Analysis of Essential Factors in Deep Learning-based Prediction of Cooling Load and Surface Temperature

Dong Kyu Lee; Woong June Chung; Se Eun Park

doi:10.7836/kses.2025.45.5.027

All Issue

2025 Vol.45, Issue 5 Preview Page Next Page

Research Article

Analysis of Essential Factors in Deep Learning-based Prediction of Cooling Load and Surface Temperature 딥러닝 기반 냉방 부하 및 표면 온도 예측을 위한 주요인자 분석

30 October 2025. pp. 27-37

PDF XML

Abstract

Radiant floor heating systems ensure a uniform thermal distribution indoors and can provide better thermal comfort to occupants compared to convection systems. In Korea’s hot and humid climate, however, the use of radiant cooling systems involves some risks of condensation and overcooling. Integrated prediction of building load and surface temperature is essential to resolve these problems. Although various sensors are required for an integrated prediction, an excessive number of sensors can also reduce the practical applicability of a model. To enhance the applicability of predictions, we identified essential input variables to predict building loads and surface temperatures using SHapley Additive exPlanations (SHAP), which is one of the most accurate eXplainable artificial intelligence (XAI) techniques.

Keywords

Building load

Surface temperature

XAI

Importance of input variables

SHapley Additive exPlanations

Deep learning

키워드

건물 부하

표면 온도

설명 가능한 인공지능

입력 변수의 중요도

SHAP

딥러닝

References

Perez-Lombard, L., Ortiz, J., and Pout C., A Review on Buildings Energy Consumption Information, Energy and Buildings, Vol. 40, No. 3, pp. 394-398, 2008.

10.1016/j.enbuild.2007.03.007

Chen, Y., Guo, M., Chen, Z., Chen, Z., and Ji, Y., Physical Energy and Data-Driven Models in Building Energy Prediction: A Review, Energy Reports, Vol. 8, pp. 2656-2671, 2022.

10.1016/j.egyr.2022.01.162

Sim, T., Choi, S., Kim, Y., Youn, S. H., Jang, D. J., Lee, S., and Chun, C. J. Explainable AI (XAI)-based Input Variable Selection Methodology for Forecasting Energy Consumption, Electronics, Vol. 11, No. 18, 2947 2022.

10.3390/electronics11182947

Korean Statistical Information Service (KOSIS), Number of Household Members Index, 2025. https://www.index.go.kr/unify/idx-info.do?idxCd=4229, last accessed on the 15^th July, 2025.

Lim, J.-H., Control and Operation Strategy of Radiant Floor Cooling Integrated with Dehumidification System in Apartment Buildings, Doctoral dissertation, Seoul National University, 2005.

Leung, M. C., Norman, C. F., Lai, L. L., and Chow, T. T., The Use of Occupancy Space Electrical Power Demand in Building Cooling Load Prediction, Energy and Buildings, Vol. 55, pp. 151-163, 2012.

10.1016/j.enbuild.2012.08.032

Yang, J., Rivard, H., and Zmeureanu, R., On-line Building Energy Prediction Using Adaptive Artificial Neural Networks, Energy and Buildings, Vol. 37, No. 12, pp. 1250-1259, 2005.

10.1016/j.enbuild.2005.02.005

Chae, Y. T., Horesh, R., Hwang, Y., and Lee, Y. M., Artificial Neural Network Model for Forecasting Sub-Hourly Electricity Usage in Commercial Buildings, Energy and Buildings, Vol. 111, pp. 184-194, 2016.

10.1016/j.enbuild.2015.11.045

Chung, W. J. and Liu, C., Analysis of Input Parameters for Deep Learning-Based Load Prediction for Office Buildings in Different Climate Zones Using eXplainable Artificial Intelligence, Energy and Buildings, Vol. 276, 112521, 2022.

10.1016/j.enbuild.2022.112521

Zhang, L., Wen, J., Li, Y., Chen, J., Ye, Y., Fu, Y., and Livingood, W., A Review of Machine Learning in Building Load Prediction, Applied Energy, Vol. 285, 116452, 2021.

10.1016/j.apenergy.2021.116452

Ahmad, M. W., Mourshed, M., and Rezgui, Y., Trees vs Neurons: Comparison between Random Forest and ANN for High-Resolution Prediction of Building Energy Consumption, Energy and Buildings, Vol. 147, pp. 77-89, 2017.

10.1016/j.enbuild.2017.04.038

Lee, D. K., Analyzing the Importance of Deep Learning Input Variables for Predicting Heating and Cooling Loads in Buildings by Usage Type Buildings Using Explainable Artificial Intelligence, Master’s thesis, Gachon University, 2025.

Lim, H. S. and Kim, G., Prediction Model of Cooling Load Considering Time-Lag for Preemptive Action in Buildings. Energy and Buildings, Vol. 151, pp. 53-65, 2017.

10.1016/j.enbuild.2017.06.019

Alabi, R. O., Elmusrati, M., Leivo, I., Almangush, A., and Mäkitie, A. A., Machine Learning Explainability in Nasopharyngeal Cancer Survival Using LIME and SHAP, Scientific Reports, Vol. 13, No. 1, 8984, 2023.

10.1038/s41598-023-35795-037268685PMC10238539

Information

Publisher :Korean Solar Energy Society
Publisher(Ko) :한국태양에너지학회
Journal Title :Journal of the Korean Solar Energy Society
Journal Title(Ko) :한국태양에너지학회 논문집
Volume : 45
No :5
Pages :27-37
Received Date : 2025-07-21
Revised Date : 2025-09-22
Accepted Date : 2025-09-26
DOI :https://doi.org/10.7836/kses.2025.45.5.027

Journal of the Korean Solar Energy Society ISSN:1598-6411(Print) 2508-3562(Online) 한국태양에너지학회 논문집

All Issue