Skip to main content
SpringerLink
Log in

Parameter estimation for building energy models using GRcGAN

  • Research Article
  • Advances in Modeling and Simulation Tools
  • Published:
Building Simulation Aims and scope Submit manuscript

Abstract

Parameter estimation methods can be classified into (1) manual (trial-and-error), (2) numerical optimization (optimization, sampling), (3) Bayesian inference (Bayes filter, Bayesian calibration), and (4) machine learning (generative model). Bayesian calibration has been widely used because it can capture stochastic nature of uncertain parameters. However, the results of Bayesian calibration could be biased by (1) the prior distribution assumed by the expert’s subjective judgment; (2) the likelihood function that cannot always describe the true likelihood; and (3) the posterior distribution approximation method, such as the Markov Chain Monte Carlo, which requires significant computation time. To overcome this, a new approach using a generator-regularized continuous conditional generative adversarial network (GRcGAN) is presented in this paper. Five target parameters of the DOE reference building model were selected. GRcGAN was trained to estimate uncertain parameters using simulated monthly electricity and gas use. GRcGAN can successfully estimate five uncertain parameters based on 1,000 training data points. The proposed approach presents a potential for stochastic parameter estimation.

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

References

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

  • ASHRAE (2017). ASHRAE Handbook Fundamentals. Atlanta, GA, USA: American Society of Heating, Refrigerating and Air-Conditioning Engineers.

  • Bendaoud NMM, Farah N, Ben Ahmed S (2021). Comparing Generative Adversarial Networks architectures for electricity demand forecasting. Energy and Buildings, 247: 111152.

    Article  Google Scholar 

  • Brastein OM, Lie B, Sharma R, Skeie NO (2019). Parameter estimation for externally simulated thermal network models. Energy and Buildings, 191: 200–210.

    Article  Google Scholar 

  • Burhenne S, Jacob D, Henze GP (2011). Sampling based on Sobol’sequences for Monte Carlo techniques applied to building simulations. In: Proceedings of the 12th International IBPSA Building Simulation Conference, Sydney, Australia.

  • Cetin KS, Fathollahzadeh MH, Kunwar N, et al. (2019). Development and validation of an HVAC on/off controller in EnergyPlus for energy simulation of residential and small commercial buildings. Energy and Buildings, 183: 467–483.

    Article  Google Scholar 

  • Chakrabarty A, Maddalena E, Qiao H, et al. (2021). Scalable Bayesian optimization for model calibration: case study on coupled building and HVAC dynamics. Energy and Buildings, 253: 111460.

    Article  Google Scholar 

  • Chen Z, Jiang C (2018). Building occupancy modeling using generative adversarial network. Energy and Buildings, 174: 372–379.

    Article  Google Scholar 

  • Chen Y, Deng Z, Hong T (2020). Automatic and rapid calibration of urban building energy models by learning from energy performance database. Applied Energy, 277: 115584.

    Article  Google Scholar 

  • Chong A, Lam KP (2017). A comparison of MCMC algorithms for the Bayesian calibration of building energy models. In: Proceedings of the 15 International IBPSA Building Simulation Conference, San Francisco, USA

  • Chong A, Lam KP, Pozzi M, et al. (2017). Bayesian calibration of building energy models with large datasets. Energy and Buildings, 154: 343–355.

    Article  Google Scholar 

  • Chong A, Menberg K (2018). Guidelines for the Bayesian calibration of building energy models. Energy and Buildings, 174: 527–547.

    Article  Google Scholar 

  • Chuah JW, Raghunathan A, Jha NK (2013). ROBESim: A retrofit-oriented building energy simulator based on EnergyPlus. Energy and Buildings, 66: 88–103.

    Article  Google Scholar 

  • CIBSE (2015). CIBSE Guide A Environmental design. The Chartered Institution of building Services Engineers (CIBSE).

  • Cipriano J, Mor G, Chemisana D, et al. (2015). Evaluation of a multi-stage guided search approach for the calibration of building energy simulation models. Energy and Buildings, 87: 370–385.

