{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T10:25:31Z","timestamp":1788258331551,"version":"build-2803163510"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Xinjiang Uyghur Autonomous Region Graduate Research Innovation Project","award":["XJ2025G085"],"award-info":[{"award-number":["XJ2025G085"]}]},{"name":"Xinjiang Uyghur Autonomous Region Youth Science and Technology Talent Project","award":["2022TSYCCX0060"],"award-info":[{"award-number":["2022TSYCCX0060"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate prediction of chiller energy consumption is crucial for reducing building energy consumption. In this study, an innovative dual-branch network architecture DNTB (A Dual-Branch Network Model Based on Transformer and Bi-LSTM for Energy Consumption Prediction in Building Chiller Systems) was proposed to address the problems of insufficient long-term dependency modeling and noise sensitivity in current prediction models. The research goal is to develop a prediction model that can simultaneously process temporal features and global dependencies. The basic principle is to utilize the complementary characteristics of Transformer and Bi-LSTM. Transformer is sensitive to data noise and Bi-LSTM is weak in capturing long-term sequence information. It can better capture the temporal information of chiller energy consumption data and well model the relationship between variables such as chilled water, building load, chiller temperature, humidity, dew point and chiller energy consumption. In order to prove the effectiveness and generalization ability of the model, experiments were carried out on long-term and short-term tasks of chiller energy consumption prediction. The long-term prediction results had MSE (mean absolute error) of 0.0051, RMSE (mean square error) of 0.0605, and R2 (coefficient of determination) of 0.8031. The short-term prediction results had MSE of 0.0080, RMSE of 0.0738, and R2 of 0.6717. The experimental results indicate that DNTB performs excellently in both long-term and short-term chiller energy consumption prediction, making it a robust framework for chiller energy consumption prediction. The introduction of DNTB enriches the diversity of empirical model algorithms.<\/jats:p>","DOI":"10.1371\/journal.pone.0330187","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T17:23:13Z","timestamp":1759512193000},"page":"e0330187","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["DNTB: Dual-branch network model based on transformer and Bi-LSTM for energy consumption prediction in building chiller systems"],"prefix":"10.1371","volume":"20","author":[{"given":"Andong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingtao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6855-7428","authenticated-orcid":true,"given":"Xiaoyi","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"issue":"4","key":"pone.0330187.ref001","doi-asserted-by":"crossref","first-page":"2897","DOI":"10.9770\/jesi.2020.7.4(21)","article-title":"Global climate change and greenhouse effect","volume":"7","author":"A Mikhaylov","year":"2020","journal-title":"Entrepreneur Sustain Issue"},{"key":"pone.0330187.ref002","doi-asserted-by":"crossref","first-page":"112873","DOI":"10.1016\/j.enpol.2022.112873","article-title":"Key areas and pathways for carbon emissions reduction in Beijing for the \u201cdual carbon\u201d targets","volume":"164","author":"R Huang","year":"2022","journal-title":"Energy Policy"},{"key":"pone.0330187.ref003","doi-asserted-by":"crossref","first-page":"104728","DOI":"10.1016\/j.nanoen.2020.104728","article-title":"Recent advances in dual-carbon based electrochemical energy storage devices","volume":"72","author":"R Hou","year":"2020","journal-title":"Nano Energy"},{"key":"pone.0330187.ref004","doi-asserted-by":"crossref","first-page":"108100","DOI":"10.1016\/j.buildenv.2021.108100","article-title":"A review of optimization approaches for controlling water-cooled central cooling systems","volume":"203","author":"L Jia","year":"2021","journal-title":"Build Environ"},{"key":"pone.0330187.ref005","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/0360-1323(86)90026-0","article-title":"Predictions of the