International Scientific Journal

Thermal Science - Online First

online first only

Classification of retrofit measures for residential buildings according to the global cost

Data-driven black-box surrogate models are widely used in research related to buildings energy efficiency. They are based on machine learning techniques, learn from available data, and act as a replacement for or an addition to complex and computationally intensive knowledge-based models. Surrogate models can predict energy demand, indoor air temperature, or occupants behavior; explore search space in optimization problems; learn control rules; etc. This paper analyzes surrogate models that classify building retrofit measures directly according to the global cost. In addition, they quantify the importance of each variable for the classification process. The models are based on random forest classifiers, which are fast and powerful ensemble learners. They can be applied to effectively reduce search spaces when optimizing energy renovation measures or to rapidly identify projects that deserve financial support. This approach is applied to two residential buildings and three scenarios of price development. The training process uses a small share of retrofit options assessed with standard calculations of the heating and cooling demands, as well as the global cost. The results show very high classification performance, even when the models are trained with small and imbalanced training sets. The obtained recall, precision, and F-score values are mostly above 95%, except for extremely small training sets.
PAPER REVISED: 2020-09-26
PAPER ACCEPTED: 2020-09-27
  1. ****, Directive (EU) 2018/844 of the European Parliament and of the Council of 30 May 2018 amending Directive 2010/31/EU on the energy performance of buildings and Directive 2012/27/EU on energy efficiency (Text with EEA relevance), Official Journal of the European Union L 156 (2018), pp. 75-91
  2. ****, Commission recommendation (EU) 2016/1318 of 29 July 2016 on guidelines for the promotion of nearly zero-energy buildings and best practices to ensure that, by 2020, all new buildings are nearly zero-energy buildings, Official Journal of the European Union L 208 (2016), pp. 46-57
  3. ****, SRPS EN 15459-1:2017 Energy performance of buildings - Economic evaluation procedure for energy systems in buildings - Part 1: Calculation procedures, Module M1-14, Institute for Standardization of Serbia, 2017
  4. Deb C. et al., A review on time series forecasting techniques for building energy consumption, Renewable and Sustainable Energy Reviews 74 (2017), pp. 902-924
  5. Shirazi A., Ashuri B., Embodied Life Cycle Assessment (LCA) comparison of residential building retrofit measures in Atlanta, Building and Environment 171 (2020), 106644.
  6. Kassai M., Prediction of the HVAC energy demand and consumption of a single family house with different calculation methods, Energy Procedia 112 (2017) pp. 585-594.
  7. Foucquier A. et al., State of the art in building modelling and energy performances prediction: A review, Renewable and Sustainable Energy Reviews 23 (2013), pp. 272-288
  8. Sun Y. et al., A review of the-state-of-the-art in data-driven approaches for building energy prediction, Energy & Buildings 221 (2020), 110022
  9. Marasco D. E., Kontokosta C. E., Applications of machine learning methods to identifying and predicting building retrofit opportunities, Energy and Buildings 128 (2016), pp. 431-441
  10. Mosavi A. et al., State of the Art of Machine Learning Models in Energy Systems, a Systematic Review, Energies 12 (2019), 7, 1301
  11. Zeng A. et al., Prediction of building electricity usage using Gaussian Process Regression, Journal of Building Engineering 28 (2020), 101054
  12. Sretenovi´c A. A. et al., Support Vector Machine for the Prediction of Heating Energy Use, Thermal Science 22 (2018), Suppl. 4, pp. S1171-S1181
  13. Seyedzadeh S. et al., Tuning machine learning models for prediction of building energy loads, Sustainable Cities and Society 47 (2019) 101484
  14. Seyedzadeh S. et al., Data driven model improved by multi-objective optimisation for prediction of building energy loads, Automation in Construction 116 (2020), 103188
  15. Dai X. et al., A review of studies applying machine learning models to predict occupancy and windowopening behaviours in smart buildings, Energy & Buildings 223 (2020), 110159
  16. Deb C. et al., Using artificial neural networks to assess HVAC related energy saving in retrofitted office buildings, Solar Energy 163 (2018), pp. 32-44
  17. Rätz M. et al., Automated data-driven modeling of building energy systems via machine learning algorithms, Energy & Buildings 202 (2019), 109384
  18. Wang Z. et al., Building thermal load prediction through shallow machine learning and deep learning, Applied Energy 263 (2020), 114683
  19. Bui D.-K. et al., An artificial neural network (ANN) expert system enhanced with the electromagnetism-based firefly algorithm (EFA) for predicting the energy consumption in buildings, Energy 190 (2020), 116370
  20. Gan V. J. L. et al., Simulation optimisation towards energy efficient green buildings: Current status and future trends, Journal of Cleaner Production 254 (2020), 120012
  21. Asadi E. et al., Multi-objective optimization for building retrofit: A model using genetic algorithm and artificial neural network and an application, Energy and Buildings 81 (2014), pp. 444-456
  22. Ascione F. et al., CASA, cost-optimal analysis by multi-objective optimisation and artificial neural networks: A new framework for the robust assessment of cost-optimal energy retrofit, feasible for any building, Energy and Buildings 146 (2017), pp. 200-219
