Skip to main content

Neural network, ARX, and extreme learning machine models for the short-term prediction of temperature in buildings

Abstract

In this paper, the possibilities of developing machine learning based data-driven models for the short-term prediction of indoor temperature within prediction horizons ranging from 1 hour up to 12 hours are systematically investigated. The study was based on a TRNSYS emulation of a residential building heated by a heat pump, combined with measured weather data for a typical winter season in Ljubljana, Slovenia. Autoregressive models with exogenous inputs (ARX), neural network models (NN), and extreme learning machine models (ELM) are considered. The results confirm the finding that nonlinear models, particularly the NN model trained by regularization, consistently outperform linear models in both fitting and generalization performance, so they are the recommended choice as predictive models. The availability of future weather data considerably improved the predictive performance of all the tested models. Besides data about the future outdoor temperature, also data about future expected solar radiation significantly improve predictions of temperature in buildings. The linear models required embedding dimensions of 24 hours for accurate predictions, whereas the nonlinear models were not very sensitive to the use of past data. Nonlinear models required about three months of training data to reach good predictive performance, whereas the linear models converged to accurate predictions within six weeks. The RMSE prediction errors, averaged over all the data sets and all the prediction horizons, are within the range between 0.155 °C for the linear ARX model (in the case of no future available weather data), and 0.065 °C for the neural network model (in the case of available future weather data).

This is a preview of subscription content, access via your institution.

References

  • Afroz Z, Shafiullah GM, Urmee T, Higgins G (2018). Modeling techniques used in building HVAC control systems: A review. Renewable and Sustainable Energy Reviews, 83: 64–84.

    Article  Google Scholar 

  • Ahmad T, Chen H, Guo Y, Wang J (2018). A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: A review. Energy and Buildings, 165: 301–320.

    Article  Google Scholar 

  • Al-Saadi SN, Zhai Z (2015). A new validated TRNSYS module for simulating latent heat storage walls. Energy and Buildings, 109: 274–290.

    Article  Google Scholar 

  • Amasyali K, El-Gohary NM (2018). A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 81: 1192–1205.

    Article  Google Scholar 

  • Arabzadeh V, Alimohammadisagvand B, Jokisalo J, Siren K (2018). A novel cost-optimizing demand response control for a heat pump heated residential building. Building Simulation, 11: 533–547.

    Article  Google Scholar 

  • ARSO (2017). Weather reference year for Ljubljana, Slovenia. Available at https://doi.org/www.meteo.si/met/en/climate/tables/test_ref_year. Accessed 24 Apr 2018.

    Google Scholar 

  • Bamdad K, Cholette ME, Guan L, Bell J (2018). Building energy optimisation under uncertainty using ACOMV algorithm. Energy and Buildings, 167: 322–333.

    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 

  • Cortes C, Vapnik V (1995). Support-vector networks. Machine Learning, 20: 273–297.

    MATH  Google Scholar 

  • Crawley DB, Hand JW, Kummert M, Griffith BT (2008). Contrasting the capabilities of building energy performance simulation programs. Building and Environment, 43: 661–673.

    Article  Google Scholar 

  • Deb C, Zhang F, Yang J, Lee SE, Shah KW (2017). A review on time series forecasting techniques for building energy consumption. Renewable and Sustainable Energy Reviews, 74: 902–924.

    Article  Google Scholar 

  • Ding S, Xu X, Nie R (2014). Extreme learning machine and its applications. Neural Computing and Applications, 25: 549–556.

    Article  Google Scholar 

  • Ding Y, Zhang Q, Yuan T, Yang K (2018). Model input selection for building heating load prediction: A case study for an office building in Tianjin. Energy and Buildings, 159: 254–270.

    Article  Google Scholar 

  • Do H, Cetin KS (2018). Residential building energy consumption: A review of energy data availability, characteristics, and energy performance prediction methods. Current Sustainable/Renewable Energy Reports, 5: 76–85.

    Article  Google Scholar 

  • Draper NR, Smith H (1998). Applied Regression Analysis, 3rd edn. New York: John Wiley & Sons.

    Book  Google Scholar 

  • Drissi Lamrhari EH, Benhamou B (2018). Thermal behavior and energy saving analysis of a flat with different energy efficiency measures in six climates. Building Simulation, 11: 1123–1144.

    Article  Google Scholar 

  • Fan C, Xiao F, Zhao Y (2017). A short-term building cooling load prediction method using deep learning algorithms. Applied Energy, 195: 222–233.

    Article  Google Scholar 

  • Fanger PO (1970). Thermal Comfort: Analysis and Applications in Environmental Engineering. New York: McGraw-Hill.

    Google Scholar 

  • Ferracuti F, Fonti A, Ciabattoni L, Pizzuti S, Arteconi A, Helsen L, Comodi G (2017). Data-driven models for short-term thermal behaviour prediction in real buildings. Applied Energy, 204: 1375–1387.

