Volume 12 • Issue 2 • PP: 66–80 • 2026
OccuTwin: Occupancy-Predictive HVAC Optimisation through Deep Learning and a BIM-Coupled Digital Twin
View PDF Abstract
Buildings account for nearly 40% of global final energy consumption, with heating, ventilation, and air conditioning systems responsible for the largest single share of that load. Conventional schedule-based HVAC controllers operate on fixed occupancy assumptions and are consequently unable to exploit the predictable but irregular occupancy patterns that characterise modern working environments. This paper proposes OccuTwin, an integrated framework that couples multi-step occupancy forecasting with a BIM-based digital twin to enable genuinely predictive HVAC optimisation. Four sequence models—Long Short-Term Memory, Gated Recurrent Unit, XGBoost with lag features, and a Temporal Fusion Transformer—are trained on the publicly available Mind Your Building occupancy dataset and the multi-building Building Data Genome Project benchmark to predict room-level occupancy at five-minute resolution. The best-performing Transformer model achieves 94.8% accuracy and an improved weighted F1- score on the 30% hold-out set, outperforming the LSTM baseline by 1.4 percentage points. An IFC-coupled co-simulation environment links real-time occupancy predictions to a virtual HVAC thermal model implemented in EnergyPlus, enabling zone-level set-point optimisation driven by predicted rather than sensed occupancy. Annual co-simulation across nine building zones documents 21.2% energy savings over a schedule-based rule controller while simultaneously improving the fraction of time within ASHRAE thermal comfort bounds from 92.4% to 97.2%. Ablation experiments identify temporal lag features and SMOTE-based class rebalancing as the two most critical preprocessing choices, and noise-injection tests confirm that the Transformer retains 95.1% accuracy under 15% sensor noise—a critical property for edge-deployed IoT environments.
Keywords
References
[1] International Energy Agency, “Buildings — tracking progress,” IEA, Tech. Rep., 2022.
[2] L. Perez-Lombard, J. Ortiz, and C. Pout, “A review on buildings energy consumption information,” Energy and Buildings, vol. 40, no. 3, pp. 394–398, 2008.
[3] C. Eastman, P. Teicholz, R. Sacks, and K. Liston, BIM Handbook: A Guide to Building Information Modelling for Owners, Managers, Designers, Engineers and Contractors, 2nd ed. Hoboken, NJ: Wiley, 2011.
[4] A. Borrmann, M. Konig, C. Koch, and J. Beetz, Eds., Building Information Modelling: Technology Foundations and Industry Practice. Cham: Springer, 2018.
[5] J. Drgoˇna, J. Arroyo, I. Cupeiro Figueroa, D. Blum, K. Arendt, D. Kim, E. P. Olšak, J. Oravec, M. Wetter, D. L. Vrabie, and L. Helsen, “All you need to know about model predictive control for buildings,” Annual Reviews in Control, vol. 50, pp. 190–232, 2020.
[6] F. Oldewurtel, A. Parisio, C. N. Jones, D. Gyalistras, M. Gwerder, V. Stauch, B. Lehmann, and M. Morari, “Use of model predictive control and weather forecasts for energy efficient building climate control,” Energy and Buildings, vol. 45, pp. 15–27, 2012.
[7] S. Privara, J. Široky, L. Ferkl, and J. Cigler, “Model predictive control of a building heating system: The first experience,” Energy and Buildings, vol. 43, no. 2–3, pp. 564–572, 2011.
[8] A. Mirakhorli and B. Dong, “Occupancy behavior based model predictive control for building indoor climate— a critical review,” Energy and Buildings, vol. 129, pp. 499–512, 2016.
[9] Y. Agarwal, B. Balaji, R. Gupta, J. Lyles, M. Wei, and T. Weng, “Occupancy-driven energy management for smart building automation,” in Proceedings of the 2nd ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings, 2010, pp. 1–6.
[10] L. M. Candanedo and V. Feldheim, “Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models,” Energy and Buildings, vol. 112, pp. 28–39, 2016.
