Skip to main content
SpringerLink
Log in

A backpropagation neural network improved by a genetic algorithm for predicting the mean radiant temperature around buildings within the long-term period of the near future

  • Research Article
  • Published:
Building Simulation Aims and scope Submit manuscript

Abstract

This study aimed to develop a neural network (NN)-based method to predict the long-term mean radiant temperature (MRT) around buildings by using meteorological parameters as training data. The MRT dramatically impacts building energy consumption and significantly affects outdoor thermal comfort. In NN-based long-term MRT prediction, two main restrictions must be overcome to achieve precise results: first, the difficulty of preparing numerous training datasets; second, the challenge of developing an accurate NN model. To overcome these restrictions, a combination of principal component analysis (PCA) and K-means clustering was employed to reduce the training data while maintaining high prediction accuracy. Second, three widely used NN models (feedforward NN (FFNN), backpropagation NN (BPNN), and BPNN optimized using a genetic algorithm (GA-BPNN)) were compared to identify the NN with the best long-term MRT prediction performance. The performances of the tested NNs were evaluated using the mean absolute percentage error (MAPE), which was ≤ 3% in each case. The findings indicate that the training dataset was reduced effectively by the PCA and K-means. Among the three NNs, the GA-BPNN produced the most accurate results, with its MAPE being below 1%. This study will contribute to the development of fast and feasible outdoor thermal environment prediction.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Abdul-Wahab SA, Bakheit CS, Al-Alawi SM (2005). Principal component and multiple regression analysis in modelling of ground-level ozone and factors affecting its concentrations. Environmental Modelling & Software, 20: 1263–1271.

    Article  Google Scholar 

  • Alam S, Kaushik SC, Garg SN (2009). Assessment of diffuse solar energy under general sky condition using artificial neural network. Applied Energy, 86: 554–564.

    Article  Google Scholar 

  • Cai H, Jia X, Feng J, et al. (2019). A combined filtering strategy for short term and long term wind speed prediction with improved accuracy. Renewable Energy, 136: 1082–1090.

    Article  Google Scholar 

  • Cao X, Liu Y, Wang J, et al. (2020). Prediction of dissolved oxygen in pond culture water based on K-means clustering and gated recurrent unit neural network. Aquacultural Engineering, 91: 102122.

    Article  Google Scholar 

  • Chan T-S, Chang Y-C, Huang J (2017). Application of artificial neural network and genetic algorithm to the optimization of load distribution for a multiple-type-chiller plant. Building Simulation, 10: 711–722.

    Article  Google Scholar 

  • Chan SY, Chau CK (2019). Development of artificial neural network models for predicting thermal comfort evaluation in urban parks in summer and winter. Building and Environment, 164: 106364.

    Article  Google Scholar 

  • Chen G, Fu K, Liang Z, et al. (2014). The genetic algorithm based back propagation neural network for MMP prediction in CO2-EOR process. Fuel, 126: 202–212.

    Article  Google Scholar 

  • Chen L, Yu B, Yang F, et al. (2016). Intra-urban differences of mean radiant temperature in different urban settings in Shanghai and implications for heat stress under heat waves: a GIS-based approach. Energy and Buildings, 130: 829–842.

    Article  Google Scholar 

  • Cheng M-Y, Cao M-T (2014). Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines. Applied Soft Computing, 22: 178–188.

    Article  Google Scholar 

  • Deo RC, Şahin M (2017). Forecasting long-term global solar radiation with an ANN algorithm coupled with satellite-derived (MODIS) land surface temperature (LST) for regional locations in Queensland. Renewable and Sustainable Energy Reviews, 72: 828–848.

    Article  Google Scholar 

  • Dogan T, Kastner P, Mermelstein R (2021). Surfer: A fast simulation algorithm to predict surface temperatures and mean radiant temperatures in large urban models. Building and Environment, 196: 107762.

    Article  Google Scholar 

  • Ekonomou L (2010). Greek long-term energy consumption prediction using artificial neural networks. Energy, 35: 512–517.

