Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting Approach
Occupant behavior (OB) has a significant impact on household air-conditioner (AC) energy use. In recent years, bottom-up simulation coupled with stochastic OB modeling has been intensively developed for estimating residential AC consumption. However, a comprehensive analysis of the diverse behaviora...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/13/2/521 |
| _version_ | 1827758153952919552 |
|---|---|
| author | Jiajun Lyu Aya Hagishima |
| author_facet | Jiajun Lyu Aya Hagishima |
| author_sort | Jiajun Lyu |
| collection | DOAJ |
| description | Occupant behavior (OB) has a significant impact on household air-conditioner (AC) energy use. In recent years, bottom-up simulation coupled with stochastic OB modeling has been intensively developed for estimating residential AC consumption. However, a comprehensive analysis of the diverse behavioral preference patterns of occupants regarding AC use is hampered by the limited availability of large-scale residential energy demand data. Therefore, this study aimed to develop a prediction model for the residential household’s AC usage considering various OB-related diversity patterns based on monitoring data of appliance-level electricity use in a residential community of 586 households in Osaka, Japan. First, individual operation schedules and thermal preferences were identified and quantitatively extracted as the two main factors for the diverse behaviors across the whole community. Then, a clustering analysis classified the target households, finding four typical patterns for schedule preferences and three typical patterns for thermal preferences. These results were used, with time and meteorological data in the summer seasons of 2013 and 2014, as inputs for the proposed prediction model using Extreme Gradient Boosting (XGBoost). The optimized XGBoost model showed a satisfactory prediction performance for the on/off state in the testing dataset, with an F1 score of 0.80 and an Area under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.845. |
| first_indexed | 2024-03-11T09:02:41Z |
| format | Article |
| id | doaj.art-19d32880af3b47f7b12fa1243fe7bc45 |
| institution | Directory Open Access Journal |
| issn | 2075-5309 |
| language | English |
| last_indexed | 2024-03-11T09:02:41Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj.art-19d32880af3b47f7b12fa1243fe7bc452023-11-16T19:33:53ZengMDPI AGBuildings2075-53092023-02-0113252110.3390/buildings13020521Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting ApproachJiajun Lyu0Aya Hagishima1Interdisciplinary Graduate School of Science Engineering (IGSES), Kyushu University, Fukuoka 816-8580, JapanInterdisciplinary Graduate School of Science Engineering (IGSES), Kyushu University, Fukuoka 816-8580, JapanOccupant behavior (OB) has a significant impact on household air-conditioner (AC) energy use. In recent years, bottom-up simulation coupled with stochastic OB modeling has been intensively developed for estimating residential AC consumption. However, a comprehensive analysis of the diverse behavioral preference patterns of occupants regarding AC use is hampered by the limited availability of large-scale residential energy demand data. Therefore, this study aimed to develop a prediction model for the residential household’s AC usage considering various OB-related diversity patterns based on monitoring data of appliance-level electricity use in a residential community of 586 households in Osaka, Japan. First, individual operation schedules and thermal preferences were identified and quantitatively extracted as the two main factors for the diverse behaviors across the whole community. Then, a clustering analysis classified the target households, finding four typical patterns for schedule preferences and three typical patterns for thermal preferences. These results were used, with time and meteorological data in the summer seasons of 2013 and 2014, as inputs for the proposed prediction model using Extreme Gradient Boosting (XGBoost). The optimized XGBoost model showed a satisfactory prediction performance for the on/off state in the testing dataset, with an F1 score of 0.80 and an Area under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.845.https://www.mdpi.com/2075-5309/13/2/521residential air-conditioning usageoccupant’s behavior diversityclustering analysisthermal preferenceschedule preferenceextreme gradient boosting method |
| spellingShingle | Jiajun Lyu Aya Hagishima Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting Approach Buildings residential air-conditioning usage occupant’s behavior diversity clustering analysis thermal preference schedule preference extreme gradient boosting method |
| title | Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting Approach |
| title_full | Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting Approach |
| title_fullStr | Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting Approach |
| title_full_unstemmed | Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting Approach |
| title_short | Predicting Diverse Behaviors of Occupants When Turning Air Conditioners on/off in Residential Buildings: An Extreme Gradient Boosting Approach |
| title_sort | predicting diverse behaviors of occupants when turning air conditioners on off in residential buildings an extreme gradient boosting approach |
| topic | residential air-conditioning usage occupant’s behavior diversity clustering analysis thermal preference schedule preference extreme gradient boosting method |
| url | https://www.mdpi.com/2075-5309/13/2/521 |
| work_keys_str_mv | AT jiajunlyu predictingdiversebehaviorsofoccupantswhenturningairconditionersonoffinresidentialbuildingsanextremegradientboostingapproach AT ayahagishima predictingdiversebehaviorsofoccupantswhenturningairconditionersonoffinresidentialbuildingsanextremegradientboostingapproach |