Comparison of artificial neural networks, fuzzy logic and neuro fuzzy for predicting optimization of building thermal consumption: a survey

  • Zahra Pezeshki
  • Sayyed Majid Mazinani


Data Mining (DM) is a useful technique to discover useful patterns which lead to large searches. This method offers a reliable treatment of all developmental phases from problem and data understanding through data preprocessing to deployment of the results. DM plays an important role in energy efficiency. The construction industry has numerous sources information to compare and turn them into beneficial information. Artificial neural networks (ANN), fuzzy logic (FL) and neuro fuzzy (NF) are used techniques. Although the ANN and FL have many advantages, they also have certain defects. NF enjoys the advantages of both ANN and FL. In this paper, by comparing these techniques present in articles from 2009 to 2017, we have introduced four advantages for NF technique and indicated that the second advantage has been paid less attention other ones. The results reveal that the NF method is more successful than FL and ANN for predicting the thermal efficiency of buildings. However, NF with a learning phase proves to be computationally heavy and time-consuming, especially when the number of rules, the antecedents and the model delays are high. As a result, the proposed method, using nonlinear neural Model Predictive Controllers, is the best answer to thermal control strategies.


Energy efficiency Thermal consumption Construction industry Artificial neural networks Data Mining Fuzzy logic Neuro fuzzy 