    Article  Google Scholar 

  • Foresee FD, Hagan MT (1997). Gauss-Newton Approximation to Bayesian Learning. In: Proceedings of the International Joint Conference on Neural Networks, Houston, Texas, pp. 1930–1935.

    Google Scholar 

  • Foucquier A, Robert S, Suard F, Stéphan L, Jay A (2013). State of the art in building modelling and energy performances prediction: A review. Renewable and Sustainable Energy Reviews, 23: 272–288.

    Article  Google Scholar 

  • Gang W, Wang J, Wang S (2014). Performance analysis of hybrid ground source heat pump systems based on ANN predictive control. Applied Energy, 136: 1138–1144.

    Article  Google Scholar 

  • Guo Y, Wang J, Chen H, Li G, Liu J, Xu C, Huang R, Huang Y (2018). Machine learning-based thermal response time ahead energy demand prediction for building heating systems. Applied Energy, 221: 16–27.

    Article  Google Scholar 

  • Hagan MT, Menhaj MB (1994). Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5: 989–993.

    Article  Google Scholar 

  • Haykin S (2009). Neural Networks and Learning Machines, 3rd edn. Hoboken, NJ, USA: Pearson.

    Google Scholar 

  • Hong T, Langevin J, Sun K (2018). Building simulation: Ten challenges. Building Simulation, 11: 871–898.

    Article  Google Scholar 

  • Huang G-B, Zhu Q-Y, Siew C-K (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70: 489–501.

    Article  Google Scholar 

  • Huang G, Huang G-B, Song S, You K (2015). Trends in extreme learning machines: A review. Neural Networks, 61: 32–48.

    Article  Google Scholar 

  • Huang S, Zuo W, Sohn MD (2018). A Bayesian Network model for predicting cooling load of commercial buildings. Building Simulation, 11: 87–101.

    Article  Google Scholar 

  • ISO 13790 (2008). Energy performance of buildings — Calculation of energy use for space heating and cooling. Geneva: International Organization for Standardization.

    Google Scholar 

  • Kalogirou SA (2001). Artificial neural networks in renewable energy systems applications: A review. Renewable and Sustainable Energy Reviews, 5: 373–401.

    Article  Google Scholar 

  • Killian M, Kozek M (2018). Implementation of cooperative Fuzzy model predictive control for an energy-efficient office building. Energy and Buildings, 158: 1404–1416.

    Article  Google Scholar 

  • Klein S, Beckman W, Mitchell J, Duffie J, Duffie N, Freeman T (2013). TRNSYS 17: A transient system simulation program.

  • Li Q, Meng Q, Cai J, Yoshino H, Mochida A (2009). Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks. Energy Conversion and Management, 50: 90–96.

    Article  Google Scholar 

  • Li X, Wen J (2014). Review of building energy modeling for control and operation. Renewable and Sustainable Energy Reviews, 37: 517–537.

    Article  Google Scholar 

  • Lindelöf D, Afshari H, Alisafaee M, Biswas J, Caban M, Mocellin X, Viaene J (2015). Field tests of an adaptive, model-predictive heating controller for residential buildings. Energy and Buildings, 99: 292–302.

    Article  Google Scholar 

  • Liu X, Gao C, Li P (2012). A comparative analysis of support vector machines and extreme learning machines. Neural Networks, 33: 58–66.

    Article  Google Scholar 

  • Liu Z, Wu D, Liu Y, Han Z, Lun L, Gao J, Jin G, Cao G (2019). Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction. Energy Exploration & Exploitation, https://doi.org/10.1177/0144598718822400.

    Google Scholar 

  • Lu S, Zhao Y, Fang K, Li Y, Sun P (2017). Establishment and experimental verification of TRNSYS model for PCM floor coupled with solar water heating system. Energy and Buildings, 140: 245–260.

    Article  Google Scholar 

  • Magalhães SMC, Leal VMS, Horta IM (2017). Modelling the relationship between heating energy use and indoor temperatures in residential buildings through Artificial Neural Networks considering occupant behavior. Energy and Buildings, 151: 332–343.

    Article  Google Scholar 

  • Oldewurtel F, Parisio A, Jones CN, Gyalistras D, Gwerder M, Stauch V, Lehmann B, Morari M (2012). Use of model predictive control and weather forecasts for energy efficient building climate control. Energy and Buildings, 45: 15–27.

    Article  Google Scholar 

  • Pang X, Duarte C, Haves P, Chuang F (2018). Testing and demonstration of model predictive control applied to a radiant slab cooling system in a building test facility. Energy and Buildings, 172: 432–441.

