주거용 공간 CO2 농도 예측 기계학습 모델 실증을 위한 기초 연구 = A Basic Study on Demonstrating Machine Learning Model for Predicting CO2 Concentration in Residential Houses

다국어 초록 (Multilingual Abstract)

In this study, the performance of an indoor CO2 concentration machine learning model learned using minimal data was verified, such as day, time, temperature, and CO2 concentration. These variables are easy to acquire in residential spaces. The prediction accuracy of three models—ANN, KNN, and LSTM—was confirmed using data from residential units, which are considered standard households in Korea. ANN achieved an R2 of 0.96, CvRMSE of 1.1%, and MBE of 2.14%, showing the best performance. Both KNN and LSTM demonstrated appropriate prediction stability (over 0.8), CvRMSE (within 2%), and MBE (within 4%). When applied to a unit scheduled for future demonstration of the ventilation algorithm, a similar level of prediction accuracy was confirmed, despite differences in shape and residential furniture compared to the standard unit. This study is a basic exploration of applying the ventilation algorithm to the demonstration unit. In future studies, we plan to apply this model to the demonstration unit and operate the ventilator according to the predicted values, aligning with the current legal operating standard of 0.5 ACH for regular operation. We intend to conduct a multifaceted performance evaluation of this ML model by comparing and analyzing the results with fan energy consumption and indoor CO2 concentration values.

참고문헌 (Reference)

• 1 김효준 ; 조영흠 ; 류성룡, "실내 이산화탄소 농도 예측을 위한 기계학습 모델 검증" 한국건축친환경설비학회 14 (14): 699-706, 2020
• 2 Alavi, H. S., "Predictive Models of Indoor Carbon Dioxide Concentration to Prevent Daily Decay of Productivity and Well-Being in Shared Offices" 2020 : 59-68, 2020
• 3 Skön, J. P., "Modelling indoor air carbon dioxide(CO2)concentration using neural network" 14 (14): 16-, 2012
• 4 Wei, W., "Machine learning and statistical models for predicting indoor air quality" 29 (29): 704-726, 2019
• 5 Statistics Korea, "Life Time Survey Result"
• 6 Zhong, L., "Indoor environmental quality evaluation of lecture classrooms in an institutional building in a cold climate" 11 (11): 6591-, 2019
• 7 Ahn, J., "Indoor air quality analysis using deep learning with sensor data" 17 (17): 2476-, 2017
• 8 Kallio, J., "Forecasting office indoor CO2concentration using machine learning with a one-year dataset" 187 : 107409-, 2021
• 9 Karaci, A., "Estimating the properties of ground-wastebrick mortars using DNN and ANN" 118 (118): 207-228, 2018
• 10 Laverge, J., "Energy saving potential and repercussions on indoor air quality of demand controlled residential ventilation strategies" 46 (46): 1497-1503, 2011
• 11 Clark, J. D., "Efficacy of occupancybased smart ventilation control strategies in energyefficient homes in the United States" 156 : 253-267, 2019
• 12 Choi, Y. J., "Development of an adaptive artificial neural network model and optimal control algorithm for a data center cyber–physical system" 210 : 108704-, 2022
• 13 Özcan, S. E., "Determination of the airflow pattern in a mechanically ventilated room with a temperaturebased sensor" 90 (90): 193-201, 2005
• 14 Pavlovas, V., "Demand controlled ventilation : A case study for existing Swedish multifamily buildings" 36 (36): 1029-1034, 2004
• 15 Tagliabue, L. C., "Data driven indoor air quality prediction in educational facilities based on IoT network" 236 : 110782-, 2021
• 16 Parkinson, T., "Continuous IEQ monitoring system : Context and development" 149 : 15-25, 2019