    Article  Google Scholar 

  • Clark A, Donahue J, Simonyan K (2019). Adversarial video generation on complex datasets. arXiv: 1907.06571.

  • Deru M, Field K, Studer D, et al. (2011). U.S. Department of Energy Commercial Reference Building Models of the National Building Stock. National Renewable Energy Laboratory (NREL), USA.

    Book  Google Scholar 

  • de Wilde P (2014). The gap between predicted and measured energy performance of buildings: A framework for investigation. Automation in Construction, 41: 40–49.

    Article  Google Scholar 

  • de Wit S, Augenbroe G (2002). Analysis of uncertainty in building design evaluations and its implications. Energy and Buildings, 34: 951–958.

    Article  Google Scholar 

  • Dunn G, Knight I (2005). Small power equipment loads in UK office environments. Energy and Buildings, 37: 87–91.

    Article  Google Scholar 

  • Goodfellow I, Pouget-Abadie J, Mirza M, et al. (2014). Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS’14).

  • Goodfellow I (2016). NIPS 2016 tutorial: generative adversarial networks. arXiv: 1701.00160.

  • Harmer LC, Henze GP (2015). Using calibrated energy models for building commissioning and load prediction. Energy and Buildings, 92: 204–215.

    Article  Google Scholar 

  • Hu J, Shen E, Gu Y (2015). Evaluation of lighting performance risk using surrogate model and EnergyPlus. Procedia Engineering, 118: 522–529.

    Article  Google Scholar 

  • IPMVP (2001). International Performance Measurement and Verification Protocol: Concepts and options for determining energy and water savings, Volume I (No. DOE/GO-102001-1187; NREL/TP-810-29564). National Renewable Energy Lab (NREL), USA.

    Google Scholar 

  • Isola P, Zhu J, Zhou T, et al. (2017). Image-to-image translation with conditional adversarial networks. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA.

  • Kamal R, Moloney F, Wickramaratne C, et al. (2019). Strategic control and cost optimization of thermal energy storage in buildings using EnergyPlus. Applied Energy, 246: 77–90.

    Article  Google Scholar 

  • Kennedy MC, O’Hagan A (2001). Bayesian calibration of computer models. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63: 425–464.

    Article  MathSciNet  MATH  Google Scholar 

  • Khayatian F, Nagy Z, Bollinger A (2021). Using generative adversarial networks to evaluate robustness of reinforcement learning agents against uncertainties. Energy and Buildings, 251: 111334.

    Article  Google Scholar 

  • Kim DW, Park CS (2011). Difficulties and limitations in performance simulation of a double skin façade with EnergyPlus. Energy and Buildings, 43: 3635–3645.

    Article  Google Scholar 

  • Kim YJ, Park CS (2016). Stepwise deterministic and stochastic calibration of an energy simulation model for an existing building. Energy and Buildings, 133: 455–468.

    Article  Google Scholar 

  • Kim YS, Shin HS, Park CS (2022). Model predictive lighting control for a factory building using a deep deterministic policy gradient. Journal of Building Performance Simulation, 15: 174–193.

    Article  Google Scholar 

  • Ledig C, Theis L, Huszár F, et al. (2017). Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.

  • Li Y, Liu S, Yang J, et al. (2017). Generative face completion. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.

  • Li B, Cheng F, Cai H, et al. (2021). A semi-supervised approach to fault detection and diagnosis for building HVAC systems based on the modified generative adversarial network. Energy and Buildings, 246: 111044.

    Article  Google Scholar 

  • Liu M, Claridge DE, Bensouda N (2003). High performance commercial building systems: manual of procedures for calibrating simulations of building systems, California Energy Commission (CEC).

  • Lunneberg TA (1999). Improving simulation accuracy through the use of short-term electrical end-use monitoring. In: Proceedings of the 6th International IBPSA Building Simulation Conference, Kyoto, Japan.

  • MacDonald I, Strachan P (2001). Practical application of uncertainty analysis. Energy and Buildings, 33: 219–227.