heating and cooling energy requirements in buildings using the degree hours method","volume":"21","author":"K Letherman","year":"1986","journal-title":"Build Environ"},{"issue":"4","key":"pone.0330187.ref006","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/S0360-1323(98)00038-9","article-title":"A tool for integrated HVAC, building, energy and control analysis part 1: overview of QUICKcontrol","volume":"34","author":"E Mathews","year":"1999","journal-title":"Build Environ"},{"key":"pone.0330187.ref007","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1016\/j.apenergy.2016.06.133","article-title":"Evaluation of a multiple linear regression model and SARIMA model in forecasting heat demand for district heating system","volume":"179","author":"T Fang","year":"2016","journal-title":"Appl Energy"},{"key":"pone.0330187.ref008","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.apenergy.2017.10.044","article-title":"Completion of wind turbine data sets for wind integration studies applying random forests and k-nearest neighbors","volume":"208","author":"R Becker","year":"2017","journal-title":"Appl Energy"},{"issue":"4","key":"pone.0330187.ref009","first-page":"1","article-title":"Stock price prediction model based on convolutional neural networks","volume":"2","author":"Z Zhou","year":"2024","journal-title":"J Ind Eng Appl Sci"},{"issue":"5","key":"pone.0330187.ref010","doi-asserted-by":"crossref","first-page":"2493","DOI":"10.1002\/cjce.24640","article-title":"Prediction of critical total drawdown in sand production from gas wells: Machine learning approach","volume":"101","author":"FS Alakbari","year":"2023","journal-title":"Canadian J Chem Eng"},{"issue":"1","key":"pone.0330187.ref011","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.jrmge.2023.04.012","article-title":"A gated recurrent unit model to predict Poisson\u2019s ratio using deep learning","volume":"16","author":"FS Alakbari","year":"2024","journal-title":"J Rock Mech Geotech Eng"},{"issue":"4","key":"pone.0330187.ref012","first-page":"20","article-title":"Cross-market arbitrage strategies based on deep learning","volume":"2","author":"R Wu","year":"2024","journal-title":"Acad J Sociol Manag"},{"key":"pone.0330187.ref013","author":"AM Hassan","year":"2022","journal-title":"A new insight into smart water assisted foam SWAF technology in carbonate rocks using artificial neural networks ANNs. In: Offshore Technology Conference Asia. OTC"},{"key":"pone.0330187.ref014","article-title":"Distributed Hybrid-Triggered Observer-Based Secondary Control of Multi-Bus DC Microgrids Over Directed Networks.","author":"X Li","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems I: Regular Papers"},{"key":"pone.0330187.ref015","article-title":"Resilient frequency regulation for microgrids under phasor measurement unit faults and communication intermittency","author":"Z Hu","year":"2024","journal-title":"IEEE Trans Ind Info"},{"key":"pone.0330187.ref016","doi-asserted-by":"crossref","first-page":"2127","DOI":"10.1016\/j.enconman.2003.10.009","article-title":"Cooling load prediction for buildings using general regression neural networks","volume":"45","author":"AE Ben-Nakhi","year":"2004","journal-title":"Energy Convers Manag"},{"issue":"5","key":"pone.0330187.ref017","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1016\/j.advengsoft.2008.05.003","article-title":"Prediction of building energy consumption by using artificial neural networks","volume":"40","author":"BB Ekici","year":"2009","journal-title":"Adv Eng Softw"},{"key":"pone.0330187.ref018","doi-asserted-by":"crossref","DOI":"10.1109\/WSC.2015.7408504","article-title":"A review of artificial intelligence based building energy prediction with a focus on ensemble prediction models.","author":"Z Wang","year":"2015","journal-title":"2015 Winter simulation conference (WSC). IEEE"},{"key":"pone.0330187.ref019","doi-asserted-by":"crossref","first-page":"109807","DOI":"10.1016\/j.enbuild.2020.109807","article-title":"The use of artificial intelligence (AI) methods in the prediction of thermal comfort in buildings: Energy implications of AI-based thermal comfort controls","volume":"211","author":"J