    Article  Google Scholar 

  • Fadare DA (2009). Modelling of solar energy potential in Nigeria using an artificial neural network model. Applied Energy, 86: 1410–1422.

    Article  Google Scholar 

  • Feng M, Wang Z (2011). A genetic K-means clustering algorithm based on the optimized initial centers. Computer and Information Science, 4(3): 88–94.

    Article  Google Scholar 

  • Gebhart B (1959). A new method for calculating radiant exchanges. ASHRAE Transactions, 65(1): 321–332.

    Google Scholar 

  • Guijo-Rubio D, Gómez-Orellana AM, Gutiérrez PA, et al. (2020). Short- and long-term energy flux prediction using Multi-Task Evolutionary Artificial Neural Networks. Ocean Engineering, 216: 108089.

    Article  Google Scholar 

  • Hajat S, O’Connor M, Kosatsky T (2010). Health effects of hot weather: from awareness of risk factors to effective health protection. The Lancet, 375(9717): 856–863.

    Article  Google Scholar 

  • Hawila AA, Merabtine A, Troussier N (2020). Metamodeling of mean radiant temperature to optimize glass facade design in PMV-based comfort controlled space. Building Simulation, 13: 271–286.

    Article  Google Scholar 

  • Howell JR, Perlmutter M (1964). Monte Carlo solution of thermal transfer through radiant media between gray walls. Journal of Heat Transfer, 86: 116–122.

    Article  Google Scholar 

  • Huang J, Cedeño-Laurent JG, Spengler JD (2014). CityComfort+: A simulation-based method for predicting mean radiant temperature in dense urban areas. Building and Environment, 80: 84–95.

    Article  Google Scholar 

  • Hwang R-L, Lin T-P, Matzarakis A (2011). Seasonal effects of urban street shading on long-term outdoor thermal comfort. Building and Environment, 46: 863–870.

    Article  Google Scholar 

  • Jang Y, Byon E, Jahani E, et al. (2020). On the long-term density prediction of peak electricity load with demand side management in buildings. Energy and Buildings, 228: 110450.

    Article  Google Scholar 

  • Jolliffe IT (1993). Principal component analysis: A beginner’s guide—II. Pitfalls, myths and extensions. Weather, 48: 246–253.

    Article  Google Scholar 

  • Juan S, Li R, Christensen MH (2021). Clustering and classification of energy meter data: A comparison analysis of data from individual homes and the aggregated data from multiple homes. Building Simulation, 14: 103–117.

    Article  Google Scholar 

  • Kalogirou SA (2000). Long-term performance prediction of forced circulation solar domestic water heating systems using artificial neural networks. Applied Energy, 66: 63–74.

    Article  Google Scholar 

  • Kalogirou SA, Panteliou S (2000). Thermosiphon solar domestic water heating systems: Long-term performance prediction using artificial neural networks. Solar Energy, 69: 163–174.

    Article  Google Scholar 

  • Kaufman L, Rousseeuw PJ (1990). Agglomerative nesting (program AGNES). In: Finding Groups in Data: An introduction to Cluster Analysis. New York: John Wiley & Sons

    Chapter  MATH  Google Scholar 

  • Kikumoto H, Ooka R, Arima Y (2016). A study of urban thermal environment in Tokyo in summer of the 2030s under influence of global warming. Energy and Buildings, 114: 54–61.

    Article  Google Scholar 

  • Koca A, Oztop HF, Varol Y, et al. (2011). Estimation of solar radiation using artificial neural networks with different input parameters for Mediterranean region of Anatolia in Turkey. Expert Systems with Applications, 38: 8756–8762.

    Article  Google Scholar 

  • Kolhe M, Lin TC, Maunuksela J (2011). GA-ANN for short-term wind energy prediction. In: Proceedings of Asia-Pacific Power and Energy Engineering Conference, Wuhan, China.

  • Kumar R, Aggarwal RK, Sharma JD (2013). Energy analysis of a building using artificial neural network: A review. Energy and Buildings, 65: 352–358.

