Defining Predictive Model for the Energy Consumption of Mid-Rise Residential Buildings Based on Geometric Factors of Southern Buildings in Isfahan City

Document Type : Scientific Research

Authors

1 Architecture Group, Faculty of Architectural Engineering and Urban Design, Shahid Rajaee Teacher Training University, Tehran, Iran

2 Associate Professor of Architecture, Faculty of Architectural Engineering and Urban Design, Shahid Rajaee Teacher Training University, Tehran, Iran

Abstract

Research Problem: The escalating demand for sustainable building design and energy reduction in the construction sector has prompted researchers and industry experts to explore innovative methods for predicting and optimizing energy consumption in residential buildings. In this context, this research aims to define and examine a predictive model for the energy consumption of mid-rise residential buildings within the framework of energy performance simulation based on geometric factors in the city of Isfahan. The primary objective of this study is the prediction, modeling, and optimization of the impact of geometric characteristics of mid-rise residential buildings in southern Isfahan on energy performance. This includes total energy consumption, heating requirements, and cooling needs, using simulation and modeling methods within the climate of Isfahan.
Research Question: What model can predict the relationship between the general geometric characteristics of mid-rise residential buildings in Isfahan and the level of energy consumption in various sectors?
Research Method: The research methodology employed in this study is quantitative, encompassing content analysis, modeling, energy performance simulation, linear regression modeling, and optimization. Initially, influential geometric factors affecting building energy consumption are identified, and a modeling process is initiated for simulation. Subsequently, in a systematic step-by-step approach, 24,192 samples of building morphologies in southern Isfahan are simulated based on climatic conditions. The results are then entered into a linear regression model. Additionally, an optimization process using a genetic algorithm with non-dominated ranking, based on energy performance, is conducted over 300 generations with 50 samples in each generation. The tools utilized in this research include Rhino software, Grasshopper environment, and plugins such as Ladybug Tools, Colibri, and Wallacei.
The Most Important Results and Conclusion: Based on linear regression analysis, predictive models for energy consumption, heating requirements, and cooling needs are presented in six equations. According to the findings, the highest correlation between architectural variables and energy performance is related to the volume and the number of building floors. Based on these results, a linear model based on general geometric characteristics predicts about 94% of energy variations. Moreover, it is concluded that the best fits for building plans are square shapes. It is also found that with an increase in building area and the number of floors, energy consumption per square meter decreases. The primary research question aimed to establish a model predicting the relationship between the general geometric characteristics of mid-rise residential buildings in Isfahan and building energy performance. In response, six equations for energy performance are provided with a prediction accuracy of over 75% and a confidence coefficient of over 95%. Another research question targeted the optimization of the morphological features of mid-rise residential buildings in Isfahan for optimal energy performance. Based on the findings, for optimal energy performance of residential buildings, a square plan is recommended, accompanied by an increase in the number of floors. No definitive relationship has been established for building orientation. According to the findings, it is suggested to increase the height of residential units, although this has a relatively minor impact on energy performance.

Graphical Abstract

Defining Predictive Model for the Energy Consumption of Mid-Rise Residential Buildings Based on Geometric Factors of Southern Buildings in Isfahan City

Keywords

Main Subjects

References

Afzal, S., Ziapour, B. M., Shokri, A., Shakibi, H., & Sobhani, B. (2023). Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms. Energy, 282, 128446. https://doi.org/10.1016/j.energy.2023.128446
Bulbaai, R., & Halman, J. I. (2021). Energy-efficient building design for a tropical climate: A field study on the caribbean island curaçao. Sustainability, 13(23), 13274. https://doi.org/10.3390/su132313274
Cai, W., Wen, X., Li, C., Shao, J., & Xu, J. (2023). Predicting the energy consumption in buildings using the optimized support vector regression model. Energy, 273, 127188. https://doi.org/10.1016/j.energy.2023.127188
Cao, Q., Yang, D., & Lu, S. (2020). A Comprehensive Review of the Impact of Building Geometry on Energy Consumption. Energy and Buildings, 213, 109805. https://doi.org/10.1016/j.energy.2023.127188
Chen, C., Gao, Z., Zhou, X., Wang, M., & Yan, J. (2024). Energy consumption prediction and energy-saving suggestions of public buildings based on machine learning. Energy and Buildings, 320, 114585. https://doi.org/10.1016/j.enbuild.2024.114585
Elbeltagi, E., & Wefki, H. (2021). Predicting energy consumption for residential buildings using ANN through parametric modeling. Energy Reports, 7, 2534-2545.  https://doi.org/10.1016/j.egyr.2021.04.053
Gao, Y., Matsunami, Y., Miyata, S., & Akashi, Y. (2023). Model predictive control of a building renewable energy system based on a long short-term hybrid model. Sustainable Cities and Society, 89, 104317.  https://doi.org/10.1016/j.scs.2022.104317
Kapp, S., Choi, J. K., & Hong, T. (2023). Predicting industrial building energy consumption with statistical and machine-learning models informed by physical system parameters. Renewable and Sustainable Energy Reviews, 172, 113045.  https://doi.org/10.1016/j.rser.2022.113045
Liu, Z., Wu, D., Liu, Y., Han, Z., Lun, L., Gao, J., ... & Cao, G. (2019). Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction. Energy Exploration & Exploitation, 37(4), 1426-1451.  https://doi.org/10.1177/0144598718822400
Olu-Ajayi, R., Alaka, H., Sulaimon, I., Sunmola, F., & Ajayi, S. (2022). Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques. Journal of Building Engineering, 45, 103406.  https://doi.org/10.1016/j.jobe.2021.103406
Pan, Y., Zhu, M., Lv, Y., Yang, Y., Liang, Y., Yin, R., ... & Yuan, X. (2023). Building energy simulation and its application for building performance optimization: A review of methods, tools, and case studies. Advances in Applied Energy, 10, 100135. https://doi.org/10.1016/j.adapen.2023.100135
Wang, Z., Xia, L., Yuan, H., Srinivasan, R. S., & Song, X. (2022). Principles, research status, and prospects of feature engineering for data-driven building energy prediction: A comprehensive review. Journal of Building Engineering, 58, 105028.  https://doi.org/10.1016/j.jobe.2022.105028
Xiao, T., & You, F. (2023). Building thermal modeling and model predictive control with physically consistent deep learning for decarbonization and energy optimization. Applied Energy, 342, 121165. https://doi.org/10.1016/j.apenergy.2023.121165
Zhang, W., Wu, Y., & Calautit, J. K. (2022). A review on occupancy prediction through machine learning for enhancing energy efficiency, air quality and thermal comfort in the built environment. Renewable and Sustainable Energy Reviews, 167, 112704. https://doi.org/10.1016/j.buildenv.2024.111595

Files

Share

How to cite

Statistics