Abstract
Accurate building energy prediction is vital to develop optimal control strategies to enhance building energy efficiency and energy flexibility. In recent years, the data-driven approach based on machine learning algorithms has been widely adopted for building energy prediction due to the availability of massive data in building automation systems (BASs), which automatically collect and store real-time building operational data. For new buildings and most existing buildings without installing advanced BASs, there is a lack of sufficient data to train data-driven predictive models. Transfer learning is a promising method to develop accurate and reliable data-driven building energy prediction models with limited training data by taking advantage of the rich data/knowledge obtained from other buildings. Few studies focused on the influences of source building datasets, pre-training data volume, and training data volume on the performance of the transfer learning method. The present study aims to develop a transfer learning-based ANN model for one-hour ahead building energy prediction to fill this research gap. Around 400 non-residential buildings’ data from the open-source Building Genome Project are used to test the proposed method. Extensive analysis demonstrates that transfer learning can effectively improve the accuracy of BPNN-based building energy models for information-poor buildings with very limited training data. The most influential building features which influence the effectiveness of transfer learning are found to be building usage and industry. The research outcomes can provide guidance for implementation of transfer learning, especially in selecting appropriate source buildings and datasets for developing accurate building energy prediction models.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amasyali K, El-Gohary NM (2018). A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 81: 1192–1205.
Asadi S, Amiri SS, Mottahedi M (2014). On the development of multi-linear regression analysis to assess energy consumption in the early stages of building design. Energy and Buildings, 85: 246–255.
Bourdeau M, Zhai X, Nefzaoui E, Guo X, Chatellier P (2019). Modeling and forecasting building energy consumption: a review of data-driven techniques. Sustainable Cities and Society, 48: 101533.
EMSD (2019). Hong Kong Energy End-use Data 2019, Available at http://www.emsd.gov.hk.
Fan C, Xiao F, Zhao Y (2017). A short-term building cooling load prediction method using deep learning algorithms. Applied Energy, 195: 222–233.
Fan C, Sun Y, Zhao Y, Song M, Wang J (2019a). Deep learning-based feature engineering methods for improved building energy prediction. Applied Energy, 240: 35–45.
Fan C, Wang J, Gang W, Li S (2019b). Assessment of deep recurrent neural network-based strategies for short-term building energy predictions. Applied Energy, 236: 700–710.
Fan C, Sun Y, Xiao F, Ma J, Lee D, et al. (2020). Statistical investigations of transfer learning-based methodology for short-term building energy predictions. Applied Energy, 262: 114499.
Goodfellow I, Bengio Y, Courville A (2016). Deep Learning. Cambridge, MA, USA: MIT Press.
Hahnloser RHR, Sarpeshkar R, Mahowald MA, Douglas RJ, Seung HS (2000). Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature, 405: 947–951.
Hooshmand A, Sharma R (2019). Energy predictive models with limited data using transfer learning. In: Proceedings of the 10th ACM International Conference on Future Energy Systems, Phoenix AZ USA.
Hosseinzadeh H, Razzazi F, Kabir E (2016). A weakly supervised large margin domain adaptation method for isolated handwritten digit recognition. Journal of Visual Communication and Image Representation, 38: 307–315.
Hu W, Qian Y, Soong FK, Wang Y (2015). Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers. Speech Communication, 67: 154–166.
IEA (2015). Building Energy Use in China. OECD/IEA, Paris.
IEA (2018). World Energy Statistics and Balances 2018. OECD/IEA, Paris.
Karpathy A (2017). A Peek at Trends in Machine Learning. Available at https://medium.com.
Kendall MG (1938). A new measure of rank correlation. Biometrika, 30: 81–93.
Keogh E, Kasetty S (2003). On the need for time series data mining benchmarks: A survey and empirical demonstration. Data Mining and Knowledge Discovery, 7: 349–371.
Kingma DP, Ba J (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Li X, Wen J (2014). Review of building energy modeling for control and operation. Renewable and Sustainable Energy Reviews, 37: 517–537.
Li W, Duan L, Xu D, Tsang IW (2014). Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36: 1134–1148.
Ma Y, Luo G, Zeng X, Chen A (2012). Transfer learning for cross-company software defect prediction. Information and Software Technology, 54: 248–256.
Miller C, Meggers F (2017a). Mining electrical meter data to predict principal building use, performance class, and operations strategy for hundreds of non-residential buildings. Energy and Buildings, 156: 360–373.
Miller C, Meggers F (2017b). The Building Data Genome Project: An open, public data set from non-residential building electrical meters. Energy Procedia, 122: 439–444.
Nichiforov C, Stamatescu G, Stamatescu I, Fagarasan I, Iliescu SS (2018). Intelligent load forecasting for building energy management systems. In: Proceedings of IEEE the 14th International Conference on Control and Automation (ICCA), Anchorage, AK, USA.
Pan SJ, Yang Q (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22: 1345–1359.
Perera ATD, Wickramasinghe PU, Nik VM, Scartezzini JL (2019). Machine learning methods to assist energy system optimization. Applied Energy, 243: 191–205.
Rahman A, Srikumar V, Smith AD (2018). Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Applied Energy, 212: 372–385.
Ramachandran P, Zoph B, Le QV (2017). Searching for activation functions. arXiv preprint arXiv:1710.05941.
Ribeiro M, Grolinger K, ElYamany HF, Higashino WA, Capretz MAM (2018). Transfer learning with seasonal and trend adjustment for cross-building energy forecasting. Energy and Buildings, 165: 352–363.
Rumelhart DE, Hinton GE, Williams RJ (1986). Learning representations by back-propagating errors. Nature, 323: 533–536.
Shin HC, Roth HR, Gao M, Lu L, Xu Z, et al. (2016). Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging, 35: 1285–1298.
Silver DL, Yang Q, Li L (2013). Lifelong machine learning systems: Beyond learning algorithms. In: Proceedings of AAAI 2013 Spring Symposium on Lifelong Machine Learning, Stanford, CA, USA.
Weiss K, Khoshgoftaar TM, Wang D (2016). A survey of transfer learning. Journal of Big Data, 3: 9.
Xue, Wang S, Sun Y, Xiao F (2014). An interactive building power demand management strategy for facilitating smart grid optimization. Applied Energy, 116: 297–310.
Yosinski J, Clune J, Bengio Y, Lipson H (2014). How transferable are features in deep neural networks? In: Proceedings of the 27th International Conference on Neural Information Processing Systems.
Zhao H, Magoulès F (2012). A review on the prediction of building energy consumption. Renewable and Sustainable Energy Reviews, 16: 3586–3592.
Acknowledgements
The authors gratefully acknowledge the support of this research by the Research Grant Council of the Hong Kong SAR (152133/19E).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, A., Xiao, F., Fan, C. et al. Development of an ANN-based building energy model for information-poor buildings using transfer learning. Build. Simul. 14, 89–101 (2021). https://doi.org/10.1007/s12273-020-0711-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12273-020-0711-5