Prediksi Konsumsi Energi Termal Bangunan Menggunakan EPO-CatBoost
Keywords:
CatBoost, EPO, Optimasi Hyperparameter, Konsumsi Energi BangunanAbstract
Building energy consumption is one of the main contributors to global energy use and carbon emissions in the construction sector. The increasing demand for heating and cooling in modern buildings requires an accurate prediction system to estimate thermal energy consumption from the design stage. An accurate prediction model can support energy efficiency policies. This study aims to develop a predictive model for building thermal energy consumption by optimizing the CatBoost algorithm using the Emperor Penguin Optimizer (EPO). The research was carried out through several stages, including data preprocessing and data splitting into two scenarios (70:30 and 80:20). The results show that the application of the EPO algorithm consistently improves the performance of the CatBoost model. In the 70:30 data split, the RMSE value for the Heating Load target decreased from 0.3522 to 0.3306 and for the Cooling Load from 0.7007 to 0.6239, while in the 80:20 data split, the RMSE decreased from 0.3352 to 0.3100 for Heating Load and from 0.6747 to 0.5589 for Cooling Load. It can be concluded that hyperparameter optimization using the Emperor Penguin Optimizer (EPO) significantly enhances the predictive performance of the CatBoost model and can serve as an effective alternative for estimating building thermal energy consumption, supporting the development of energy-efficient building design.
References
A. H. Alharbi, D. S. Khafaga, A. M. Zaki, E.-S. M. El-Kenawy, A. Ibrahim, A. A. Abdelhamid, M. M. Eid, M. El-Said, N. Khodadadi, L. Abualigah, and M. A. Saeed, “Forecasting of energy efficiency in buildings using multilayer perceptron regressor with waterwheel plant algorithm hyperparameter,” Frontiers in Energy Research, vol. 12, 2024. doi:10.3389/fenrg.2024.1393794.
B. Mehdizadeh Khorrami, A. Soleimani, A. Pinnarelli, G. Brusco, & P. Vizza, “Forecasting heating and cooling loads in residential buildings using machine learning: a comparative study of techniques and influential indicators,” Asian Journal of Civil Engineering, vol. 25, no. 2, pp. 1163–1177, 2024. doi:10.1007/s42107-023-00834-8.
R. A. Ibrahim, N. Belouaggadia, and L. Zalewski, “Application of Ventilated Solar Façades to enhance the energy efficiency of buildings: A comprehensive review,” Energy Reports, vol. 13, pp. 1266–1292, 2025. doi:10.1016/j.egyr.2024.12.051.
S. Afzal, B. M. Ziapour, A. Shokri, H. Shakibi, and B. Sobhani, “Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms,” Energy, vol. 282, 2023, Art. no. 128446, doi:10.1016/j.energy.2023.128446.
F. Asdrubali and U. Desideri, “Introduction,” in Handbook of Energy Efficiency in Buildings: A Life Cycle Approach, Elsevier, 2019, ch. 1, pp. 1-3, doi: 10.1016/B978-0-12-812817-6.00001-2.
V. S. C. Widardji, Objektivitas Target Nilai Intensitas Konsumsi Energi (IKE) dari GBCI dan ASEAN-USAID pada Bangunan Hotel di Indonesia, S2 thesis, Universitas Atma Jaya Yogyakarta, Yogyakarta, Indonesia, 2017. [Online]. Available: https://repository.uajy.ac.id/id/eprint/11306/.
M. Yang and X. Yu, Energy Efficiency: Benefits for Environment and Society, Green Energy and Technology. London: Springer-Verlag, 2015. doi:10.1007/978-1-4471-6666-5.
B. N. Jørgensen and Z. Ma, “Towards energy efficient buildings by digital transformation of the building lifecycle,” Energy Informatics, vol. 7, Article no. 81, 2024. doi:10.1186/s42162-024-00405-4.
J. Zheng, M. Hu, C. Wang, S. Wang, B. Han, and H. Wang, “Spatial patterns of residents’ daily activity space and its influencing factors based on the CatBoost model: A case study of Nanjing, China,” Frontiers of Architectural Research, vol. 11, no. 6, pp. 1193-1204, 2022. doi:10.1016/j.foar.2022.04.003.
M. Abdullah and S. Said, “Performance evaluation of machine learning regression models for rainfall prediction,” Preprint, 2023. doi:10.21203/rs.3.rs-3258529/v1.
H. Jia, K. Sun, W. Song, X. Peng, C. Lang, and Y. Li, “Multi-Strategy Emperor Penguin Optimizer for RGB Histogram-Based Color Satellite Image Segmentation Using Masi Entropy,” IEEE Access, vol. 7, pp. 134448-134474, 2019. doi:10.1109/ACCESS.2019.2942064.
M. A. Angel and T. Jaya, “An Enhanced Emperor Penguin Optimization Algorithm for Secure Energy Efficient Load Balancing in Wireless Sensor Networks,” Wireless Personal Communications, vol. 125, no. 3, pp. 2101-2127, 2022. doi:10.1007/s11277-022-09647-5.
