Research on Adaptive Control Systems for Building Shading Based on Decision Tree and Random Forest Classification Algorithms

Jiating Chen; Yan Liu

doi:10.62051/ijcsit.v4n1.23

Authors

Jiating Chen
Yan Liu

DOI:

https://doi.org/10.62051/ijcsit.v4n1.23

Keywords:

Decision Tree, Random Forest, Shading, Adaptive Control System, Machine Learning

Abstract

Dynamic shading systems for buildings, due to their variable mechanisms and high adaptability, have the potential to reduce energy consumption in buildings significantly. However, the performance of dynamic shading is largely influenced by the control system employed. This study aims to explore an adaptive control method for building shading based on decision tree and random forest classification algorithms (machine learning), with the objective of minimizing energy demands related to lighting and cooling as much as possible. The adaptive control system model may independently modify the location of building shading in response to input environmental conditions, thereby achieving energy savings for both lighting and cooling. According to the findings, the automated control system model may reduce building energy consumption by 38% overall, which is close to the ideal level of energy conservation.

Downloads

Download data is not yet available.

References

[1] Guan Lingli. Influence of external shading on building energy consumption and indoor photothermal environment [D]. Nanjing: Nanjing University of Science and Technology, 2018.

[2] Residual theory. Study on the influence of building exterior shading on indoor light environment [D]. Chongqing: Chongqing University, 2019.

[3] Janiesch C, Zschech P, Heinrich K. Machine Learning and Deep Learning. Electronic Markets, 2021, 3(3): 685-695.

[4] Zhao J, Liu X. A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis [J]. Energy and Buildings, 2018, 174:293-308.

[5] Singaravel S, Suykens J, Geyer P Deep-learning neural-network architectures and methods: Using component-based models in building-design energy prediction [J]. Advanced Engineering Informatics, 2018.38:81-90.

[6] Chen S, Zhao L, Zheng L, et al. A rapid evaluation method for design strategies of high rise office buildings achieving nearly zero energy in Guangzhoul [J]. Journal of Building Engineering, 2021.44:103297.

[7] Zheng Lintao. Research on Year-Round Load Forecasting of Air Conditioning in Shopping Mall Modeling in the Pearl River Delta Region Based on Machine Learning Methods [D]. South China University of Technology, 2019.

[8] Xie J, Sawyer A 0. Simulation-assisted data-driven method for glare control with 5systems in offce buildings [J]. Building and Environment,automated shading, 2021.196: 107801.

[9] Luo Z, Sun C, Dong Q, et al. An innovative shading controller for blinds in an open-plan office using machine learning []. Building and Environment, 2021, 189:107529.

[10] Yeon S, Yu B, Seo B, et al. ANN based automatic slat angle control of venetian blind for minimized total load in an office building [l]. Solar Energy, 2019, 180:133-145.

[11] LOONEN RC G M, FAVOINO F, HENSEN J L M, et al. Review of current status, requireme11ts and opportunities for building performance simulation of adaptive facades [J]. Journal of building perfom1ance simulation. 2017, 10(2): 205-223.

[12] Ministry of Housing and Urban-Rural Development, PRC. General Code for Building Energy Conservation and Renewable Energy Utilization: GB 55015 Beijing: China Building and Building Press, 2021.

[13] NABILA, A, MARDALJEVIC. Useful daylight illuminances, A replacement for daylight factors [J]. Energy and B A surname gs. 2016, 38(7), 905-913.

[14] BAKKER L G, HOES-VAJN OEFFELEN E C M, LOONEN R C G M, et al. User satisfaction and interaction with automated dynamic facades: A pilot study [J]. Building and Environment. 2020, 78, 44-52.