The authors wish to express sincere gratitude to the anonymous reviewers for their constructive comments and helpful suggestions, which lead to substantial improvements of this paper.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. Ahmad S, Khan L (2017) Performance analysis of conjugate gradient algorithms applied to the neuro-fuzzy feedback linearization-based adaptive control paradigm for multiple HVDC Links in AC/DC power system. Energies 10(819):1–23Google Scholar
  2. Ahmad A, Hassan M, Abdullah M, Rahman H, Hussin F, Abdullah H, Saidur R (2014) A review on applications of ANN and SVM for building electrical energy consumption forecasting. Renew Sustain Energy Rev 33:102–109CrossRefGoogle Scholar
  3. Ak V (1993) An approach for the design of the energy efficient building and the settlement. Ph.D. thesis. Natural Sciences Institute, Istanbul Technical University, IstanbulGoogle Scholar
  4. Alasha’ary H, Moghtaderi B, Page A, Sugo H (2009) A neuro–fuzzy model for prediction of the indoor temperature in typical Australian residential buildings. Energy Buildings 41:703–710CrossRefGoogle Scholar
  5. Ali MM, Khan MA, Shafi M, Abdul M, Khan O, Farooky MAA, Azam S, Khasim S, Ahmed SWE (2014) Heat ventilation & air-conditioning system with self-tuning fuzzy PI controller. Int J Mod Eng Res (IJMER) 4(9):24–35Google Scholar
  6. Allouhi A, El Fouih Y, Kousksou T, Jamil A, Zeraouli Y, Mourad Y (2015) Energy consumption and efficiency in buildings: current status and future trends. J Clean Prod 109:118–130CrossRefGoogle Scholar
  7. Atia DM, El-madany HT (2016) Analysis and design of greenhouse temperature control using adaptive neuro-fuzzy inference system. J Electr Syst Inf Technol. 5 Dec 2016Google Scholar
  8. Attia S (2010) Building performance simulation tools: selection criteria and user survey. Universit Catholique de Louvain, Louvain La NeuveGoogle Scholar
  9. Bahar YN, Pere C, Landrieu J, Nicolle C (2013) A thermal simulation tool for building and its interoperability through the building information modelling (BIM) platform. Buildings 3(2):380–398CrossRefGoogle Scholar
  10. Czogaa E, Leski J (2000) Fuzzy and neuro-fuzzy intelligent systems, Studies in fuzziness and soft computing, vol 47. Springer.
  11. da Silva IN, Spatti DH, Flauzino RA, Liboni LHB (2017) Artificial neural network architectures and training processes. In: Artificial neural networks. Springer, Berlin, pp 21–28.
  12. Deb C, Eang LS, Yang J, Santamouris M (2015) Forecasting energy consumption of institutional buildings in Singapore. Procedia Engineering 121:1734–1740CrossRefGoogle Scholar
  13. Dehestani D, Su S, Nguyen H, Guo Y (2013) Robust fault tolerant application for HVAC system based on combination of online SVM and ANN black box model. In: 2013 European Control Conference (ECC), Zurich, pp 2976–2981Google Scholar
  14. Ekici BB, Aksoy UT (2009) Prediction of building energy consumption by using artificial neural networks. Adv Eng Softw 40:356–362CrossRefzbMATHGoogle Scholar
  15. Fayyad U, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery in databases. American Association for Artificial Intelligence 17(3):37–54. Google Scholar
  16. Ferreira PM, Ruano AE, Silva S, Conceicao EZE (2012) Neural networks based predictive control for thermal comfort and energy savings in buildings. Energy Build 55:238–251CrossRefGoogle Scholar
  17. Fletcher R (1987) Practical methods of optimization, 2nd edn. Wiley, Chichester, pp 80–94zbMATHGoogle Scholar
  18. Ghadi YY, Rasul MMG, Khan MKK (2014) Recent developments of advanced fuzzy logic controllers used in smart buildings in subtropical climate. Energy Procedia 61:1021–1024CrossRefGoogle Scholar
  19. Graupe D (1997) Chapter 1–12. In: Chen W, Mlynski DA (eds) Principles of artificial neural networks. Advanced Series in circuits and systems, vol 3, 1st edn. World Scientific, p. 4e189Google Scholar
  20. Grieu S, Faugeroux O, Traore A, Claudet B, Bodnar J-L (2011) Artificial intelligence tools and inverse methods for estimating the thermal diffusivity of the building materials. Energy Build 43(2–3):543–554CrossRefGoogle Scholar
  21. Henken J, Biswas MAR (2015) Validation of neural network model for residential energy consumption. In: Proceedings of the 2015 ASEE Gulf-Southwest annual conference. The University of Texas, San AntonioGoogle Scholar
  22. Hosseini MS, Zekri M (2012) Review of medical image classification using the adaptive neuro-fuzzy inference system. Journal of Medical Signals and Sensors 2(1):49–60Google Scholar
  23. Kotsopoulos SD, Casalegno F, Cuenin A (2013) Personalizing thermal comfort in a prototype indoor space. In: SIMUL 2013: the fifth international conference on advances in system simulation, IARIAGoogle Scholar
  24. Kumar R, Aggarwal R, Sharma J (2013) Energy analysis of a building using artificial neural network: a review. Energy Build 65:352–358CrossRefGoogle Scholar
  25. Kumari N, Sunita S (2013) Comparison of ANNs, fuzzy logic and neuro-fuzzy integrated approach for diagnosis of coronary heart disease: a survey. IJCSMC 2(6):216–224Google Scholar
  26. Lindelof 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 Build 99:292–302CrossRefGoogle Scholar
  27. Lu J-T, Chang Y-C, Ho C-Y (2015) The optimization of chiller loading by adaptive neuro-fuzzy inference system and genetic algorithms. Math Probl Eng 2015, 1–10, Article ID 306401.
  28. Maile T, Fischer M, Bazjanac V (2007) Building energy performance simulation tools a life-cycle and interoperable perspective. Stanford University, StanfordGoogle Scholar
  29. Mlakić D, Nikolovski S, Vucinic D (2016) Standalone application using JAVA and ANFIS for predicting electric energy consumption based on forecasted temperature. Annals of DAAAM & Proceedings 27:671–677CrossRefGoogle Scholar