[11] B. Balaji, A. Bhattacharya, G. Fierro, J. Gao, J. Gluck, D. Hong, A. Johansen, J. Koh, J. Ploennigs, Y. Agarwal, M. Berges, D. Culler, R. Gupta, M. B. Kjargaard, M. Srivastava, and K. Whitehouse, “Brick: Towards a unified metadata schema for buildings,” in Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments, 2016, pp. 41–50.
[12] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735– 1780, 1997.
[13] K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, 2014, pp. 1724–1734.
[14] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems, vol. 30, 2017.
[15] B. Lim, S. O. Arık, N. Loeff, and T. Pfister, “Temporal fusion transformers for interpretable multi-horizon time series forecasting,” International Journal of Forecasting, vol. 37, no. 4, pp. 1748–1764, 2021.
[16] H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang, “Informer: Beyond efficient transformer for long sequence time-series forecasting,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 12, 2021, pp. 11 106–11 115.
[17] M. Grieves and J. Vickers, “Digital twin: Mitigating unpredictable, undesirable emergent behavior in complex systems,” in Transdisciplinary Perspectives on Complex Systems, F.-J. Kahlen, S. Flumerfelt, and A. Alves, Eds. Cham: Springer, 2017, pp. 85–113.
[18] Q. Lu, A. K. Parlikad, P. Woodall, G. Don Ranasinghe, X. Xie, Z. Liang, E. Konstantinou, J. Heaton, and J. Schooling, “Developing a digital twin at building and city levels: Case study of west Cambridge campus,” Journal of Management in Engineering, vol. 36, no. 3, p. 05020004, 2020.
[19] S. H. Khajavi, N. H. Motlagh, A. Jaribion, L. C.Werner, and J. Holmstrom, “Digital twin: Vision, benefits, boundaries, and creation for buildings,” IEEE Access, vol. 7, pp. 147 406–147 419, 2019.
[20] U.S. Department of Energy, “EnergyPlus engineering reference,” National Renewable Energy Laboratory, Tech. Rep., 2023.
[21] Z. Zhang, X. Cheng, H. Luo, R. Li, and J. Zheng, “Building occupancy estimation with environmental sensors via CDBLSTM,” IEEE Transactions on Industrial Electronics, vol. 66, no. 12, pp. 9683–9692, 2019.
[22] C. Miller, J. Boman, and T. de Coupade, “The building data genome project 2: Benchmarking methods using one year of hourly energy use data from 307 nonresidential buildings,” SoftwareX, vol. 12, p. 100573, 2020.
[23] T. Wei, Y. Wang, and Q. Zhu, “Deep reinforcement learning for building HVAC control,” in Proceedings of the 54th Annual Design Automation Conference, 2017, pp. 22:1–22:6.
[24] J.-Y. Kim and S.-B. Cho, “Electric energy consumption prediction by deep learning with state explainable autoencoder,” Energies, vol. 12, no. 4, p. 739, 2019.
[25] A. Fuller, Z. Fan, C. Day, and C. Barlow, “Digital twin: Enabling technology, challenges and open research,” IEEE Access, vol. 8, pp. 108 952–108 971, 2020.
[26] F. Tao, Q. Qi, L. Wang, and A. Y. C. Nee, “Digital twins and cyber–physical systems toward smart manufacturing and industry 4.0: Correlation and comparison,” Engineering, vol. 5, no. 4, pp. 653–661, 2019.
[27] J. Y. Park, Z. Chen, K. Febrian, A. K. Alqahtani, and T. Hong, “Comprehensive analyses of occupant behavior and energy use in mixed-mode commercial buildings using occupant sensing data and BIM-based digital twin,” Building and Environment, vol. 217, p. 109057, 2022.
[28] P. Pauwels and W. Terkaj, “EXPRESS to OWL for construction industry: Towards a recommendable and usable ifcOWL ontology,” Automation in Construction, vol. 63, pp. 100–133, 2016.
[29] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014.
[30] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.
[31] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” International Conference on Learning Representations, 2015.
[32] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R.Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
Cite This Article
Choose your preferred format