Skip to main content
SpringerLink
Log in

Development of data-driven thermal sensation prediction model using quality-controlled databases

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

Abstract

Predicting the thermal sensations of building occupants is challenging, but useful for indoor environment conditioning. In this study, a data-driven thermal sensation prediction model was developed using three quality-controlled thermal comfort databases. Different machine-learning algorithms were compared in terms of prediction accuracy and rationality. The model was further improved by adding categorical inputs, and building submodels and general models for different contexts. A comprehensive data-driven thermal sensation prediction model was established. The results indicate that the multilayer perceptron (MLP) algorithm achieves higher prediction accuracy and more rational results than the other four algorithms in this specific case. Labeling AC and NV scenarios, climate zones, and cooling and heating seasons can improve model performance. Establishing submodels for specific scenarios can result in better thermal sensation vote (TSV) predictions than using general models with or without labels. With 11 submodels corresponding to 11 scenarios, and three general models without labels, the final TSV prediction model achieved higher prediction accuracy, with 64.7%–90.7% fewer prediction errors (reducing SSE by 3.2–4.9) than the predicted mean vote (PMV). Possible applications of the new model are discussed. The findings of this study can help in development of simple, accurate, and rational thermal sensation prediction tools.

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

Abbreviations

GPR:

Gaussian process regression

KNN:

K nearest neighbors

ML:

machine learning

MLP:

multilayer perception

PI:

permutation importance

RF:

random forest

SVM:

support vector machine

AC:

air-conditioned

Clo:

clothing insulation (clo)

HVAC:

heating, ventilation, and air-conditioning

Met:

metabolic rate (met)

NV:

naturally ventilated

PMV:

predicted mean vote

RH:

relative humidity (%)

TSV:

thermal sensation vote

Ta:

indoor air temperature (°C)

Tout:

outdoor air temperature (°C)

Tr:

mean radiant temperature (°C)

Va:

air speed (m/s)

RMSE:

root mean squared error

MAE:

mean absolute error

R 2 :

correlation coefficients (r) squared

SSE:

sum of squares for residuals

References

  • ASHRAE (2017). ASHRAE Standard 55. Thermal Environmental Conditions for Human Occupancy. Atlata, GA, USA: American Society of Heating, Refrigerating and Air-Conditioning Engineers.

    Google Scholar 

  • Cheung T, Schiavon S, Parkinson T, et al. (2019). Analysis of the accuracy on PMV-PPD model using the ASHRAE Global Thermal Comfort Database II. Building and Environment, 153: 205–217.

    Article  Google Scholar 

  • Cosma AC, Simha R (2019). Machine learning method for real-time non-invasive prediction of individual thermal preference in transient conditions. Building and Environment, 148: 372–383.

    Article  Google Scholar 

  • De Dear R (1998). A global database of thermal comfort field experiments. ASHRAE Transaction, 104: 1141–1152.

    Google Scholar 

  • De Dear R, Schiller Brager G (2001). The adaptive model of thermal comfort and energy conservation in the built environment. International Journal of Biometeorology, 45: 100–108.

    Article  Google Scholar 

  • Elnaklah R, Fosas D, Natarajan S (2020). Indoor environment quality and work performance in “green” office buildings in the Middle East. Building Simulation, 13: 1043–1062.

    Article  Google Scholar 

  • Fanger PO (1970). Thermal Comfort. Copenhagen: Danish Technical Press.

    Google Scholar 

  • Fanger PO, Toftum J (2002). Extension of the PMV model to non-air-conditioned buildings in warm climates. Energy and Buildings, 34: 533–536.

    Article  Google Scholar 

  • Földváry Ličina V, Cheung T, Zhang H, et al. (2018). Development of the ASHRAE global thermal comfort database II. Building and Environment, 142: 502–512.

    Article  Google Scholar 

  • Frontczak M, Schiavon S, Goins J, et al. (2012). Quantitative relationships between occupant satisfaction and satisfaction aspects of indoor environmental quality and building design. Indoor Air, 22: 119–131.

    Article  Google Scholar 

  • Kim J, Zhou Y, Schiavon S, et al. (2018). Personal comfort models: Predicting individuals’ thermal preference using occupant heating and cooling behavior and machine learning. Building and Environment, 129: 96–106.

    Article  Google Scholar 

  • Li W, Zhang J, Zhao T, et al. (2019). Experimental study of human thermal sensation estimation model in built environment based on the Takagi-Sugeno fuzzy model. Building Simulation, 12: 365–377.

    Article  Google Scholar 

  • Lin Y, Yang L, Luo M (2021). Physiological and subjective thermal responses to heat exposure in northern and southern Chinese people. Building Simulation, 14: 1619–1631.

    Article  Google Scholar 

  • Lu S, Wang W, Lin C, et al. (2019). Data-driven simulation of a thermal comfort-based temperature set-point control with ASHRAE RP884. Building and Environment, 156: 137–146.

    Article  Google Scholar 

  • Luo M, Wang Z, Brager G, et al. (2018a). Indoor climate experience, migration, and thermal comfort expectation in buildings. Building and Environment, 141: 262–272.

    Article  Google Scholar 

  • Luo M, Wang Z, Ke K, et al. (2018b). Human metabolic rate and thermal comfort in buildings: The problem and challenge. Building and Environment, 131: 44–52.

