Comparative Study of Building Energy Use Prediction Based on Three Artificial Neural Network Algorithms

  • Zhi ZhuangEmail author
  • Ziyu Peng
  • Weipeng Guo
Conference paper
Part of the Environmental Science and Engineering book series (ESE)


With the advent of the era of big data, artificial neural network (ANN) algorithms have been widely used in the field of building energy data analysis. In order to effectively use ANN algorithms to predict building energy consumption, the data-driven building energy consumption prediction with three typical ANNs: Backpropagation neural network (BPNN), generalized regression neural network (GRNN), and fuzzy neural network (FNN) were studied. The simulated data of an office building model setup by EnergyPlus is presented for a case study. The BPNN algorithm with different hidden layer numbers, GRNN algorithm with different scatter constants, and FNN algorithm with different evolution times were investigated, and the optimal parameters of each neural network algorithm for building energy consumption prediction were finally obtained. The results show that the MSEs of all ANN-based models are almost the same with very small values. But the operation time is very different, which of GRNN has the smallest value. So, the GRNN is highly recommended for building energy consumption prediction due to its both good prediction accuracy and short operation time. This study helps to guide the selections of ANNs and the determinations of related parameters of their algorithms in engineering application.


Building energy consumption Data-driven model Artificial neural network 



The study was supported by the National Key R&D Program of China (Grant No. 2017YFC0704200) and the Fundamental Research Funds for the Central Universities.


  1. 1.
    Building Energy Center of Tsinghua University: China Building Energy Consumption Annual Research Report, China Architectural Industry Press, Beijing (2017)Google Scholar
  2. 2.
    Becerik-Gerber, B., et al.: Civil engineering grand challenges: opportunities for data sensing, information analysis, and knowledge discovery. Comput. Civ. Eng. 28, 401–413 (2014)Google Scholar
  3. 3.
    Kadir, A., et al.: A review of data-driven building energy consumption prediction studies. Renew. Sustain. Energy Rev. 81, 1192–1205 (2018)CrossRefGoogle Scholar
  4. 4.
    Hou, Z., et al.: Cooling-load prediction by the combination of rough set theory and an artificial neural-network based on data-fusion technique. Appl. Energy 83, 1033–1046 (2006)CrossRefGoogle Scholar
  5. 5.
    Penya, Y., et al.: Short-term load forecasting in non-residential Buildings. Africon 11, 1–6 (2011)Google Scholar
  6. 6.
    Chou, J., et al.: Modeling heating and cooling loads by artificial intelligence for energy-efficient building design. Energy Build. 82, 437–446 (2014)CrossRefGoogle Scholar
  7. 7.
    Wen, X., et al.: MATLAB Neural Network Simulation and Application. China Science Press, Beijing (2003)Google Scholar
  8. 8.
    Zhang, X., et al.: Research of dynamic tuning of BP model with amending nerve cell output function in the forecast of pool purchse price. Relay 20, 22–28 (2004)Google Scholar
  9. 9.
    Li, Z., et al.: BP algorithm improvement based on sample expected training number. Comput. Technol. Dev. 19(5), 104–105 (2009)Google Scholar
  10. 10.
    Ye, B., Lei, Y.: Analysis of choosing the number of the hidden layers and its nodes number in back propagation network. J. Shangqiu Vocat. Tech. Coll. 3(15), 52–53 (2004)Google Scholar
  11. 11.
    Kong, G., et al.: Generalized regression neural network modeling method based on genetic algorithm. Comput. Eng. Design 38(2), 489 (2017)Google Scholar
  12. 12.
    Cheng, Y., et al.: Fuzzy Neural Network’s Application on Data Prediction. University of Science and Technology of China, Hefei (2012)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Sino-German College of Applied SciencesTongji UniversityShanghaiChina
  2. 2.College of Architecture and Urban PlanningTongji UniversityShanghaiChina

Personalised recommendations