Skip to main content
SpringerLink
Log in

Federated learning-based short-term building energy consumption prediction method for solving the data silos problem

  • Research Article
  • Published:
Building Simulation Aims and scope Submit manuscript

Abstract

Transfer learning is an effective method to predict the energy consumption of information-poor buildings by learning transferable knowledge from operational data of information-rich buildings. However, it is not recommended to directly use the operational data without protection due to the risk of leaking occupants’ privacy. To address this problem, this study proposes a federated learning-based method to learn transferable knowledge from building operational data without privacy leaking. It trains a transferable federated model based on the operational data from the buildings similar to the target building with limited data. An advanced secure aggregation algorithm is adopted in the training process to ensure that no one can infer private information from the training data. The federated model obtained is evaluated by comparing it with the standalone model without federated learning based on 13 similar office buildings from the Building Data Genome Project. The results show that the federated model outperforms the standalone model concerning the prediction accuracy and training time. On average, the federated model achieves a 25.4% decrease in CV-RMSE when the target building has limited operational data. Even if the target building has no operational data, the federated model still achieves acceptable accuracy (CV-RMSE is 22.2%). Meanwhile, the training time of the federated model is 90% less than that of the standalone model. The research insights can help develop federated learning-based methods for solving the data silos problem in building energy management. The methodology and analysis procedures are reproducible and all codes and data sets are available on Github.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Abbreviations

ANN:

artificial neural network

GBT:

gradient boosted tree

LFM:

local federated model

LSTM:

long short-term memory network

MLR:

multiple linear regression

RF:

random forest

SGD:

stochastic gradient descent

SM:

standalone model

SVM:

support vector machine

CV-RMSE :

coefficient of variation of the root mean squared error

f(·):

model output

g :

gradient vector

L(·):

loss on all samples

MAE :

mean absolute error

MAPE :

mean absolute percentage error

n :

number of samples

p :

perturbation vector

RIM :

relative improvement

RMSE :

root mean squared error

T :

training time of a prediction model

w :

vector of weights and biases

W t :

vector of weights and biases at the time step t

x :

model input

x :

set of model inputs

y :

actual energy consumption

\(\bar y\) :

average of actual energy consumption

ŷ :

predicted energy consumption

y :

set of actual energy consumption

δ :

vector

References

  • Ahmad MW, Mourshed M, Rezgui Y (2017). Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption. Energy and Buildings, 147: 77–89.

    Article  Google Scholar 

  • Amasyali K, El-Gohary N (2021). Machine learning for occupant-behavior-sensitive cooling energy consumption prediction in office buildings. Renewable and Sustainable Energy Reviews, 142: 110714.

    Article  Google Scholar 

  • Arjunan P, Poolla K, Miller C (2020). EnergyStar++: Towards more accurate and explanatory building energy benchmarking. Applied Energy, 276: 115413.

    Article  Google Scholar 

  • ASHRAE (2013). ASHRAE Standard 169-2013. Climatic Data for Building Design Standards. GA, Atlanta, USA: American Society of Heating, Refrigerating and Air-Conditioning Engineers.

    Google Scholar 

  • ASHRAE (2014). ASHRAE Guideline 14-2014. Measurement of Energy, Demand, and Water Savings. GA, Atlanta, USA: American Society of Heating, Refrigerating and Air-Conditioning Engineers.

    Google Scholar 

  • Bianco V, de Rosa M, Scarpa F, et al. (2016). Analysis of energy demand in residential buildings for different climates by means of dynamic simulation. International Journal of Ambient Energy, 37: 108–120.

    Article  Google Scholar 

  • Biswas MAR, Robinson MD, Fumo N (2016). Prediction of residential building energy consumption: A neural network approach. Energy, 117: 84–92.

    Article  Google Scholar 

  • Bonawitz K, Ivanov V, Kreuter B, et al. (2016). Practical secure aggregation for federated learning on user-held data. arXiv:1611. 04482.

  • Brisimi TS, Chen R, Mela T, et al. (2018). Federated learning of predictive models from federated Electronic Health Records. International Journal of Medical Informatics, 112: 59–67.

