Skip to main content

Influencing factors in energy use of housing blocks: a new methodology, based on clustering and energy simulations, for decision making in energy refurbishment projects


In recent years, big efforts have been dedicated to identify which are the factors with highest influence in the energy consumption of residential buildings. These factors include aspects such as weather dependence, user behaviour, socio-economic situation, type of the energy installations and typology of buildings. The high number of factors increases the complexity of analysis and leads to a lack of confidence in the results of the energy simulation analysis. This fact grows when we move one step up and perform global analysis of blocks of buildings. The aim of this study is to report a new methodology for the assessment of the energy performance of large groups of buildings when considering the real use of energy. We combine two clustering methods, Generative Topographic Mapping and k-means, to obtain reference dwellings that can be considered as representative of the different energy patterns and energy systems of the neighbourhood. Then, simulation of energy demand and indoor temperature against the monitored comfort conditions in a short period is performed to obtain end use load disaggregation. This methodology was applied in a district at Terrassa City (Spain), and six reference dwellings were selected. Results showed that the method was able to identify the main patterns and provide occupants with feasible recommendations so that they can make required decisions at neighbourhood level. Moreover, given that the proposed method is based on the comparison with similar buildings, it could motivate building occupants to implement community improvement actions, as well as to modify their behaviour.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9



International Energy Agency–Energy in Building and Communities


European Union Energy Performance of Buildings Directive


Energy use intensity


  • American Society of Heating, Refrigerating and Air-Conditioning Engineers. (ASHRAE). (1999). Handbook of HVAC applications. Chapter 38 (pp. 8–9).

    Google Scholar 

  • Bishop, C. M., Svensén, M., & Williams, C. K. I. (1998). GTM: the Generative Topographic Mapping. Neural Computation, 10(1), 215–234.

    Article  MATH  Google Scholar 

  • Bishop, C. M. (1998). Latent variable models. In Learning in graphical models (pp. 371–403). Netherlands: Springer.

    Chapter  Google Scholar 

  • Chicco, G. (2012). Overview and performance assessment of the clustering methods for electrical load pattern grouping. Energy, 42, 68–80. doi:10.1016/

    Article  Google Scholar 

  • Chicco, G., Napoli, R., Postolache, P., Scutariu, M., & Toader, C. (2003). Customer characterization options for improving the tariff offer. IEEE Transactions on Power Systems, 18, 381–387. doi:10.1109/TPWRS.2002.807085.

    Article  Google Scholar 

  • Código Técnico de la Edificación (CTE). (1999). Ley 38/1999 de 5 de Noviembre, de Ordenación de la Edificación (LOE). Spain: Ministerio de Industria.

    Google Scholar 

  • Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed.). Hillsdale, NJ: Erlbaum.

    MATH  Google Scholar 

  • Cruz, R., & Vellido, A. (2011). Semi-supervised analysis of human brain tumours from partially labelled MRS information, using manifold learning models. International Journal of Neural Systems, 21, 17–29.

    Article  Google Scholar 

  • Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39(1), 1–38.

    MathSciNet  MATH  Google Scholar 

  • Directive 2010/31/EU of the European Parliament and of the Council of 19 May 2010 on the energy performance of buildings. European Commission (2010).

  • EnergyPlus Energy Simulation Software (v6), US Department of Energy (2009).

  • Etchells, T. A., Nebot, A., Vellido, A., Lisboa, P. J. G., & Mugica, F. (2006). Learning what is important: feature selection and rule extraction in a virtual course (Proceedings of the 14th European Symposium on Artificial Neural Networks (ESANN 2006), Bruges, Belgium, pp. 401–406).

    Google Scholar 

  • Evans, J. D. (1996). Straightforward statistics for the behavioral sciences. Pacific Grove: Brooks/Cole Publishing.

    Google Scholar 

  • Giampietro, M., Mayumi, K., & Sorman, A. H. (2011). The metabolic pattern of societies: where economists fall short. London: Routledge.

    Google Scholar 

  • Goldstein, D. B., & Eley. (2014). A classification of building energy performance indices. Energy Efficiency, 7, 353–375. doi:10.1007/s12053-013-9248-0.

    Article  Google Scholar 

  • International Energy Agency Energy Conservation in Buildings and Community Systems Programme, (IEA-CBCS) (2010) Annex 33: energy related environmental impact in buildings.

