KNN and adaptive comfort applied in decision making for HVAC systems

  • Pablo Aparicio-RuizEmail author
  • Elena Barbadilla-Martín
  • José Guadix
  • Pablo Cortés
S.I.: Data Mining and Decision Analytics


The decision making of a suitable heating, ventilating and air conditioning system’s set-point temperature is an energy and environmental challenge in our society. In the present paper, a general framework to define such temperature based on a dynamic adaptive comfort algorithm is proposed. Due to the fact that the thermal comfort of the occupants of a building has different ranges of acceptability, this method is applied to learn such comfort temperature with respect to the running mean temperature and therefore to decide the suitable range of indoor temperature. It is demonstrated that this solution allows to dynamically build an adaptive comfort algorithm, an algorithm based on the human being’s thermal adaptability, without applying the traditional theory. The proposed methodology based on the K-Nearest-Neighbour algorithm was tested and compared with data from an experimental thermal comfort field study carried out in a mixed mode building in the south-western area of Spain and with the Support Vector Machine method. The results show that K-Nearest-Neighbour algorithm represents the pattern of thermal comfort data better than the traditional solution and that it is a suitable method to learn the thermal comfort area of a building and to define the set-point temperature for a heating, ventilating and air-conditioning system.


Adaptive comfort K-Nearest Neighbour Algorithm Buildings HVAC SVM 



The authors wish to acknowledge the financial support of project DACAR (Ref. BIA2016-77431-C2-1-R) funded by the Programa Estatal de Investigación, Desarrollo e Innovación Orientada a los Retos de la Sociedad (MINECO).


