Hybrid Model for Forecasting Indoor CO<sub>2</sub> Concentration
Indoor CO<sub>2</sub> concentration is considered a metric of indoor air quality that affects the health of occupants. In this study, a hybrid model was developed for forecasting the varying indoor CO<sub>2</sub> concentration levels in a residential apartment unit in the pre...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/12/10/1540 |
| _version_ | 1797474663123648512 |
|---|---|
| author | Ki Uhn Ahn Deuk-Woo Kim Kyungjoo Cho Dongwoo Cho Hyun Mi Cho Chang-U Chae |
| author_facet | Ki Uhn Ahn Deuk-Woo Kim Kyungjoo Cho Dongwoo Cho Hyun Mi Cho Chang-U Chae |
| author_sort | Ki Uhn Ahn |
| collection | DOAJ |
| description | Indoor CO<sub>2</sub> concentration is considered a metric of indoor air quality that affects the health of occupants. In this study, a hybrid model was developed for forecasting the varying indoor CO<sub>2</sub> concentration levels in a residential apartment unit in the presence of occupants by controlling the ventilation rates of a heat recovery ventilator. In this model, the mass balance equation for a single zone as a white-box model was combined with a Bayesian neural network (BNN) as a black box model. During the learning process of the hybrid model, the BNN estimated an aggregated unknown ventilation rate and transferred the estimation to the mass-balance equation. A parametric study was conducted by changing the prediction horizons of the hybrid model from 5 to 15 min, and the forecasting performance of the hybrid model was compared with the stand-alone mass balance equation. The hybrid model showed better forecasting performance than that of the mass balance equation on the experimental dataset for a living room and bedroom. The average MBE and CVRMSE of the hybrid model for the prediction horizon of 15 min were 0.65% and 5.23%, respectively, whereas those of the mass balance equation were 0.99% and 9.30%, respectively. |
| first_indexed | 2024-03-09T20:34:20Z |
| format | Article |
| id | doaj.art-b529d35800334d608ab1a84860bf47eb |
| institution | Directory Open Access Journal |
| issn | 2075-5309 |
| language | English |
| last_indexed | 2024-03-09T20:34:20Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj.art-b529d35800334d608ab1a84860bf47eb2023-11-23T23:15:59ZengMDPI AGBuildings2075-53092022-09-011210154010.3390/buildings12101540Hybrid Model for Forecasting Indoor CO<sub>2</sub> ConcentrationKi Uhn Ahn0Deuk-Woo Kim1Kyungjoo Cho2Dongwoo Cho3Hyun Mi Cho4Chang-U Chae5Department of Building Research, Korea Institute of Civil Engineering and Building Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si 10223, Gyeonggi-do, KoreaDepartment of Building Energy Research, Korea Institute of Civil Engineering and Building Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si 10223, Gyeonggi-do, KoreaDepartment of Building Energy Research, Korea Institute of Civil Engineering and Building Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si 10223, Gyeonggi-do, KoreaDepartment of Building Energy Research, Korea Institute of Civil Engineering and Building Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si 10223, Gyeonggi-do, KoreaDepartment of Building Research, Korea Institute of Civil Engineering and Building Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si 10223, Gyeonggi-do, KoreaResearch Strategic Planning Department, Korea Institute of Civil Engineering and Building Technology, 283 Goyangdae-ro, Ilsanseo-gu, Goyang-si 10223, Gyeonggi-do, KoreaIndoor CO<sub>2</sub> concentration is considered a metric of indoor air quality that affects the health of occupants. In this study, a hybrid model was developed for forecasting the varying indoor CO<sub>2</sub> concentration levels in a residential apartment unit in the presence of occupants by controlling the ventilation rates of a heat recovery ventilator. In this model, the mass balance equation for a single zone as a white-box model was combined with a Bayesian neural network (BNN) as a black box model. During the learning process of the hybrid model, the BNN estimated an aggregated unknown ventilation rate and transferred the estimation to the mass-balance equation. A parametric study was conducted by changing the prediction horizons of the hybrid model from 5 to 15 min, and the forecasting performance of the hybrid model was compared with the stand-alone mass balance equation. The hybrid model showed better forecasting performance than that of the mass balance equation on the experimental dataset for a living room and bedroom. The average MBE and CVRMSE of the hybrid model for the prediction horizon of 15 min were 0.65% and 5.23%, respectively, whereas those of the mass balance equation were 0.99% and 9.30%, respectively.https://www.mdpi.com/2075-5309/12/10/1540machine learningbayesian neural networkhybrid modelCO<sub>2</sub> concentrationventilation system |
| spellingShingle | Ki Uhn Ahn Deuk-Woo Kim Kyungjoo Cho Dongwoo Cho Hyun Mi Cho Chang-U Chae Hybrid Model for Forecasting Indoor CO<sub>2</sub> Concentration Buildings machine learning bayesian neural network hybrid model CO<sub>2</sub> concentration ventilation system |
| title | Hybrid Model for Forecasting Indoor CO<sub>2</sub> Concentration |
| title_full | Hybrid Model for Forecasting Indoor CO<sub>2</sub> Concentration |
| title_fullStr | Hybrid Model for Forecasting Indoor CO<sub>2</sub> Concentration |
| title_full_unstemmed | Hybrid Model for Forecasting Indoor CO<sub>2</sub> Concentration |
| title_short | Hybrid Model for Forecasting Indoor CO<sub>2</sub> Concentration |
| title_sort | hybrid model for forecasting indoor co sub 2 sub concentration |
| topic | machine learning bayesian neural network hybrid model CO<sub>2</sub> concentration ventilation system |
| url | https://www.mdpi.com/2075-5309/12/10/1540 |
| work_keys_str_mv | AT kiuhnahn hybridmodelforforecastingindoorcosub2subconcentration AT deukwookim hybridmodelforforecastingindoorcosub2subconcentration AT kyungjoocho hybridmodelforforecastingindoorcosub2subconcentration AT dongwoocho hybridmodelforforecastingindoorcosub2subconcentration AT hyunmicho hybridmodelforforecastingindoorcosub2subconcentration AT changuchae hybridmodelforforecastingindoorcosub2subconcentration |