{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:35:57Z","timestamp":1776184557974,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T00:00:00Z","timestamp":1612310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/00308\/2020"],"award-info":[{"award-number":["UIDB\/00308\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Nowadays, as more data is now available from an increasing number of installed sensors, load forecasting applied to buildings is being increasingly explored. The amount and quality of resulting information can provide inputs for smarter decisions when managing and operating office buildings. In this article, the authors use two data-driven methods (artificial neural networks and support vector machines) to predict the heating and cooling energy demand in an office building located in Lisbon, Portugal. In the present case-study, these methods prove to be an accurate and appealing alternative to the use of accurate but time-consuming multi-zone dynamic simulation tools, which strongly depend on several parameters to be inserted and user expertise to calibrate the model. Artificial neural networks and support vector machines were developed and parametrized using historical data and different sets of exogenous variables to encounter the best performance combinations for both the heating and cooling periods of a year. In the case of support vector regression, a variation introduced simulated annealing to guide the search for different combinations of hyperparameters. After a feature selection stage for each individual method, the results for the different methods were compared, based on error metrics and distributions. The outputs of the study include the most suitable methodology for each season, and also the features (historical load records, but also exogenous features such as outdoor temperature, relative humidity or occupancy profile) that led to the most accurate models. Results clearly show there is a potential for faster, yet accurate machine-learning based forecasting methods to replace well-established, very accurate but time-consuming multi-zone dynamic simulation tools to forecast building energy consumption.<\/jats:p>","DOI":"10.3390\/app11041356","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T11:54:31Z","timestamp":1612353271000},"page":"1356","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A Data-Driven Approach to Forecasting Heating and Cooling Energy Demand in an Office Building as an Alternative to Multi-Zone Dynamic Simulation"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8587-4812","authenticated-orcid":false,"given":"Xavier","family":"Godinho","sequence":"first","affiliation":[{"name":"School of Technology and Management, Polytechnic of Leiria, 2411-901 Leiria, Portugal"},{"name":"INESC Coimbra, DEEC, Polo II, University of Coimbra, 3030-790 Coimbra, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5290-6424","authenticated-orcid":false,"given":"Hermano","family":"Bernardo","sequence":"additional","affiliation":[{"name":"School of Technology and Management, Polytechnic of Leiria, 2411-901 Leiria, Portugal"},{"name":"INESC Coimbra, DEEC, Polo II, University of Coimbra, 3030-790 Coimbra, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7567-4910","authenticated-orcid":false,"given":"Jo\u00e3o C.","family":"de Sousa","sequence":"additional","affiliation":[{"name":"School of Technology and Management, Polytechnic of Leiria, 2411-901 Leiria, Portugal"},{"name":"INESC Coimbra, DEEC, Polo II, University of Coimbra, 3030-790 Coimbra, Portugal"}]},{"given":"Filipe T.","family":"Oliveira","sequence":"additional","affiliation":[{"name":"School of Technology and Management, Polytechnic of Leiria, 2411-901 Leiria, Portugal"},{"name":"INESC Coimbra, DEEC, Polo II, University of Coimbra, 3030-790 Coimbra, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Fallah, S., Deo, R., Shojafar, M., Conti, M., and Shamshirband, S. (2018). Computational Intelligence Approaches for Energy Load Forecasting in Smart Energy Management Grids: State of the Art, Future Challenges, and Research Directions. Energies, 11.","DOI":"10.3390\/en11030596"},{"key":"ref_2","unstructured":"Filho, W.L. (2019). Energy Management Tools for Sustainability. Encyclopedia of Sustainability in Higher Education, Springer Nature."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Jang, J., Lee, J., Son, E., Park, K., Kim, G., Lee, J.H., and Leigh, S.-B. (2019). Development of an Improved Model to Predict Building Thermal Energy Consumption by Utilizing Feature Selection. Energies, 12.","DOI":"10.3390\/en12214187"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.aei.2013.05.001","article-title":"Building simulation approaches for the training of automated data analysis tools in building energy management","volume":"27","author":"Pearson","year":"2013","journal-title":"Adv. Eng. Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"101533","DOI":"10.1016\/j.scs.2019.101533","article-title":"Modeling and forecasting building energy consumption: A review of data-driven techniques","volume":"48","author":"Bourdeau","year":"2019","journal-title":"Sustain. Cities Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.enbuild.2018.03.059","article-title":"Performance optimization of a demand controlled ventilation system by long term monitoring","volume":"169","author":"Schibuola","year":"2018","journal-title":"Energy Build."},{"key":"ref_7","unstructured":"Saheb, Y., Shnapp, S., and Paci, D. (2019). From Nearly-Zero Energy Buildings to Net-Zero Energy Districts\u2014Lessons Learned from Existing EU Projects, Publications Office of the European Union."},{"key":"ref_8","unstructured":"Lopes, M., Antunes, C.H., and Janda, K.B. (2019). Resource-efficient nondomestic buildings: Intertwining behaviour and technology. Energy and Behaviour: Towards a Low Carbon Future, Elsevier."