy.2024.130388_bib37 article-title: Determination of HVAC meteorological parameters for floating nuclear power stations (FNPSs) in the area of China sea and its vicinity publication-title: Energy doi: 10.1016/j.energy.2021.121084 – volume: 107 start-page: 445 year: 2015 ident: 10.1016/j.energy.2024.130388_bib17 article-title: An improved office building cooling load prediction model based on multivariable linear regression publication-title: Energy Build doi: 10.1016/j.enbuild.2015.08.041 – volume: 233 year: 2021 ident: 10.1016/j.energy.2024.130388_bib29 article-title: Incorporating deep learning of load predictions to enhance the optimal active energy management of combined cooling, heating and power system publication-title: Energy doi: 10.1016/j.energy.2021.121134 – volume: 309 year: 2022 ident: 10.1016/j.energy.2024.130388_bib26 article-title: Improved harris hawks optimization with hybrid deep learning based heating and cooling load prediction on residential buildings publication-title: Chemosphere doi: 10.1016/j.chemosphere.2022.136525 – volume: 128 start-page: 225 year: 2018 ident: 10.1016/j.energy.2024.130388_bib8 article-title: Effect of input variables on cooling load prediction accuracy of an office building publication-title: Appl Therm Eng doi: 10.1016/j.applthermaleng.2017.09.007 – start-page: 296 year: 2023 ident: 10.1016/j.energy.2024.130388_bib16 article-title: Load extraction from actual operation data for data-driven ultra-short-term room air-conditioning load prediction publication-title: Energy Build – volume: 197 start-page: 7 year: 2019 ident: 10.1016/j.energy.2024.130388_bib7 article-title: Cooling load prediction and optimal operation of HVAC systems using a multiple nonlinear regression model publication-title: Energy Build doi: 10.1016/j.enbuild.2019.05.043 – volume: 238 year: 2022 ident: 10.1016/j.energy.2024.130388_bib9 article-title: A hybrid method of cooling load forecasting for large commercial building based on extreme learning machine publication-title: Energy doi: 10.1016/j.energy.2021.122073 – start-page: 168 year: 2021 ident: 10.1016/j.energy.2024.130388_bib34 article-title: Optimized neural network combined model based on the induced ordered weighted averaging operator for vegetable price forecasting publication-title: Expert Syst Appl – start-page: 244 year: 2021 ident: 10.1016/j.energy.2024.130388_bib41 article-title: Short time air temperature prediction using pattern approximate matching publication-title: Energy Build – volume: 96 year: 2023 ident: 10.1016/j.energy.2024.130388_bib22 article-title: An improved attention-based deep learning approach for robust cooling load prediction: public building cases under diverse occupancy schedules publication-title: Sustain Cities Soc doi: 10.1016/j.scs.2023.104679 – volume: vol. 124 year: 2023 ident: 10.1016/j.energy.2024.130388_bib28 – volume: 195 start-page: 222 year: 2017 ident: 10.1016/j.energy.2024.130388_bib11 article-title: A short-term building cooling load prediction method using deep learning algorithms publication-title: Appl Energy doi: 10.1016/j.apenergy.2017.03.064 – volume: 266 year: 2023 ident: 10.1016/j.energy.2024.130388_bib31 article-title: A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction publication-title: Energy doi: 10.1016/j.energy.2022.126419 – volume: 272 year: 2022 ident: 10.1016/j.energy.2024.130388_bib3 article-title: Short-term building cooling load prediction model based on DwdAdam-ILSTM algorithm: a case study of a commercial building publication-title: Energy Build doi: 10.1016/j.enbuild.2022.112337 – volume: 154 start-page: 254 year: 2017 ident: 10.1016/j.energy.2024.130388_bib13 article-title: Research on short-term and ultra-short-term cooling load prediction models for office buildings publication-title: Energy Build doi: 10.1016/j.enbuild.2017.08.077 – start-page: 282 year: 2023 ident: 10.1016/j.energy.2024.130388_bib20 article-title: Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism publication-title: Energy – volume: 61 year: 2022 ident: 10.1016/j.energy.2024.130388_bib18 article-title: Prediction and optimization of heating and cooling loads for low energy buildings in Morocco: an application of hybrid machine learning methods publication-title: J Build Eng – start-page: 236 year: 2023 ident: 10.1016/j.energy.2024.130388_bib35 article-title: Prediction of heating and cooling loads based on light gradient boosting machine algorithms publication-title: Build Environ – volume: 234 year: 2021 ident: 10.1016/j.energy.2024.130388_bib36 article-title: A hybrid optimized grey seasonal variation index model improved by whale optimization algorithm for forecasting the residential electricity consumption publication-title: Energy doi: 