    Article  Google Scholar 

  • Chen F, Luo M, Dong Z, et al. (2018). Federated meta-learning with fast convergence and efficient communication. arXiv:1802.07876.

  • Ciulla G, D’Amico A (2019). Building energy performance forecasting: A multiple linear regression approach. Applied Energy, 253: 113500.

    Article  Google Scholar 

  • Czeizler E, Wiessler W, Koester T, et al. (2020). Using federated data sources and Varian Learning Portal framework to train a neural network model for automatic organ segmentation. Physica Medica, 72: 39–45.

    Article  Google Scholar 

  • Delcroix B, Ny JL, Bernier M, et al. (2021). Autoregressive neural networks with exogenous variables for indoor temperature prediction in buildings. Building Simulation, 14: 165–178.

    Article  Google Scholar 

  • Diaz-Acevedo JA, Grisales-Noreña LF, Escobar A (2019). A method for estimating electricity consumption patterns of buildings to implement Energy Management Systems. Journal of Building Engineering, 25: 100774.

    Article  Google Scholar 

  • Dong Z, Liu J, Liu B, et al. (2021). Hourly energy consumption prediction of an office building based on ensemble learning and energy consumption pattern classification. Energy and Buildings, 241: 110929.

    Article  Google Scholar 

  • Dreyfus SE (1990). Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure. Journal of Guidance, Control, and Dynamics, 13: 926–928.

    Article  MathSciNet  Google Scholar 

  • EIA (2019). International Energy Outlook 2019. Energy Information Administration. Available at https://www.eia.gov/outlooks/ieo/pdf/ieo2019.pdf.

  • Fan C, Sun Y, Xiao F, et al. (2020). Statistical investigations of transfer learning-based methodology for short-term building energy predictions. Applied Energy, 262: 114499.

    Article  Google Scholar 

  • Fan C, Xiao F, Yan D (2021a). Advanced data analytics for building energy modeling and management. Building Simulation, 14: 1–2.

    Article  Google Scholar 

  • Fan C, Yan D, Xiao F, et al. (2021b). Advanced data analytics for enhancing building performances: From data-driven to big data-driven approaches. Building Simulation, 14: 3–24.

    Article  Google Scholar 

  • Fredrikson M, Jha S, Ristenpart T (2015). Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, Denver, CO, USA.

  • Goodfellow I, Bengio Y, Courville A (2016). Deep Learning. Cambridge, MA, USA: MIT Press.

    MATH  Google Scholar 

  • Grubinger T, Chasparis GC, Natschläger T (2017). Generalized online transfer learning for climate control in residential buildings. Energy and Buildings, 139: 63–71.

    Article  Google Scholar 

  • Gupta TK, Raza K (2019). Optimization of ANN architecture: A review on nature-inspired techniques. In: Dey N, Borra S, Ashour AS, et al. (Eds.), Machine Learning in Bio-Signal Analysis and Diagnostic Imaging. London: Academic Press.

    Google Scholar 

  • Hitaj B, Ateniese G, Perez-Cruz F (2017). Deep models under the GAN: Information leakage from collaborative deep learning. In: Proceedings of the ACM Conference on Computer and Communications Security.

  • Hong Y, Ezeh CI, Deng W, et al. (2020). Correlation between building characteristics and associated energy consumption: Prototyping low-rise office buildings in Shanghai. Energy and Buildings, 217: 109959.

    Article  Google Scholar 

  • Huang L, Shea AL, Qian H, et al. (2019). Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records. Journal of Biomedical Informatics, 99: 103291.

    Article  Google Scholar 

  • IEA (2019). Global Status Report for Buildings and Construction 2019. International Energy Agency. Available at https://www.iea.org/reports/global-status-report-for-buildings-and-construction-2019.

  • Ilbeigi M, Ghomeishi M, Dehghanbanadaki A (2020). Prediction and optimization of energy consumption in an office building using artificial neural network and a genetic algorithm. Sustainable Cities and Society, 61: 102325.

    Article  Google Scholar 

  • Jin Y, Yan D, Chong A, et al. (2021a). Building occupancy forecasting: A systematical and critical review. Energy and Buildings, 251: 111345.