Ngarambe","year":"2020","journal-title":"Energ Build"},{"key":"pone.0330187.ref020","doi-asserted-by":"crossref","first-page":"111718","DOI":"10.1016\/j.enbuild.2021.111718","article-title":"Building energy prediction using artificial neural networks: A literature survey","volume":"262","author":"C Lu","year":"2022","journal-title":"Energ Build"},{"key":"pone.0330187.ref021","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.neucom.2019.02.040","article-title":"A comprehensive review on the application of artificial neural networks in building energy analysis","volume":"340","author":"SR Mohandes","year":"2019","journal-title":"Neurocomputing"},{"key":"pone.0330187.ref022","doi-asserted-by":"crossref","first-page":"100071","DOI":"10.1016\/j.enrev.2024.100071","article-title":"AI in HVAC fault detection and diagnosis: A systematic review","author":"J Bi","year":"2024","journal-title":"Energy Rev"},{"key":"pone.0330187.ref023","article-title":"AI-powered Thermal Comfort: Predicting Indoor Air Temperature for Efficient HVAC Systems.","author":"S Zubair","year":"2024","journal-title":"2024 29th International Conference on Automation and Computing (ICAC). IEEE"},{"issue":"3","key":"pone.0330187.ref024","article-title":"HVAC load prediction and energy saving strategies in building automation","volume":"9","author":"V Sharma","year":"2022","journal-title":"European J Adv Eng Technol"},{"key":"pone.0330187.ref025","doi-asserted-by":"crossref","first-page":"113508","DOI":"10.1016\/j.enbuild.2023.113508","article-title":"An energy consumption prediction method for HVAC systems using energy storage based on time series shifting and deep learning","volume":"298","author":"H Liu","year":"2023","journal-title":"Energ Build"},{"key":"pone.0330187.ref026","doi-asserted-by":"crossref","first-page":"120936","DOI":"10.1016\/j.apenergy.2023.120936","article-title":"Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning","volume":"338","author":"D Zhuang","year":"2023","journal-title":"Appl Energy"},{"key":"pone.0330187.ref027","doi-asserted-by":"crossref","first-page":"111275","DOI":"10.1016\/j.enbuild.2021.111275","article-title":"Fault detection diagnostic for HVAC systems via deep learning algorithms","volume":"250","author":"S Taheri","year":"2021","journal-title":"Energ Build"},{"key":"pone.0330187.ref028","doi-asserted-by":"crossref","first-page":"104103","DOI":"10.1016\/j.jobe.2022.104103","article-title":"Real-time building heat gains prediction and optimization of HVAC setpoint: An integrated framework","volume":"49","author":"Z Wang","year":"2022","journal-title":"J Build Eng"},{"key":"pone.0330187.ref029","doi-asserted-by":"crossref","first-page":"107158","DOI":"10.1016\/j.jobe.2023.107158","article-title":"Predictive control optimization of chiller plants based on deep reinforcement learning","volume":"76","author":"K He","year":"2023","journal-title":"J Build Eng"},{"issue":"8","key":"pone.0330187.ref030","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1080\/23744731.2023.2247938","article-title":"Model-free MIMO control tuning of a chiller process using reinforcement learning","volume":"29","author":"C Rosdahl","year":"2023","journal-title":"Sci Technol Built Environ"},{"key":"pone.0330187.ref031","doi-asserted-by":"crossref","first-page":"125679","DOI":"10.1016\/j.energy.2022.125679","article-title":"Cross temporal-spatial transferability investigation of deep reinforcement learning control strategy in the building HVAC system level","volume":"263","author":"X Fang","year":"2023","journal-title":"Energy"},{"key":"pone.0330187.ref032","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","article-title":"Long short-term memory.","volume-title":"Supervised sequence labelling with recurrent neural networks","author":"A Graves","year":"2012"},{"issue":"24","key":"pone.0330187.ref033","doi-asserted-by":"crossref","first-page":"11820","DOI":"10.3390\/app112411820","article-title":"Field data forecasting using LSTM and Bi-LSTM approaches","volume":"11","author":"P Suebsombut","year":"2021","journal-title":"Appl Sci"},{"key":"pone.0330187.ref034","doi-asserted-by":"crossref","first-page":"17569","DOI":"10.1007\/s00521-020-04926-3","article-title":"LSTM-based