  1. Ahmad, M. W., Mourshed, M., Yuce, B., & Rezgui, Y. (2016). Computational intelligence techniques for hvac systems: A review. Building Simulation, 9(4), 359–398. Scholar
  2. Altman, D. G. (1990). Practical statistics for medical research. Boca Raton: CRC Press.Google Scholar
  3. Altman, N. S. (1992). An introduction to kernel and nearest-neighbour nonparametric regression. The American Statistician, 46(3), 175–185. Scholar
  4. Aparicio-Ruiz, P., Barbadilla-Martín, E., Salmerón-Lissén, J. M., & Guadix-Martín, J. (2018). Building automation system with adaptive comfort in mixed mode buildings. Sustainable Cities and Society, 43, 77–85. Scholar
  5. ASHRAE. (2013). Handbook fundamentals. Atlanta: ASHRAE.Google Scholar
  6. Barbadilla-Martín, E., Salmerón Lissén, J., Guadix Martín, J., Aparicio-Ruiz, P., & Brotas, L. (2017). Field study on adaptive thermal comfort in mixed mode office buildings in southwestern area of Spain. Building and Environment,. Scholar
  7. Bermejo, P., Redondo, L., de la Ossa, L., Rodríguez, D., Flores, J., Urea, C., et al. (2012). Design and simulation of a thermal comfort adaptive system based on fuzzy logic and on-line learning. Energy and Buildings, 49, 367–379. Scholar
  8. Camelo, S. A., González-Lima, M. D., & Quiroz, A. J. (2015). Nearest neighbors methods for support vector machines. Annals of Operations Research, 235(1), 85–101. Scholar
  9. CIBSE. (2015). Guide A: Environmental design.Google Scholar
  10. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37–46.CrossRefGoogle Scholar
  11. Cole, R. J., Brown, Z., & McKay, S. (2010). Building human agency: A timely manifesto. Building Research and Information, 38(3), 339–350. Scholar
  12. Cover, T. M., & Hart, P. E. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27. Scholar
  13. Cunningham, P., & Delany, S. J. (2007). K-nearest neighbour classifiers. Multiple Classifier Systems (pp. 1–17). Scholar
  14. de Dear, R. J., Brager, G. S., Reardon, J., Nicol, F., et al. (1998). Developing an adaptive model of thermal comfort and preference/discussion. ASHRAE Transactions, 104, 145.Google Scholar
  15. Freidman, J. H., Bentley, J. L., & Finkel, R. A. (1977). An algorithm for finding best matches in logarithmic expected time. ACM Transactions on Mathematical Software, 3(3), 209–226. Scholar
  16. Griffiths, I. (1990). Thermal comfort studies in buildings with passive solar features, field studies. Report to the Commission of the European Community 35.Google Scholar
  17. Humphreys, M., Nicol, F., & Roaf, S. (2015). Adaptive thermal comfort: Foundations and analysis. London: Routledge.CrossRefGoogle Scholar
  18. Hussein, I., & Rahman, M. H. A. (2009). Field study on thermal comfort in malaysia. European Journal of Scientific Research, 37(1), 134–152.Google Scholar
  19. ISO Standard. (2008). ISO 15251: Indoor environmental input parameters for design and assessment of energy performance of buildings addressing indoor air quality, thermal environment, lighting and acoustics. EN 15251.Google Scholar
  20. Jain, A. K. (2010). Data clustering: 50 years beyond k-means. Pattern Recognition Letters, 31(8), 651–666. Scholar
  21. Kang, C. S., Hyun, C. H., & Park, M. (2015). Fuzzy logic-based advanced on-off control for thermal comfort in residential buildings. Applied Energy, 155, 270–283. Scholar
  22. Kim, J., Zhou, Y., Schiavon, S., Raftery, P., & Brager, G. (2018). Personal comfort models: Predicting individuals’ thermal preference using occupant heating and cooling behavior and machine learning. Building and Environment, 129, 96–106. Scholar
  23. Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33, 159–174.CrossRefGoogle Scholar
  24. Liu, T., Moore, A. W., & Gray, A. (2006). New algorithms for efficient high dimensional non-parametric classification. Journal for Machine Learning Research, 7(c), 1135–1158.Google Scholar
  25. Nicol, F., & Humphreys, M. (2007). Maximum temperatures in european office buildings to avoid heat discomfort. Solar Energy, 81(3), 295–304. Scholar
  26. Nicol, J. F. (2011). Adaptive comfort. Building Research and Information, 39(2), 105–107. Scholar
  27. Peng, Y., Rysanek, A., Nagy, Z., & Schlüter, A. (2018). Using machine learning techniques for occupancy-prediction-based cooling control in office buildings. Applied Energy, 211, 1343–1358. Scholar
  28. Rupp, R. F., Vásquez, N. G., & Lamberts, R. (2015). A review of human thermal comfort in the built environment. Energy and Buildings, 105, 178–205. Scholar
  29. Shalabi, L. A., Shaaban, Z., & Kasasbeh, B. (2006). Data mining: A preprocessing engine. Journal of Computer Science, 2(9), 735–739. Scholar
  30. Song, W. S., Hong, S. H., & Park, T. J. (2007). The effects of service delays on a BACnet-based HVAC control system. Control Engineering Practice, 15(2), 209–217.CrossRefGoogle Scholar
  31. Si, Tanabe, Haneda, M., & Nishihara, N. (2015). Workplace productivity and individual thermal satisfaction. Building and Environment, 91, 42–50. Scholar
  32. Tuohy, P., Roaf, S., Nicol, F., Humphreys, M., & Boerstra, A. (2010). 21st century standards for thermal comfort fostering low carbon building design. Architectural Science Review, 53(1), 78–86. Scholar
  33. Valor, E., Meneu, V., Caselles, V., Valor, E., Meneu, V., & Caselles, V. (2001). Daily air temperature and electricity load in Spain. Journal of Applied Meteorology, 40(8), 1413–1421.<1413:DATAEL>2.0.CO;2.
  34. Vapnik, V., & Vapnik, V. (1998). Statistical learning theory (pp. 156–160). New York: Wiley.Google Scholar
  35. Wang, S., Jiang, W., & Tsui, K. L. (2010). Adjusted support vector machines based on a new loss function. Annals of Operations Research, 174(1), 83–101. Scholar
  36. Yaşar Sağlam, Ş., & Street, W. N. (2018). Distant diversity in dynamic class prediction. Annals of Operations Research, 263(1), 5–19. Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Grupo de Ingeniería de Organización, Escuela Técnica Superior de IngenieríaUniversidad de SevillaSevilleSpain

Personalised recommendations