COOLING LOAD PREDICTION USING MACHINE LEARNING AND WEATHER PARAMETERS
DOI:
https://doi.org/10.53893/austenit.v17i2.11332Keywords:
Cooling load, Time delay, Machine learning, Prediction, BuildingAbstract
Cooling systems account for a substantial amount of end-use energy consumption in building sector. This system is responsible for removing the heat from the building to maintain the indoor temperature at a certain comfort level standard. Prediction of cooling load in a building is useful to design the HVAC system operation and energy management efficiently. This paper presents a method for predicting instantaneous building cooling load, relying on the inputs extracted from weather data and artificial neural networks. The data sets are generated by simulating cooling load at an educational building located in Indonesia for one year using Energy Plus software. The input parameters include dry-bulb temperature, relative humidity, wind speed, wind direction, horizontal infrared radiation rate, diffuse solar radiation rate, and direct solar radiation rate. Analysis of variance and Pearson coefficient of correlation was applied to analyze the relative contribution of individual input parameters on the cooling load. Both methods have consistently shown that the dry bulb temperature is the most influential parameters, while wind speed and wind direction have less significant effect on cooling loads. The result of this study indicates that the optimized ANN model with selected input parameters has successfully predicted the cooling load with coefficient of variation (CV) of 15.26%.
Downloads
References
Amasyali, K., & El‑Gohary, N. M. (2018). A review of data‑driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 81, 1192–1205. https://doi.org/10.1016/j.rser.2017.07.098
Badan Standardisasi Nasional. (2020). SNI 6390:2020 Konservasi energi sistem tata udara pada bangunan gedung. Badan Standardisasi Nasional.
International Energy Agency. (2024). World energy statistics and balances. https://www.iea.org/data-and-statistics/data-product/world-energy-statistics-and-balances
Meteotest, 2025. MeteoNorm (Version 8.2) [Software]. https://mn8.meteonorm.com/
Pham, A. D., Ngo, N. T., Truong, T. T. H., Huynh, N. T., & Truong, N. S. (2020). Predicting energy consumption in multiple buildings using machine learning for improving energy efficiency and sustainability. Journal of Cleaner Production, 260, 121082. https://doi.org/10.1016/j.jclepro.2020.121082
Qi, R., Lu, L., & Yang, H. (2012). Investigation on air‑conditioning load profile and energy consumption of desiccant cooling system for commercial buildings in Hong Kong. Energy and Buildings, 49, 509–518. https://doi.org/10.1016/j.enbuild.2012.01.003
Rock, M., Balouktsi, M., & Saade, M. R. M. (2023). Embodied carbon emissions of buildings and how to tame them. One Earth, 6, 1458–1464. https://doi.org/10.1016/j.oneear.2023.10.018
Serale, G., Fiorentini, M., Capozzoli, A., Bernardini, D., & Bemporad, A. (2018). Model predictive control (MPC) for enhancing building and HVAC system energy efficiency: Problem formulation, applications and opportunities. Energies, 11, 631. https://doi.org/10.3390/en11030631
Sha, H., Moujahed, M., & Qi, D. (2021). Machine learning‑based cooling load prediction and optimal control for mechanical ventilative cooling in high‑rise buildings. Energy and Buildings, 242, 110980. https://doi.org/10.1016/j.enbuild.2021.110980
Sholahudin, S., & Han, H. (2016). Simplified dynamic neural network model to predict heating load of a building using Taguchi method. Energy, 115, 1672–1678. https://doi.org/10.1016/j.energy.2016.08.005
Sholahudin, S., Ohno, K., Giannetti, N., Yamaguchi, S., & Saito, K. (2019). Dynamic modeling of room temperature and thermodynamic efficiency for direct expansion air‑conditioning systems using Bayesian neural network. Applied Thermal Engineering, 158, 113809. https://doi.org/10.1016/j.applthermaleng.2019.113809
Sholahudin, S., Giannetti, N., Miyaoka, Y., Saito, K., Tanaka, K., & Ogami, H. (2023). Experimental verification of artificial neural network scalability for performance monitoring of multi‑split type air conditioners. Journal of Building Engineering, 76, 107427. https://doi.org/10.1016/j.jobe.2023.107427
Tao, W., Kailin, Y., & Yongxin, G. (2008). Application of artificial neural networks to predicting ice conditions of the Yellow River in the Inner Mongolia Reach. Journal of Hydrologic Engineering, 13(9), 811–816. https://doi.org/10.1061/(ASCE)HE.1943-584.0000006
Timotius Kelvin Wijaya, Sholahudin, Alhamid, M. I., Saito, K., & Nasruddin, N. (2022). Dynamic optimization of chilled water pump operation to reduce HVAC energy consumption. Thermal Science and Engineering Progress, 36, 101512. https://doi.org/10.1016/j.tsep.2022.101512
Widagdo, T. (2010). Pengujian refrigeran alternatif ramah lingkungan pada mesin pendingin jenis kompresi uap. Jurnal Austenit, 2(2), 137–144.
Yıldız, M. E., & Beyhan, F. (2025). Prediction of cooling load via machine learning on building envelope design parameters. Journal of Building Engineering, 100, 111724. https://doi.org/10.1016/j.jobe.2025.111724
Zhang, L., Cao, M., Li, N., Luo, L., Chen, Y., & Li, Z. (2025). Machine learning prediction of heating and cooling loads based on Athenian residential buildings’ simulation dataset. Energy and Buildings, 342, 115808. https://doi.org/10.1016/j.enbuild.2025.115808
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Authors and Publisher
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
The Authors submitting a manuscript do so on the understanding that if accepted for publication, Authors retain copyright and grant the AUSTENIT right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
AUSTENIT, the Editors and the Advisory International Editorial Board make every effort to ensure that no wrong or misleading data, opinions or statements be published in the journal. In any way, the contents of the articles and advertisements published in AUSTENIT are the sole responsibility of their respective authors and advertisers.