    Article  Google Scholar 

  • Luo M, Xie J, Yan Y, et al. (2020). Comparing machine learning algorithms in predicting thermal sensation using ASHRAE Comfort Database II. Energy and Buildings, 210: 109776.

    Article  Google Scholar 

  • Nicol JF, Humphreys MA (1973). Thermal comfort as part of a self-regulating system. Building Research and Practice, 1: 174–179.

    Article  Google Scholar 

  • Nicol F, Humphreys M (2010). Derivation of the adaptive equations for thermal comfort in free-running buildings in European standard EN15251. Building and Environment, 45: 11–17.

    Article  Google Scholar 

  • O’Brien W, Wagner A, Schweiker M, et al. (2020). Introducing IEA EBC Annex 79: Key challenges and opportunities in the field of occupant-centric building design and operation. Building and Environment, 178: 106738.

    Article  Google Scholar 

  • Peel MC, Finlayson BL, McMahon TA (2007). Updated world map of the Köppen-Geiger climate classification. Hydrology and Earth System Sciences, 11: 1633–1644.

    Article  Google Scholar 

  • Schiavon S, Hoyt T, Piccioli A (2014). Web application for thermal comfort visualization and calculation according to ASHRAE Standard 55. Building Simulation, 7: 321–334.

    Article  Google Scholar 

  • Schweiker M (2016). Comf: An R package for thermal comfort studies. The R Journal, 8: 341.

    Article  Google Scholar 

  • Tang J, Liu Y, Du H, et al. (2021). The effects of portable cooling systems on thermal comfort and work performance in a hot environment. Building Simulation, 14: 1667–1683.

    Article  Google Scholar 

  • Tartarini F, Schiavon S (2020). Pythermalcomfort: A Python package for thermal comfort research. SoftwareX, 12: 100578.

    Article  Google Scholar 

  • Wagner A, Gossauer E, Moosmann C, et al. (2007). Thermal comfort and workplace occupant satisfaction—Results of field studies in German low energy office buildings. Energy and Buildings, 39: 758–769.

    Article  Google Scholar 

  • Witten IH, Frank E (2000). Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. San Francisco, CA, USA: Morgan Kaufmann Publishers.

    Google Scholar 

  • Wu Z, Li N, Peng J, et al. (2018). Using an ensemble machine learning methodology-Bagging to predict occupants’ thermal comfort in buildings. Energy and Buildings, 173: 117–127.

    Article  Google Scholar 

  • Wu Y, Liu H, Li B, et al. (2021). Individual thermal comfort prediction using classification tree model based on physiological parameters and thermal history in winter. Building Simulation, 14: 1651–1665.

    Article  Google Scholar 

  • Xie J, Li H, Li C, et al. (2020). Review on occupant-centric thermal comfort sensing, predicting, and controlling. Energy and Buildings, 226: 110392.

    Article  Google Scholar 

  • Yao R, Li B, Liu J (2009). A theoretical adaptive model of thermal comfort—Adaptive Predicted Mean Vote (aPMV). Building and Environment, 44: 2089–2096.

    Article  Google Scholar 

  • Zhang J, Zhou X, Lei S, et al. (2022). Energy and comfort performance of occupant-centric air conditioning strategy in office buildings with personal comfort devices. Building Simulation, 15: 899–911.

    Article  Google Scholar 

  • Zhou X, Liu Y, Luo M, et al. (2019). Thermal comfort under radiant asymmetries of floor cooling system in 2 h and 8 h exposure durations. Energy and Buildings, 188: 98–110.

    Article  Google Scholar 

  • Zhou X, Xu L, Zhang J, et al. (2020). Data-driven thermal comfort model via support vector machine algorithms: Insights from ASHRAE RP-884 database. Energy and Buildings, 211: 109795.

    Article  Google Scholar 

  • Zhu Y, Luo M, Ouyang Q, et al. (2015). Dynamic characteristics and comfort assessment of airflows in indoor environments: A review. Building and Environment, 91: 5–14.

    Article  Google Scholar 

Download references

Acknowledgements

This study was supported by the National Natural Science Foundation of China (No. 52178087), the China National Key R&D Program during the 13th Five-year Plan Period (No. 2018YFC0704500), and the Fundamental Research Funds for the Central Universities (No. 22120210537). The authors would like to thank Guangdong Midea Air-Conditioning Equipment Co., Ltd. for their support.

Author information

Authors and Affiliations

  1. School of Mechanical Engineering, Tongji University, Shanghai, 200092, China

    Xiang Zhou, Ling Xu, Jingsi Zhang & Maohui Luo

  2. Guangdong Midea Air-Conditioning Equipment Co., LTD, Guangdong, 528311, China

    Jingsi Zhang, Lie Ma & Mingzheng Zhang

Authors
  1. Xiang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ling Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jingsi Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lie Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mingzheng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Maohui Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Maohui Luo.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhou, X., Xu, L., Zhang, J. et al. Development of data-driven thermal sensation prediction model using quality-controlled databases. Build. Simul. 15, 2111–2125 (2022). https://doi.org/10.1007/s12273-022-0911-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12273-022-0911-2

Keywords

Search

Navigation