    Article  Google Scholar 

  • Pedersen L (2007). Use of different methodologies for thermal load and energy estimations in buildings including meteorological and sociological input parameters. Renewable and Sustainable Energy Reviews, 11: 998–1007.

    Article  Google Scholar 

  • Potočnik P, Vidrih B, Kitanovski A, Govekar E (2018). Analysis and optimization of thermal comfort in residential buildings by means of a weather-controlled air-to-water heat pump. Building and Environment, 140: 68–79.

    Article  Google Scholar 

  • Prívara S, Cigler J, Váňa Z, Oldewurtel F, Sagerschnig C, Žáčeková E (2013). Building modeling as a crucial part for building predictive control. Energy and Buildings, 56: 8–22.

    Article  Google Scholar 

  • Reynders G, Diriken J, Saelens D (2014). Quality of grey-box models and identified parameters as function of the accuracy of input and observation signals. Energy and Buildings, 82: 263–274.

    Article  Google Scholar 

  • Ríos-Moreno GJ, Trejo-Perea M, Castañeda-Miranda R, Hernández-Guzmán VM, Herrera-Ruiz G (2007). Modelling temperature in intelligent buildings by means of autoregressive models. Automation in Construction, 16: 713–722.

    Article  Google Scholar 

  • Robinson C, Dilkina B, Hubbs J, Zhang W, Guhathakurta S, Brown MA, Pendyala RM (2017). Machine learning approaches for estimating commercial building energy consumption. Applied Energy, 208: 889–904.

    Article  Google Scholar 

  • Romero Rodríguez L, Sánchez Ramos J, Álvarez Domínguez S, Eicker U (2018). Contributions of heat pumps to demand response: A case study of a plus-energy dwelling. Applied Energy, 214: 191–204.

    Article  Google Scholar 

  • Safa AA, Fung AS, Kumar R (2015). Heating and cooling performance characterisation of ground source heat pump system by testing and TRNSYS simulation. Renewable Energy, 83: 565–575.

    Article  Google Scholar 

  • Schmelas M, Feldmann T, Bollin E (2017). Savings through the use of adaptive predictive control of thermo-active building systems (TABS): A case study. Applied Energy, 199: 294–309.

    Article  Google Scholar 

  • Serale G, Fiorentini M, Capozzoli A, Bernardini D, Bemporad A (2018). Model predictive control (MPC) for enhancing building and HVAC system energy efficiency: Problem formulation, applications and opportunities. Energies, 11: 631.

    Article  Google Scholar 

  • Smarra F, Jain A, de Rubeis T, Ambrosini D, D’Innocenzo A, Mangharam R (2018). Data-driven model predictive control using random forests for building energy optimization and climate control. Applied Energy, 226: 1252–1272.

    Article  Google Scholar 

  • Soldo B, Potočnik P, Šimunović G, Šarić T, Govekar E (2014). Improving the residential natural gas consumption forecasting models by using solar radiation. Energy and Buildings, 69: 498–506.

    Article  Google Scholar 

  • Villa-Arrieta M, Sumper A (2018). A model for an economic evaluation of energy systems using TRNSYS. Applied Energy, 215: 765–777.

    Article  Google Scholar 

  • Wang L, Kubichek R, Zhou X (2018). Adaptive learning based data-driven models for predicting hourly building energy use. Energy and Buildings, 159: 454–461.

    Article  Google Scholar 

  • Wei Y, Zhang X, Shi Y, Xia L, Pan S, Wu J, Han M, Zhao Z (2018). A review of data-driven approaches for prediction and classification of building energy consumption. Renewable and Sustainable Energy Reviews, 82: 1027–1047.

    Article  Google Scholar 

  • Yun K, Luck R, Mago PJ, Cho H (2012). Building hourly thermal load prediction using an indexed ARX model. Energy and Buildings, 54: 225–233.

    Article  Google Scholar 

  • Žáčeková E, Váňa Z, Cigler J (2014). Towards the real-life implementation of MPC for an office building: Identification issues. Applied Energy, 135: 53–62.

    Article  Google Scholar 

  • Zygierewicz A (2016). Implementation of the Energy Efficiency Directive (2012/27/EU): Energy Efficiency Obligation Schemes.

Download references

Acknowledgements

This work was supported by ARRS — the Slovenian Research Agency, Research program P2-0241 “Synergetics of complex systems and processes”, and was co-financed by the Republic of Slovenia and the European Union under the European Regional Development Fund.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Primož Potočnik.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Potočnik, P., Vidrih, B., Kitanovski, A. et al. Neural network, ARX, and extreme learning machine models for the short-term prediction of temperature in buildings. Build. Simul. 12, 1077–1093 (2019). https://doi.org/10.1007/s12273-019-0548-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12273-019-0548-y

Keywords

  • predictive models
  • neural networks
  • ARX model
  • extreme learning machines
  • residential buildings
  • indoor temperature