    Article  Google Scholar 

  • Jin Y, Yan D, Zhang X, An J, Han M (2021b). A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development. Building Simulation, 14: 219–235.

    Article  Google Scholar 

  • Kim J, Ha H, Chun BG, et al. (2016). Collaborative analytics for data silos. In: Proceedings of 2016 IEEE 32nd International Conference on Data Engineering (ICDE), Helsinki, Finland.

  • Konečný J, McMahan HB, Ramage D, et al. (2016a). Federated optimization: Distributed machine learning for on-device intelligence. arXiv:1610.02527.

  • Konečný J, McMahan HB, Yu FX, et al. (2016b). Federated learning: Strategies for improving communication efficiency. arXiv:1610. 05492.

  • Li Z, Dai J, Chen H, et al. (2019). An ANN-based fast building energy consumption prediction method for complex architectural form at the early design stage. Building Simulation, 12: 665–681.

    Article  Google Scholar 

  • Li A, Xiao F, Fan C, et al. (2021). Development of an ANN-based building energy model for information-poor buildings using transfer learning. Building Simulation, 14: 89–101.

    Article  Google Scholar 

  • Liu J, Zhang Q, Dong Z, et al. (2021). Quantitative evaluation of the building energy performance based on short-term energy predictions. Energy, 223: 120065.

    Article  Google Scholar 

  • Lundberg, SM, Lee SI (2017). A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems.

  • Luo XJ, Oyedele LO, Ajayi AO, et al. (2020). Comparative study of machine learning-based multi-objective prediction framework for multiple building energy loads. Sustainable Cities and Society, 61: 102283.

    Article  Google Scholar 

  • Mcmahan B, Moore E, Ramage D, et al. (2017). Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics.

  • Melis L, Song C, de Cristofaro E, et al. (2019). Exploiting unintended feature leakage in collaborative learning. In: Proceedings of 2019 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.

  • Miller C, Meggers F (2017). The Building Data Genome Project: An open, public data set from non-residential building electrical meters. Energy Procedia, 122: 439–444.

    Article  Google Scholar 

  • Miller C (2019). More buildings make more generalizable models—Benchmarking prediction methods on open electrical meter data. Machine Learning and Knowledge Extraction, 1: 974–993.

    Article  Google Scholar 

  • Miller C, Arjunan P, Kathirgamanathan A, et al. (2020). The ASHRAE great energy predictor III competition: Overview and results. Science and Technology for the Built Environment, 26: 1427–1447.

    Article  Google Scholar 

  • Mocanu E, Nguyen PH, Kling WL, et al. (2016). Unsupervised energy prediction in a Smart Grid context using reinforcement cross-building transfer learning. Energy and Buildings, 116: 646–655.

    Article  Google Scholar 

  • Piscitelli MS, Brandi S, Capozzoli A, et al. (2021). A data analytics-based tool for the detection and diagnosis of anomalous daily energy patterns in buildings. Building Simulation, 14: 131–147.

    Article  Google Scholar 

  • Ribeiro M, Grolinger K, ElYamany HF, et al. (2018). Transfer learning with seasonal and trend adjustment for cross-building energy forecasting. Energy and Buildings, 165: 352–363.

    Article  Google Scholar 

  • Rueda L, Agbossou K, Cardenas A, et al. (2020). A comprehensive review of approaches to building occupancy detection. Building and Environment, 180: 106966.

    Article  Google Scholar 

  • Runge J, Zmeureanu R (2019). Forecasting energy use in buildings using artificial neural networks: A review. Energies, 12: 3254.

    Article  Google Scholar 

  • Shao M, Wang X, Bu Z, et al. (2020). Prediction of energy consumption in hotel buildings via support vector machines. Sustainable Cities and Society, 57: 102128.

    Article  Google Scholar 

  • Short CA, Song J, Mottet L, et al. (2018). Challenges in the low-carbon adaptation of China’s apartment towers. Building Research and Information, 46: 899–930.

    Article  Google Scholar 

  • Speiser S, Harth A (2010). Taking the LIDS off data silos. In: Proceedings of the 6th International Conference on Semantic Systems, Graz, Austria.