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1016\/j.apenergy.2016.06.013","article-title":"Predicting energy performance of a net-zero energy building: A statistical approach","volume":"178","author":"Kneifel","year":"2016","journal-title":"Appl. Energy"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/S0360-5442(99)00086-9","article-title":"Artificial neural networks for the prediction of the energy consumption of a passive solar building","volume":"25","author":"Kalogirou","year":"2000","journal-title":"Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"110287","DOI":"10.1016\/j.rser.2020.110287","article-title":"Machine learning applications in urban building energy performance forecasting: A systematic review","volume":"133","author":"Fathi","year":"2020","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.enbuild.2018.01.017","article-title":"A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: A review","volume":"165","author":"Ahmad","year":"2018","journal-title":"Energy Build."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Paone, A., and Bacher, J.-P. (2018). The Impact of Building Occupant Behavior on Energy Efficiency and Methods to Influence It: A Review of the State of the Art. Energies, 11.","DOI":"10.3390\/en11040953"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.autcon.2014.02.009","article-title":"The gap between predicted and measured energy performance of buildings: A framework for investigation","volume":"41","year":"2014","journal-title":"Autom. Constr."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s40327-018-0064-7","article-title":"Machine learning for estimation of building energy consumption and performance: A review","volume":"6","author":"Seyedzadeh","year":"2018","journal-title":"Vis. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.enbuild.2018.06.050","article-title":"A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis","volume":"174","author":"Zhao","year":"2018","journal-title":"Energy Build."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1734","DOI":"10.1016\/j.proeng.2015.09.144","article-title":"Forecasting Energy Consumption of Institutional Buildings in Singapore","volume":"121","author":"Deb","year":"2015","journal-title":"Procedia Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Xuemei, L., Lixing, D., and Lanlan, L. (2010, January 5\u20137). A novel building cooling load prediction based on SVR and SAPSO. Proceedings of the 2010 International Symposium on Computer, Communication, Control and Automation (3CA), Tainam, Taiwan.","DOI":"10.1109\/3CA.2010.5533863"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.energy.2014.07.064","article-title":"Heating, cooling, and electrical load forecasting for a large-scale district energy system","volume":"74","author":"Powell","year":"2014","journal-title":"Energy"},{"key":"ref_20","first-page":"2169","article-title":"Comparison between Detailed Model Simulation and Artificial Neural Network for Forecasting Building Energy Consumption","volume":"40","author":"Neto","year":"2008","journal-title":"Elsevier"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.egypro.2018.08.169","article-title":"Forecasting District Heating Demand using Machine Learning Algorithms","volume":"149","author":"Saloux","year":"2018","journal-title":"Energy Procedia"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1016\/j.rser.2016.10.079","article-title":"A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models","volume":"75","author":"Wang","year":"2017","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Godinho, X., Bernardo, H., Oliveira, F., and Sousa, J.C. (2020, January 3). de Forecasting Heating and Cooling Energy Demand in an Office Building using Machine Learning Methods. Proceedings of the 2020 International Young Engineers Forum (YEF-ECE), Caparica, Portugal.","DOI":"10.1109\/YEF-ECE49388.2020.9171807"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Runge, J., and Zmeureanu, R. (2019). Forecasting Energy Use in Buildings Using Artificial Neural Networks: A Review. Energies, 12.","DOI":"10.3390\/en12173254"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2669","DOI":"10.1016\/j.enconman.2005.02.004","article-title":"Support vector machines with simulated annealing algorithms in electricity load forecasting","volume":"46","author":"Pai","year":"2005","journal-title":"Energy Convers. Manag."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1002\/er.3048","article-title":"Short-term load forecasting based on support vector regression and load profiling","volume":"38","author":"Sousa","year":"2014","journal-title":"Int. J. Energy Res."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Abbas, S.M., and Arif, M. (2006, January 23\u201324). Electric Load Forecasting Using Support Vector Machines Optimized by Genetic Algorithm. Proceedings of the 2006 IEEE International Multitopic Conference, Islamabad, Pakistan.","DOI":"10.1109\/INMIC.2006.358199"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1016\/j.asoc.2007.10.012","article-title":"Parameter determination of support vector machine and feature selection using simulated annealing approach","volume":"8","author":"Lin","year":"2008","journal-title":"Appl. Soft Comput."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/59.910780","article-title":"Neural networks for short-term load forecasting: A review and evaluation","volume":"16","author":"Hippert","year":"2001","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zuniga-Garcia, M.A., Santamar\u00eda-Bonfil, G., Arroyo-Figueroa, G., and Batres, R. (2019). Prediction interval adjustment for load-forecasting using machine learning. Appl. Sci., 9.","DOI":"10.3390\/app9245269"}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/11\/4\/1356\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:19:17Z","timestamp":1760159957000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/11\/4\/1356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,3]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["app11041356"],"URL":"https:\/\/doi.org\/10.3390\/app11041356","relation":{},"ISSN":["2076-3417"],"issn-type":[{"value":"2076-3417","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,3]]}}}