10.1016/j.energy.2021.121127 – volume: 174 start-page: 388 year: 2018 ident: 10.1016/j.energy.2024.130388_bib33 article-title: Parameter extraction of solar photovoltaic models using an improved whale optimization algorithm publication-title: Energy Convers Manag doi: 10.1016/j.enconman.2018.08.053 – volume: 278 year: 2023 ident: 10.1016/j.energy.2024.130388_bib23 article-title: Multi-head attention-based probabilistic CNN-BiLSTM for day-ahead wind speed forecasting publication-title: Energy doi: 10.1016/j.energy.2023.127865 – volume: 275 year: 2022 ident: 10.1016/j.energy.2024.130388_bib1 article-title: A novel approach of day-ahead cooling load prediction and optimal control for ice-based thermal energy storage (TES) system in commercial buildings publication-title: Energy Build doi: 10.1016/j.enbuild.2022.112478 – start-page: 274 year: 2023 ident: 10.1016/j.energy.2024.130388_bib15 article-title: Automated machine learning-based framework of heating and cooling load prediction for quick residential building design publication-title: Energy – volume: 217 year: 2023 ident: 10.1016/j.energy.2024.130388_bib24 article-title: Feature extraction and classification of time-varying power load characteristics based on PCANet and CNN+Bi-LSTM algorithms publication-title: Elec Power Syst Res doi: 10.1016/j.epsr.2023.109149 – volume: 82 start-page: 1027 year: 2018 ident: 10.1016/j.energy.2024.130388_bib10 article-title: A review of data-driven approaches for prediction and classification of building energy consumption publication-title: Renew Sustain Energy Rev doi: 10.1016/j.rser.2017.09.108 – volume: 81 start-page: 1192 year: 2018 ident: 10.1016/j.energy.2024.130388_bib38 article-title: A review of data-driven building energy consumption prediction studies publication-title: Renew Sustain Energy Rev doi: 10.1016/j.rser.2017.04.095 – volume: 240 year: 2022 ident: 10.1016/j.energy.2024.130388_bib25 article-title: Prediction and optimization of heating and cooling loads in a residential building based on multi-layer perceptron neural network and different optimization algorithms publication-title: Energy doi: 10.1016/j.energy.2021.122692 – volume: 44 start-page: 1583 issue: 1 year: 2022 ident: 10.1016/j.energy.2024.130388_bib40 article-title: A dual decomposition with error correction strategy based improved hybrid deep learning model to forecast solar irradiance publication-title: Energy Sources, Part A Recovery, Util Environ Eff |
| SSID | ssj0005899 |
| Score | 2.5165775 |
| Snippet | Accurate and reliable cooling load forecasting is a prerequisite for air-conditioning system control and the basis for building-side energy management.... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 130388 |
| SubjectTerms | algorithms Bidirectional long short-term memory Cooling load forecasting energy Improved whale optimization algorithm Large commercial building neural networks prediction Prediction accuracy principal component analysis |
| Title | A hybrid prediction model of improved bidirectional long short-term memory network for cooling load based on PCANet and attention mechanism |
| URI | https://dx.doi.org/10.1016/j.energy.2024.130388 https://www.proquest.com/docview/3153557434 |
| Volume | 292 |
| WOSCitedRecordID | wos001171923500001&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/eLvHCXMwtV3da9swEBchHWwvY-tW1u4DDfYWXGJbtuVHUzK6MULHOsiejC3La0pqlzopyXMf-0_vTmfZ_WB0G4yACYctObpfpNPpd3eMfdAq0-MsUE4e56EjPCWc3A1KR0SyKKV23ZA0_SWaTuVsFh8NBlc2FuZyEVWVXK_j8_-qapCBsjF09i_U3TUKAvgOSocrqB2uf6T4ZHSywTAsDP8v5lQJ3NS7MdkhjA8Brc45LWbkCVxgxaHmBExxB6fq0Rnybzejijjihoqo6tpEri_qDJ6Gta_Ac4ajg2SqiaSOiTqJOnmmMZzY5ia0bn8KMsTspmsi1HcuiB_khJ3NVxu7kCKnZ07C6uf6hhRZuCj_CjJ86_5Qy7RxmLWi1pHh3eS_GO-ajbDp6UwU1TV2AiFuzdgelc-7N_uTI-J0X5tftI-dYLVrnwoH3smr_Q2bxpaRRQtGHazjW14UxHLItpJPk9nnnikkTRnS7lVsBKahCd7v63cWzp213hgwx8_Y03bnwRNCzHM20NU2e2wD05tttjPpgx7hxnbWb16w64QTpHgPKW4gxeuSW0jxW5DiqBzeQ4oTpHgLKQ4Q4C2kOEKKG0hxaJggxQFSvIMU7yD1kn3_ODk-OHTaIh6O8v146YS5FlmkcznOMhmWsJyUrqv8KM_CWPu5wgxzeTiOsxCHsHR9BR9ZKAF7A61F4O-wYVVX-hXjCvYqCv0RXuALmQeYylGXXiFV7opCRbvMtwOfqjbDPRZaWaSWyniakrpS7Cslde0yp3vqnDK8PHB_ZHWatlYqjW4KMHzgyfcWAilM4ngyl1W6XjWpD3ZHEIAxL_b-ufXX7En_r3rDhsuLlX7LHqnL5by5eNdi-hdK1sor |
| 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+hybrid+prediction+model+of+improved+bidirectional+long+short-term+memory+network+for+cooling+load+based+on+PCANet+and+attention+mechanism&rft.jtitle=Energy+%28Oxford%29&rft.au=Yan%2C+Xiuying&rft.au=Ji%2C+Xingxing&rft.au=Meng%2C+Qinglong&rft.au=Sun%2C+Hang&rft.date=2024-04-01&rft.pub=Elsevier+Ltd&rft.issn=0360-5442&rft.volume=292&rft_id=info:doi/10.1016%2Fj.energy.2024.130388&rft.externalDocID=S0360544224001592 |
| 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 |