    Article  Google Scholar 

  • Martínez S, Eguía P, Granada E, et al. (2020). A performance comparison of multi-objective optimization-based approaches for calibrating white-box building energy models. Energy and Buildings, 216: 109942.

    Article  Google Scholar 

  • Nagpal S, Mueller C, Aijazi A, et al. (2019). A methodology for auto-calibrating urban building energy models using surrogate modeling techniques. Journal of Building Performance Simulation, 12: 1–16.

    Article  Google Scholar 

  • Oh S, Kim YJ, Park CS, Kim IH (2011). Process-driven BIM-based optimal design using integration of EnergyPlus, genetic algorithm, and pareto optimality. In: Proceedings of the 12th International IBPSA Building Simulation Conference, Sydney, Australia.

  • O’Neill Z, Eisenhower B (2013). Leveraging the analysis of parametric uncertainty for building energy model calibration. Building Simulation, 6: 365–377.

    Article  Google Scholar 

  • Paszke A, Gross S, Massa F, et al. (2019). PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NIPS’19).

  • GNU Affero General Public License]. Available at https://pypi.org/project/eppy/

  • Queiroz N, Westphal FS, Ruttkay et al. (2020). A performance-based design validation study on EnergyPlus for daylighting analysis. Building and Environment, 183: 107088.

    Article  Google Scholar 

  • Raftery P, Keane M, Costa A (2011a). Calibrating whole building energy models: Detailed case study using hourly measured data. Energy and Buildings, 43: 3666–3679.

    Article  Google Scholar 

  • Raftery P, Keane M, O’Donnell J (2011b). Calibrating whole building energy models: an evidence-based methodology. Energy and Buildings, 43: 2356–2364.

    Article  Google Scholar 

  • Raillon L, Ghiaus C (2018). An efficient Bayesian experimental calibration of dynamic thermal models. Energy, 152: 818–833.

    Article  Google Scholar 

  • Roberti F, Oberegger UF, Gasparella A (2015). Calibrating historic building energy models to hourly indoor air and surface temperatures: Methodology and case study. Energy and Buildings, 108: 236–243.

    Article  Google Scholar 

  • Rosso F, Ciancio V, Dell’Olmo J, et al. (2020). Multi-objective optimization of building retrofit in the Mediterranean climate by means of genetic algorithm application. Energy and Buildings, 216: 109945.

    Article  Google Scholar 

  • Sakiyama NRM, Mazzaferro L, Carlo JC, et al. (2021). Natural ventilation potential from weather analyses and building simulation. Energy and Buildings, 231: 110596.

    Article  Google Scholar 

  • Sobol IM (1967). On the distribution of points in a cube and the approximate evaluation of integrals. USSR Computational Mathematics and Mathematical Physics, 7: 86–112.

    Article  MathSciNet  MATH  Google Scholar 

  • Soebarto VI (1997). Calibration of hourly energy simulations using hourly monitored data and monthly utility records for two case study buildings. In: Proceedings of the 5th International IBPSA Building Simulation Conference, Prague, Czech Republic.

  • Shaham TR, Dekel T, Michaeli T (2019). SinGAN: Learning a generative model from a single natural image. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, R.O. Korea.

  • Shi Z, O’Brien W (2019). Sequential state prediction and parameter estimation with constrained dual extended Kalman filter for building zone thermal responses. Energy and Buildings, 183: 538–546.

    Article  Google Scholar 

  • Subbarao K (1988). PSTAR: Primary and secondary terms analysis and renormalization: a unified approach to building energy simulations and short-term monitoring (No. SERI/STR-254-3175). Solar Energy Research Institute (SERI).

  • Tardioli G, Narayan A, Kerrigan R, et al. (2020). A methodology for calibration of building energy models at district scale using clustering and surrogate techniques. Energy and Buildings, 226: 110309.

    Article  Google Scholar 

  • Tian W, Heo Y, de Wilde P, et al. (2018). A review of uncertainty analysis in building energy assessment. Renewable and Sustainable Energy Reviews, 93: 285–301.