  • Sra S, Nowozin S, Wright SJ (2012). Optimization for Machine Learning. Cambridge, MA, USA: MIT Press.

    Google Scholar 

  • Sun Y, Haghighat F, Fung BCM (2020). A review of the-state-of-the-art in data-driven approaches for building energy prediction. Energy and Buildings, 221: 110022.

    Article  Google Scholar 

  • Wang C, Yan D, Jiang Y (2011). A novel approach for building occupancy simulation. Building Simulation, 4: 149–167.

    Article  Google Scholar 

  • Wang R, Lu S, Feng W (2020). A novel improved model for building energy consumption prediction based on model integration. Applied Energy, 262: 114561.

    Article  Google Scholar 

  • Yang Q, Liu Y, Chen T, et al. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 10: 1–19.

    Article  Google Scholar 

  • Yang L, Fu R, He W, et al. (2020). Adaptive thermal comfort and climate responsive building design strategies in dry-hot and dry-cold areas: Case study in Turpan, China. Energy and Buildings, 209: 109678.

    Article  Google Scholar 

  • Yao Y, Rosasco L, Caponnetto A (2007). On early stopping in gradient descent learning. Constructive Approximation, 26: 289–315.

    Article  MathSciNet  MATH  Google Scholar 

  • Zhang L, Wen J (2019). A systematic feature selection procedure for short-term data-driven building energy forecasting model development. Energy and Buildings, 183: 428–442.

    Article  Google Scholar 

  • Zhang C, Li J, Zhao Y, et al. (2020). A hybrid deep learning-based method for short-term building energy load prediction combined with an interpretation process. Energy and Buildings, 225: 110301.

    Article  Google Scholar 

  • Zhang C, Li J, Zhao Y, et al. (2021). Problem of data imbalance in building energy load prediction: Concept, influence, and solution. Applied Energy, 297: 117139.

    Article  Google Scholar 

  • Zhang C, Zhao Y, Zhou Y, et al. (2022). A real-time abnormal operation pattern detection method for building energy systems based on association rule bases. Building Simulation, 15: 69–81.

    Article  Google Scholar 

  • Zhao Y, Li T, Zhang X, et al. (2019). Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future. Renewable and Sustainable Energy Reviews, 109: 85–101.

    Article  Google Scholar 

  • Zhao Y, Zhang C, Zhang Y, et al. (2020). A review of data mining technologies in building energy systems: Load prediction, pattern identification, fault detection and diagnosis. Energy and Built Environment, 1: 149–164.

    Article  Google Scholar 

  • Zhou X, Ren J, An J, et al. (2021a). Predicting open-plan office window operating behavior using the random forest algorithm. Journal of Building Engineering, 42: 102514.

    Article  Google Scholar 

  • Zhou X, Tian S, An J, et al. (2021b). Comparison of different machine learning algorithms for predicting air-conditioning operating behavior in open-plan offices. Energy and Buildings, 251: 111347.

    Article  Google Scholar 

  • Zhu L, Liu Z, Han S (2019). Deep leakage from gradients. In: Proceedings of Annual Conference on Neural Information Processing Systems.

Download references

Acknowledgements

This work was supported by the National Key Research and Development Program of China (No. 2018YFE0116300) and the National Natural Science Foundation of China (No. 51978601).

Author information

Authors and Affiliations

  1. Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, China

    Junyang Li, Chaobo Zhang, Yang Zhao & Xuejun Zhang

  2. Department of Energy Engineering, Zhejiang University, Hangzhou, China

    Weikang Qiu

  3. Zhejiang Energy Group Co., Ltd., Hangzhou, China

    Qi Chen

Authors
  1. Junyang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chaobo Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Weikang Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qi Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xuejun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yang Zhao.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, J., Zhang, C., Zhao, Y. et al. Federated learning-based short-term building energy consumption prediction method for solving the data silos problem. Build. Simul. 15, 1145–1159 (2022). https://doi.org/10.1007/s12273-021-0871-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12273-021-0871-y

Keywords

Search

Navigation