  • International Energy Agency Energy Conservation in Buildings and Community Systems Programme, (IEA-CBCS) Annex 53 (2013). Total energy use in buildings: analysis & evaluation methods. Final report of ST-C—statistical analysis and prediction methods, Chapter 10—statistical analysis of total energy use.

  • Jain, A. K. (2010). Data clustering: 50 years beyond k-means. Pattern Recognition Letters, 31(8), 651–666.

    Article  Google Scholar 

  • Kavgic, M., Mavrogianni, A., Mumovic, D., Summerfield, A., Stevanovic, Z., & Djurovic-Petrovic, M. (2010). A review of bottom-up building stock models for energy consumption in the residential sector. Building and Environment, 45, 1683–1697. doi:10.1016/j.buildenv.2010.01.021.

    Article  Google Scholar 

  • Kohonen, T. (2001). Self-organizing maps (3rd ed.). Berlin: Springer-Verlag.

    Book  MATH  Google Scholar 

  • Li, C., Hong, T., & Yan, D. (2014). An insight into actual energy use and its drivers in high-performance buildings. Applied Energy, 131, 394–410.

    Article  Google Scholar 

  • Li, X., Bowers, C. P., & Schnier, T. (2010). Classification of energy consumption in buildings with outlier detection. IEEE Transactions on Industrial Electronics, 57, 3639–3644. doi:10.1109/TIE.2009.2027926.

    Article  Google Scholar 

  • Lopes, L., Hokoi, S., Miura, H., & Shuhei, K. (2005). Energy efficiency and energy savings in Japanese residential buildings—research methodology and surveyed results. Energy and Buildings, 37, 698–706. doi:10.1016/j.enbuild.2004.09.019.

    Article  Google Scholar 

  • Mata, E., Sasic Kalagasidis, A., & Johnsson, F. (2014). Building-stock aggregation through archetype buildings: France, Germany, Spain and the UK. Building and Environment, 81, 270–282. doi:10.1016/j.buildenv.2014.06.013.

    Article  Google Scholar 

  • McLoughlin, F., Duffy, A., Conlon, M., (2012). Analysing domestic electricity smart metering data using self organising maps. Lisbon: CIRED Workshop.

  • Mooi, E., & Sarstedt, M. (2014). A concise guide to market research: the process, data, and methods using IBM SPSS. Springer Books. ISBN: 978-3-642-53964-0 (Print) 978-3-642-53965-7 (Online)

  • Murray, S. N., Walsh, B. P., Kelliher, D., & O’Sullivan, D. T. J. (2014). Multi-variable optimization of thermal energy efficiency retrofitting of buildings using static modelling and genetic algorithms—a case study. Building and Environment, 75, 98–107. doi:10.1016/j.buildenv.2014.01.011.

    Article  Google Scholar 

  • Nakagami, H. (1996). Lifestyle change and energy use in Japan: household equipment and energy consumption. Energy, 21, 1157–1167.

    Article  Google Scholar 

  • Oca, S. D., & Hong, T. (2014). A data-mining approach to discover patterns of window opening and closing behavior in offices. Building and Environment, 82, 726–739.

    Article  Google Scholar 

  • Oca, S. D., & Hong, T. (2015). Occupancy schedules learning process through a data mining framework. Energy & Buildings, 88, 395–408.

    Article  Google Scholar 

  • Ourghi, R., Al-Anzi, A., & Krarti, M. (2007). A simplified analysis method to predict the impact of shape on annual energy use for office buildings. Energy Conversion and Management, 48, 300–305. doi:10.1016/j.enconman.2006.04.011.

    Article  Google Scholar 

  • Pedrini, A., Westphal, F. S., & Lamberts, R. (2002). A methodology for building energy modelling and calibration in warm climates. Building and environment, Elsevier, 37(8-9), 903–912.

    Article  Google Scholar 

  • Räsänen, T., Ruskanen, J., & Kolehmainen, M. (2008). Reducing energy consumption by using self-organizing maps to create more personalized electricity use information. Applied Energy, 85, 830–840. doi:10.1016/j.apenergy.2007.10.012.

    Article  Google Scholar 

  • Ren, X., Yan, D., & Hong, T. (2015). Data mining of space heating system performance in affordable housing. Building and Environment, 89, 1–13.