  30. Moon JW, Jung SK, Kim Y, Han S-H (2011) Comparative study of artificial intelligence-based building thermal control methods—application of fuzzy, adaptive neuro-fuzzy inference system, and artificial neural network. Appl Therm Eng 31:2422–2429CrossRefGoogle Scholar
  31. Moon JW, Lee J-H, Yoon Y, Kim S (2014) Determining optimum control of double skin envelope for indoor thermal environment based on artificial neural network. Energy Build 69:175–183CrossRefGoogle Scholar
  32. Naji S, Shamshirband S, Basser H, Keivani A, Alengarama UJ, Jumaat MZ, Petkovi D (2016) Application of adaptive neuro fuzzy methodology for estimating building energy consumption. Renew Sustain Energy Rev 53:1520–1528CrossRefGoogle Scholar
  33. Nauck DD, Nürnberger A (2013) Neuro-fuzzy Systems: a short historical review. In: Moewes C, Nürnberger A (eds) Computational intelligence in intelligent data analysis. Studies in computational intelligence, vol 445. Springer, BerlinGoogle Scholar
  34. Nejat P, Jomehzadeh F, Taheri MM, Gohari M, Majid MZA (2015) A global review of energy consumption, CO2 emissions and policy in the residential sector (with an overview of the top ten CO2 emitting countries). Renew Sustain Energy Rev 43:843–862. CrossRefGoogle Scholar
  35. Nürnberger A (2001) A hierarchical recurrent neuro-fuzzy system. In: Proceedings of joint 9th IFSA world congress and 20th NAFIPS international conference. IEEE, pp 1407–1412Google Scholar
  36. Oztemel E (2003) Artificial neural networks. Papatya Publishing, IstanbulGoogle Scholar
  37. Parsons KC (2003) Human thermal environments, 2nd edn. Taylor & Francis, LondonGoogle Scholar
  38. Perera DWU, Pfeiffer CF, Skeie N-O (2014) Control of temperature and energy consumption in buildings—a review. International Journal of Energy and Environment 5(4):471–484Google Scholar
  39. Pérez-Lombard L, Ortiz J, Pout C (2008) A review on buildings energy consumption information. Energy Build 40:394–398. CrossRefGoogle Scholar
  40. Pezeshki Z, Ivari SAS (2018) Applications of BIM: a brief review and future outline. Arch Computat Methods Eng. 25(2):273–312. MathSciNetCrossRefGoogle Scholar
  41. Powell MJ (1977) Restart procedures for the conjugate gradient method. Math Program 12:241–254MathSciNetCrossRefzbMATHGoogle Scholar
  42. Shaikh PH, Nor NBM, Nallagownden P, Elamvazuthi I (2013) Building energy management through a distributed fuzzy inference system. International Journal of Engineering and Technology (IJET) 5(4):3236–3242Google Scholar
  43. Shamshirband S, Petkovi D, Enayatifa R, Abdullah AH, Markovi D, Lee M, Ahmad R (2015) Heat load prediction in district heating systems with adaptive neuro-fuzzy method. Renew Sustain Energy Rev 48:760–767CrossRefGoogle Scholar
  44. Shewchuk JR (1994) An introduction to the conjugate gradient method without the agonizing pain. Carnegie Mellon University, PittsburghGoogle Scholar
  45. Shi L, Sun Z, Li H, Liu W (2007) Research on diagnosing coronary heart disease using fuzzy adaptive resonance theory mapping neural networks. 2007 IEEE international conference on control and automation, Guangzhou, pp 1126–1128Google Scholar
  46. Singhala P, Shah DN, Patel B (2014) Temperature control using fuzzy logic. Int J Instrum Control Syst (IJICS) 4(1):1–10Google Scholar
  47. Soares A, Gomes Á, Antunes CH (2017) An evolutionary algorithm for the optimization of residential energy resources. In: Bertsch V, Fichtner W, Heuveline V, Leibfried T (eds) Advances in energy system optimization. Trends in mathematics. Birkhäuser, Cham. Google Scholar
  48. Soyguder S, Alli H (2009) An expert system for the humidity and temperature control in HVAC systems using ANFIS and optimization with fuzzy modelling approach. Energy Build 41:814–822CrossRefGoogle Scholar
  49. Thai TN (2013) Estimate thermo-physical parameters from characterization of the building materials by using artificial intelligence. In: 27th International conference on advanced information networking and applications workshops, Barcelona, pp 329-334Google Scholar
  50. Turhan C, Simani S, Zajic I, Akkurt GG (2017) Performance analysis of data-driven and model-based control strategies applied to a thermal unit model. Energies 10(67):1–20Google Scholar
  51. U.S. Energy Information Administration (2013) Annual energy outlook 2013 with Projectionto 2040, April 2013Google Scholar
  52. van Hoof J (2008) Forty years of Fanger’s model of thermal comfort: comfort for all? Indoor Air 18(3):182–201CrossRefGoogle Scholar
  53. Wang LX, Mendel JM (1992) Back-propagation fuzzy system as nonlinear dynamic system identification. In: Proceedings of IEEE international conference on fuzzy systems, pp 1409–1418Google Scholar
  54. Welle B, Haymaker J, Rogers Z (2011) ThermalOpt: a methodology for automated BIM-based multidisciplinary thermal simulation for use in optimization environments. Build Simul 4(4):293–313CrossRefGoogle Scholar
  55. Yao Y, Lian ZW, Hou ZJ, Liu W (2006) An innovative air-conditioning load forecasting model based on RBF neural network and combined residual error correction. Int J Refrig 29:528–538CrossRefGoogle Scholar
  56. Yeh J-P, Yang R-P (2014) Application of the adaptive neuro-fuzzy inference system for optimal design of reinforced concrete beams. J Intell Learn Syst Appl 6:162–175Google Scholar
  57. Yu Z, Fung BCM, Haghighat F (2013) Extracting knowledge from building-related data—a data mining framework. Build Simul 6(2):207222CrossRefGoogle Scholar
  58. Zahedi G, Azizi S, Bahadori A, Elkamel A, Sharifah R, Alwi W (2013) Electricity demand estimation using an adaptive neuro-fuzzy network: a case study from the Ontario province e Canada. Energy 49:323–328CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Faculty of Electrical and Robotic EngineeringShahrood University of TechnologyShahrudIran
  2. 2.Electrical Department, Faculty of EngineeringImam Reza International UniversityMashhadIran

Personalised recommendations