  23. Gossard D. et al., Multi-objective optimization of a building envelope for thermal performance using genetic algorithms and artificial neural network, Energy and Buildings 67 (2013), pp. 253-260
  24. Sharif S. A., Hammad A., Developing surrogate ANN for selecting near-optimal building energy renovation methods considering energy consumption, LCC and LCA, Journal of Building Engineering 25 (2019), 100790
  25. Chen X., Yang H., A multi-stage optimization of passively designed high-rise residential buildings in multiple building operation scenarios, Applied Energy 206 (2017), pp. 541-557
  26. Chou J.-S., Tran D.-S., Forecasting energy consumption time series using machine learning techniques based on usage patterns of residential householders, Energy 165 (2018), pp. 709-726
  27. Gong M. et al., Heat load prediction of residential buildings based on discrete wavelet transform and tree-based ensemble learning, Journal of Building Engineering 32 (2020), 101455
  28. Rahman A. et al., Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks, Applied Energy 212 (2018), pp. 372-385
  29. Rahman A., Smith A., Predicting heating demand and sizing a stratified thermal storage tank using deep learning algorithms, Applied Energy 228 (2018), pp. 108-121
  30. Mawson V. J., Hughes B. R., Deep learning techniques for energy forecasting and condition monitoring in the manufacturing sector, Energy & Buildings 217 (2020), 109966
  31. Smarra F., Data-driven model predictive control using random forests for building energy optimization and climate control, Applied Energy 226 (2018), pp. 1252-1272
  32. Wang J. et al., Data-driven model predictive control for building climate control: Three case studies on different buildings, Building and Environment 160 (2019), 106204
  33. Carreira P., et al., Can HVAC really learn from users? A simulation-based study on the effectiveness of voting for comfort and energy use optimization, Sustainable Cities and Society 41 (2018), pp. 275-285
  34. Jin X. et al., Foresee: A user-centric home energy management system for energy efficiency and demand response, Applied Energy 205 (2017), pp. 1583-1595
  35. Drgoˇna J. et al., Approximate model predictive building control via machine learning, Applied Energy 218 (2018), pp. 199-216
  36. Ngarambe J. et al., The use of artificial intelligence (AI) methods in the prediction of thermal comfort in buildings: energy implications of AI-based thermal comfort controls, Energy & Buildings 211 (2020), 109807
  37. Yang S. et al., Model predictive control with adaptive machine-learning-based model for building energy efficiency and comfort optimization, Applied Energy 271 (2020), 115147
  38. Cui B. et al., A hybrid building thermal modeling approach for predicting temperatures in typical, detached, two-story houses, Applied Energy 236 (2019), pp. 101-116
  39. Runge J. et al., Hybrid short-term forecasting of the electric demand of supply fans using machine learning, Journal of Building Engineering 29 (2020), 101144
  40. Rankovic´ A. M., C´ etenovic´ D. N., Modeling of Photovoltaic Modules Using a Gray-Box Neural Network Approach, Thermal Science 21 (2017), 6B, pp. 2837-2850
  41. Ghahramani A. et al., Learning occupants' workplace interactions from wearable and stationary ambient sensing systems, Applied Energy 230 (2018), pp. 42-51
  42. Domahidi A. et al., Learning decision rules for energy efficient building control, Journal of Process Control 24 (2014), pp. 763-772
  43. Gonzalez D. et al., Automatic detection of building typology using deep learning methods on street level images, Building and Environment 177 (2020), 106805
  44. Banihashemi S. et al., Developing a hybrid model of prediction and classification algorithms for building energy consumption, Energy Procedia 110 (2017), pp. 371-376
  45. Miller C. et al., A review of unsupervised statistical learning and visual analytics techniques applied to performance analysis of non-residential buildings, Renewable and Sustainable Energy Reviews 81 (2018), pp. 1365-1377
  46. Jovanovi´c R. Ž. et al.: Multistage Ensemble of Feedforward Neural Networks for Prediction of Heating Energy Consumption, Thermal Science 20, (2016), 4, pp. 1321-1331
  47. Ding Y. et al., Effect of input variables on cooling load prediction accuracy of an office building, Applied Thermal Engineering 128 (2018), pp. 225-234
  48. Westermann P. et al., Unsupervised learning of energy signatures to identify the heating system and building type using smart meter data, Applied Energy 264 (2020), 114715
  49. Wang Z., Hong T., Reinforcement learning for building controls: The opportunities and challenges, Applied Energy 269 (2020), 115036
  50. Liu T. et al., A novel deep reinforcement learning based methodology for short-term HVAC system energy consumption prediction, International Journal of Refrigeration 107 (2019), pp. 39-51
  51. Mason K., Grijalva S., A review of reinforcement learning for autonomous building energy management, Computers and Electrical Engineering 78 (2019), pp. 300-312
  52. Stojiljkovi´c M. M. et al., Cost-optimal energy retrofit for Serbian residential buildings connected to district heating systems, Thermal Science 23 (2019), Suppl. 5, pp. 1707-1717
  53. ****, Rulebook on energy efficiency of buildings, Official Gazette of the Republic of Serbia 61 (2011) (In Serbian)
  54. Breiman L., Random Forests, Machine Learning 45 (2001), pp. 5-32
  55. Ahmad M. W. et al., Trees vs Neurons: Comparison between random forest and ANN for highresolution prediction of building energy consumption, Energy and Buildings 147 (2017), pp. 77-89
  56. Huchuk B. et al., Comparison of machine learning models for occupancy prediction in residential buildings using connected thermostat data, Building and Environment 160 (2019), 106177