    Article  Google Scholar 

  • Lai H, Deng J, Wen S (2019). Application of ToF-SIMS and PCA to study interaction mechanism of dodecylamine and smithsonite. Applied Surface Science, 496: 143698.

    Article  Google Scholar 

  • Li Z, Dai J, Chen H, et al. (2019). An ANN-based fast building energy consumption prediction method for complex architectural form at the early design stage. Building Simulation, 12: 665–681.

    Article  Google Scholar 

  • Magoulast GD, Vrahatis MN, Androulakis GS (1997). On the alleviation of the problem of local minima in back-propagation. Nonlinear Analysis: Theory, Methods & Applications, 30: 4545–4550.

    Article  MathSciNet  MATH  Google Scholar 

  • Mahgoub AO, Gowid S, Ghani S (2020). Global evaluation of WBGT and SET indices for outdoor environments using thermal imaging and artificial neural networks. Sustainable Cities and Society, 60: 102182.

    Article  Google Scholar 

  • Masmoudi S, Mazouz S (2004). Relation of geometry, vegetation and thermal comfort around buildings in urban settings, the case of hot arid regions. Energy and Buildings, 36: 710–719.

    Article  Google Scholar 

  • Mayer H, Höppe P (1987). Thermal comfort of man in different urban environments. Theoretical and Applied Climatology, 38: 43–49.

    Article  Google Scholar 

  • McClelland JL, Rumelhart DE (1989). Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises. Cambridge, MA, USA: MIT Press.

    Google Scholar 

  • Mochida A, Yoshino H, Miyauchi S, et al. (2006). Total analysis of cooling effects of cross-ventilation affected by microclimate around a building. Solar Energy, 80: 371–382.

    Article  Google Scholar 

  • Mohandes SR, Zhang X, Mahdiyar A (2019). A comprehensive review on the application of artificial neural networks in building energy analysis. Neurocomputing, 340: 55–75.

    Article  Google Scholar 

  • Naboni E, Meloni M, Coccolo S, et al. (2017). An overview of simulation tools for predicting the mean radiant temperature in an outdoor space. Energy Procedia, 122: 1111–1116.

    Article  Google Scholar 

  • Nakamura Y (1987). Expression method of the radiant field on a human body in buildings and urban spaces. Journal of Architecture, Planning and Environmental Engineering (Transactions of AIJ), 376: 29–35.

    Article  Google Scholar 

  • Østergård T, Jensen RL, Maagaard SE (2018). A comparison of six metamodeling techniques applied to building performance simulations. Applied Energy, 211: 89–103.

    Article  Google Scholar 

  • Pang Z, Niu F, O’Neill Z (2020). Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons. Renewable Energy, 156: 279–289.

    Article  Google Scholar 

  • Papantoniou S, Kolokotsa D-D (2016). Prediction of outdoor air temperature using neural networks: Application in 4 European cities. Energy and Buildings, 114: 72–79.

    Article  Google Scholar 

  • Pentoś K (2016). The methods of extracting the contribution of variables in artificial neural network models — Comparison of inherent instability. Computers and Electronics in Agriculture, 127: 141–146.

    Article  Google Scholar 

  • Rajee AM, Francis FS (2013). A Study on Outlier distance and SSE with multidimensional datasets in K-means clustering. In: Proceedings of the 5th International Conference on Advanced Computing (ICoAC), Chennai, India.

  • Roman ND, Bre F, Fachinotti VD, et al. (2020). Application and characterization of metamodels based on artificial neural networks for building performance simulation: A systematic review. Energy and Buildings, 217: 109972.

    Article  Google Scholar 

  • Romani Z, Draoui A, Allard F (2015). Metamodeling the heating and cooling energy needs and simultaneous building envelope optimization for low energy building design in Morocco. Energy and Buildings, 102: 139–148.

    Article  Google Scholar 

  • Santamouris M (2014). On the energy impact of urban heat island and global warming on buildings. Energy and Buildings, 82: 100–113.

    Article  Google Scholar 

  • Sturm J-E, Hartwig J (2012). An outlier-robust extreme bounds analysis of the determinants of health-care expenditure growth. KOF Working Papers, No. 307.