    Article  Google Scholar 

  • Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Computational and Applied Mathematics, 20, 53–65. doi:10.1016/0377-0427(87)90125-7.

    Article  MATH  Google Scholar 

  • Salmerón, J. M., Cerezuela, A., & Salmerón, R. (2009). Escala de calificación energética para edificios existentes. Cuadernos de Eficiencia Energética: Publicaciones IDAE, Madrid, Spain.

    Google Scholar 

  • Swan, L., Ugursal, V. I., & Beausoleil-Morrison, I. (2009). Implementation of a Canadian residential energy end-use model for assessing new technology impacts (pp. 1429–1436). Glasgow: Proceedings of Building Simulation.

    Google Scholar 

  • Tosi, A., Olier, I., & Vellido, A. (2014). Probability ridges and distortion flows: visualizing multivariate time series using a variational Bayesian manifold learning method. 10th Workshop on Self-Organizing Maps (WSOM 2014). Advances in Intelligent Systems and Computing, 295, 55–64.

    Article  Google Scholar 

  • Tosi, A., & Vellido, A. (2013). Robust cartogram visualization of outliers in manifold learning (Proceedings of the 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2013), Bruges, Belgium, pp. 555–560).

    Google Scholar 

  • Tsekouras, G. J., Kotoulas, P. B., Tsirekis, C. D., Dialynas, E. N., & Hatziargyriou, N. D. (2008). A pattern recognition methodology for evaluation of load profiles and typical days of large electricity customers. Electric Power Systems Research, 78, 1494–1510. doi:10.1016/j.epsr.2008.01.010.

    Article  Google Scholar 

  • Ueno, T., Sano, F., Saeki, O., & Tsuji, K. (2006). Effectiveness of an energy-consumption information system on energy savings in residential houses based on monitored data. Applied Energy, 83, 166–183. doi:10.1016/j.apenergy.2005.02.002.

    Article  Google Scholar 

  • Vellido, A., Martí, E., Comas, J., Rodríguez-Roda, I., & Sabater, F. (2007). Exploring the ecological status of human altered streams through Generative Topographic Mapping. Environmental Modelling & Software, 22(7), 1053–1065.

    Article  Google Scholar 

  • Vellido, A., Martín, J. D., Rossi, F., & Lisboa, P. J. G. (2011). Seeing is believing: the importance of visualization in real-world machine learning applications (Procs. of the 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2011), pp. 219–226).

    Google Scholar 

  • Yang, Z., & Becerik-Gerber, B. (2014). Modeling personalized occupancy profiles for representing long term patterns by using ambient context. Building and Environment, 78, 23–35. doi:10.1016/j.buildenv.2014.04.003.

    Article  Google Scholar 

  • Yu, Z., Fung, B. C. M., Haghighat, F., Yoshino, H., & Morofsky, E. (2011). A systematic procedure to study the influence of occupant behaviour on building energy consumption. Energy and Buildings, 43, 1409–1417. doi:10.1016/j.enbuild.2011.02.002.

    Article  Google Scholar 

  • Yu, Z., Haghighat, F., Fung, B. C. M., & Yoshino, H. (2010). A decision tree method for building energy demand modelling. Energy and Buildings, 42, 1637–1646. doi:10.1016/j.enbuild.2010.04.006.

    Article  Google Scholar 

Download references


Xavier Cipriano is thankful to the Catalan Housing Agency of the Catalan Government for funding the main research, as well as to María Heras, Nuria Cardellach, and Eduard Calderón for their participation in the energy audits and surveys to tenants. We also are thankful to Dr. Nicolas Kosoy for his suggestions in the socio-economic analysis of surveys, as well as the Can Jofresa’s neighbour association for their answers and information about their homes. Jaime Martí-Herrero is thankful to the Prometeo Project of the Secretariat for Higher Education, Science, Technology and Innovation of the Republic of Ecuador that funded part of his work.

Author information

Authors and Affiliations


Corresponding author

Correspondence to X. Cipriano.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cipriano, X., Vellido, A., Cipriano, J. et al. Influencing factors in energy use of housing blocks: a new methodology, based on clustering and energy simulations, for decision making in energy refurbishment projects. Energy Efficiency 10, 359–382 (2017).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Building energy use
  • Energy building simulation
  • Clustering analysis
  • Urban energy refurbishment