indoor air temperature prediction framework for HVAC systems in smart buildings","volume":"32","author":"F Mtibaa","year":"2020","journal-title":"Neural Comput Appl"},{"key":"pone.0330187.ref035","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1016\/j.cherd.2020.06.008","article-title":"An encoder\u2013decoder LSTM-based EMPC framework applied to a building HVAC system","volume":"160","author":"MJ Ellis","year":"2020","journal-title":"Chem Eng Res Design"},{"key":"pone.0330187.ref036","author":"A Vaswani","year":"2017","journal-title":"Attention is all you need. In: Advances in Neural Information Processing Systems"},{"issue":"4","key":"pone.0330187.ref037","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting","volume":"37","author":"B Lim","year":"2021","journal-title":"Int J Forecast"},{"key":"pone.0330187.ref038","doi-asserted-by":"crossref","first-page":"113409","DOI":"10.1016\/j.enbuild.2023.113409","article-title":"A novel transformer-based network forecasting method for building cooling loads","volume":"296","author":"L Li","year":"2023","journal-title":"Energy Build"},{"key":"pone.0330187.ref039","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"A Graves","year":"2005","journal-title":"Neural Netw"},{"key":"pone.0330187.ref040","author":"E Shutova","year":"2016","journal-title":"Black holes and white rabbits: Metaphor identification with visual features. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Human language technologies"},{"key":"pone.0330187.ref041","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-44415-3_16","article-title":"Majority vote of diverse classifiers for late fusion.","author":"E Morvant","year":"2014","journal-title":"Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop, S+ SSPR 2014, Joensuu, Finland, August 20-22, 2014. Proceedings. Springer"},{"issue":"7","key":"pone.0330187.ref042","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1109\/TMM.2013.2267205","article-title":"Multimodal saliency and fusion for movie summarization based on aural, visual, and textual attention","volume":"15","author":"G Evangelopoulos","year":"2013","journal-title":"IEEE Trans Multimedia"},{"key":"pone.0330187.ref043","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"A Krizhevsky","year":"2012","journal-title":"Adv Neural Information Process Syst"},{"key":"pone.0330187.ref044","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"pone.0330187.ref045","author":"K He","year":"2016","journal-title":"Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0330187.ref046","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","volume":"10","author":"S Bai","year":"2018","journal-title":"arXiv"},{"key":"pone.0330187.ref047","author":"H Zhou","year":"2021","journal-title":"Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI conference on artificial intelligence"},{"key":"pone.0330187.ref048","unstructured":"Chiller energy data: HVAC system energy data with weather data [Online]. 2023. Available from: https:\/\/www.kaggle.com\/chillerenergy"},{"key":"pone.0330187.ref049","unstructured":"Ashraf A. Correlation in machine learning\u2014All you need to know. 2023. Available from: https:\/\/medium.com\/@abdallahashraf90x\/all-you-need-to-know-about-correlation-for-machine-learning-e249fec292e9"},{"key":"pone.0330187.ref050","unstructured":"Cross-validation: evaluating estimator performance. 2023. Available from: https:\/\/scikit-learn.org\/stable\/modules\/cross_validation.html"},{"key":"pone.0330187.ref051","doi-asserted-by":"crossref","first-page":"112337","DOI":"10.1016\/j.enbuild.2022.112337","article-title":"Short-term building cooling load prediction model based on DwdAdam-ILSTM algorithm: A case study of a commercial building","volume":"272","author":"F Dong","year":"2022","journal-title":"Energ Build"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T17:23:21Z","timestamp":1759512201000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330187"}},"subtitle":[],"editor":[{"given":"Zhengmao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":51,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0330187","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]}}}