  • Thorsson S, Rocklöv J, Konarska J, et al. (2014). Mean radiant temperature—A predictor of heat related mortality. Urban Climate, 10: 332–345.

    Article  Google Scholar 

  • Van Gelder L, Das P, Janssen H, Roels S (2014). Comparative study of metamodelling techniques in building energy simulation: Guidelines for practitioners. Simulation Modelling Practice and Theory, 49: 245–257.

    Article  Google Scholar 

  • Wang J, Du Y, Wang J (2020a). LSTM based long-term energy consumption prediction with periodicity. Energy, 197: 117197.

    Article  Google Scholar 

  • Wang S, Wang J, Shang F, et al. (2020b). A GA-BP method of detecting carbamate pesticide mixture based on three-dimensional fluorescence spectroscopy. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 224: 117396.

    Article  Google Scholar 

  • Xuan Y, Yang G, Li Q, et al. (2016). Outdoor thermal environment for different urban forms under summer conditions. Building Simulation, 9: 281–296.

    Article  Google Scholar 

  • Xue X (2017). Prediction of daily diffuse solar radiation using artificial neural networks. International Journal of Hydrogen Energy, 42: 28214–28221.

    Article  Google Scholar 

  • Yadav AK, Chandel SS (2014). Solar radiation prediction using Artificial Neural Network techniques: A review. Renewable and Sustainable Energy Reviews, 33: 772–781.

    Article  Google Scholar 

  • Yamamoto M, Kasai M, Okaze T, et al. (2018). Analysis of climatic factors leading to future summer heatstroke risk changes in Tokyo and Sendai based on dynamical downscaling of pseudo global warming data using WRF. Journal of Wind Engineering and Industrial Aerodynamics, 183: 187–197.

    Article  Google Scholar 

  • Yuan J, Nian V, Su B, et al. (2017). A simultaneous calibration and parameter ranking method for building energy models. Applied Energy, 206: 657–666.

    Article  Google Scholar 

  • Yuan C, Yang H (2019). Research on K-value selection method of K-means clustering algorithm. J, 2: 226–235.

    Google Scholar 

  • Yumino S, Uchida T, Sasaki K, et al. (2015). Total assessment for various environmentally conscious techniques from three perspectives: Mitigation of global warming, mitigation of UHIs, and adaptation to urban warming. Sustainable Cities and Society, 19: 236–249.

    Article  Google Scholar 

  • Zarra T, Galang MG, Ballesteros F, Jr, et al. (2019). Environmental odour management by artificial neural network — A review. Environment International, 133: 105189.

    Article  Google Scholar 

  • Zhao H-x, Magoulès F (2012). A review on the prediction of building energy consumption. Renewable and Sustainable Energy Reviews, 16: 3586–3592.

    Article  Google Scholar 

  • Zhou X, Hu J, Mochida A (2017). A method of predicting long period outdoor thermal environment and building cooling load Part 2. A case study for city blocks in Sendai. In: Proceedings of Summaries of Design Works of Annual Meeting, Architectural Institute of Japan.

Download references

Acknowledgements

This study was supported by a Grant-in-Aid for Challenging Research (Exploratory) (No. 19K22004) and the China Scholarship Council (No. 201708430100).

Author information

Authors and Affiliations

  1. Department of Architecture and Building Science, Graduate School of Engineering, Tohoku University, Sendai, Japan

    Yuquan Xie, Yasuyuki Ishida & Akashi Mochida

  2. Institute of Technology, Tokyu Construction, Tokyu, Japan

    Jialong Hu

Authors
  1. Yuquan Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yasuyuki Ishida
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jialong Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Akashi Mochida
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuquan Xie.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xie, Y., Ishida, Y., Hu, J. et al. A backpropagation neural network improved by a genetic algorithm for predicting the mean radiant temperature around buildings within the long-term period of the near future. Build. Simul. 15, 473–492 (2022). https://doi.org/10.1007/s12273-021-0823-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12273-021-0823-6

Keywords

Search

Navigation