    Article  Google Scholar 

  • Tian C, Li C, Zhang G, et al. (2019). Data driven parallel prediction of building energy consumption using generative adversarial nets. Energy and Buildings, 186: 230–243.

    Article  Google Scholar 

  • Tulyakov S, Liu M, Yang X, et al. (2018). MoCoGAN: decomposing motion and content for video generation. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

  • Waltz JP (1992). Practical experience in achieving high levels of accuracy in energy simulations of existing buildings. ASHRAE Transactions, 98 (1): 606–617.

    Google Scholar 

  • Wang Z, Hong T (2020). Generating realistic building electrical load profiles through the Generative Adversarial Network (GAN). Energy and Buildings, 224: 110299.

    Article  Google Scholar 

  • Ward R, Choudhary R, Gregory A, et al. (2021). Continuous calibration of a digital twin: comparison of particle filter and Bayesian calibration approaches. Data-Centric Engineering, 2: e15.

    Article  Google Scholar 

  • Yan K, Huang J, Shen W, Ji Z (2020a). Unsupervised learning for fault detection and diagnosis of air handling units. Energy and Buildings, 210: 109689.

    Article  Google Scholar 

  • Yan K, Chong A, Mo Y (2020b). Generative adversarial network for fault detection diagnosis of chillers. Building and Environment, 172: 106698.

    Article  Google Scholar 

  • Yan K (2021). Chiller fault detection and diagnosis with anomaly detective generative adversarial network. Building and Environment, 201: 107982.

    Article  Google Scholar 

  • Yang MD, Chen Y, Lin Y, et al. (2016). Multiobjective optimization using nondominated sorting genetic algorithm-II for allocation of energy conservation and renewable energy facilities in a campus. Energy and Buildings, 122: 120–130.

    Article  Google Scholar 

  • Yi DH, Kim DW, Park CS (2019). Parameter identifiability in Bayesian inference for building energy models. Energy and Buildings, 198: 318–328.

    Article  Google Scholar 

  • Yi DH, Kim DW, Park CS (2020). Prior selection method using likelihood confidence region and Dirichlet process Gaussian mixture model for Bayesian inference of building energy models. Energy and Buildings, 224: 110293.

    Article  Google Scholar 

  • Yi DH, Park CS (2021). Model selection for parameter identifiability problem in Bayesian inference of building energy model. Energy and Buildings, 245: 111059.

    Article  Google Scholar 

  • Zheng Y, Zhang Y, Zheng Z (2021). Continuous conditional generative adversarial networks (cGAN) with generator regularization. arXiv: 2103.14884.

  • Zhou Q, Xing J, Yang Q, et al. (2021). Enabling non-intrusive occupant activity modeling using WiFi signals and a generative adversarial network. Energy and Buildings, 249: 111228.

    Article  Google Scholar 

  • Zhu J, Park T, Isola P, et al. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.

  • Zhu C, Tian W, Yin B, et al. (2020). Uncertainty calibration of building energy models by combining approximate Bayesian computation and machine learning algorithms. Applied Energy, 268: 115025.

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the Korea Institute of Energy Technology Evaluation and Planning(KETEP) and the Ministry of Trade, Industry & Energy(MOTIE) of the Republic of Korea (No. 20202020800360).

Author information

Authors and Affiliations

  1. Department of Architecture and Architectural Engineering, College of Engineering, Seoul National University, Seoul, 08826, R.O. Korea

    Hansol Shin & Cheol-Soo Park

  2. Institute of Construction and Environmental Engineering, Institute of Engineering Research, College of Engineering, Seoul National University, Seoul, 08826, R.O. Korea

    Cheol-Soo Park

Authors
  1. Hansol Shin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Cheol-Soo Park
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Cheol-Soo Park.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shin, H., Park, CS. Parameter estimation for building energy models using GRcGAN. Build. Simul. 16, 629–639 (2023). https://doi.org/10.1007/s12273-022-0965-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12273-022-0965-1

Keywords

Search

Navigation