Deep learning for prediction of energy consumption: an applied use case in an office building Morcillo Jiménez, Roberto Mesa, Jesús Gómez-Romero, Juan Vila, M. Amparo Martín Bautista, María José Buildings Energy consumption forecasting Time series Non-residential buildings are responsible for more than a third of global energy consumption. Estimating building energy consumption is the first step towards identifying inefficiencies and optimizing energy management policies. This paper presents a study of Deep Learning techniques for time series analysis applied to building energy prediction with real environments. We collected multisource sensor data from an actual office building under normal operating conditions, pre-processed them, and performed a comprehensive evaluation of the accuracy of feed-forward and recurrent neural networks to predict energy consumption. The results show that memory-based architectures (LSTMs) perform better than stateless ones (MLPs) even without data aggregation (CNNs), although the lack of ample usable data in this type of problem avoids making the most of recent techniques such as sequence-to-sequence (Seq2Seq). 2024-07-23T11:10:08Z 2024-07-23T11:10:08Z 2024-05-01 journal article Morcillo-Jimenez, R., Mesa, J., Gómez-Romero, J. et al. Deep learning for prediction of energy consumption: an applied use case in an office building. Appl Intell 54, 5813–5825 (2024). [https://doi.org/10.1007/s10489-024-05451-9] https://hdl.handle.net/10481/93404 10.1007/s10489-024-05451-9 eng info:eu-repo/grantAgreement/EC/NextGenerationEU/MIA.2021.M04.0008 http://creativecommons.org/licenses/by/4.0/ open access Atribución 4.0 Internacional Springer Nature