| 주 저자 | 김태연 |
|---|
| 공동 저자 | 김세헌, 이수진, 홍수연, 안소연, 오정민, 정재원 |
|---|
| 소속 | 한양대학교 건축공학과 |
|---|
| Abstract | Autonomous air conditioner control systems are gaining attention as a promising solution to reduce building energy consumption while
maintaining occupant comfort. However, conventional systems based on PMV-PPD models often fail to reflect individual thermal
preferences and face practical limitations in actual building environments. To address this, this study propose a data-driven method that
derives personalized preference ranges using environmental data and air conditioner control histories. An Artificial Neural Network (ANN)
model was trained on occupant control patterns under varying indoor conditions to estimate the likelihood of preferred, neutral, or
dissatisfied states. This suggests the model's potential to enhance personalized thermal comfort in autonomous HVAC systems |
|---|
| Keyword | Building Energy, Thermal Comfort, Air Conditioner, Machine
Learning, ANN |
|---|
| 페이지 | pp. 78~79 |
|---|
| 논문 파일 |
없음
|
|---|
| 게재일시 |
2025-05
|
|---|
| DOI | - |
|---|
| 학회/저널명 | 한국생태환경건축학회논문집 Vol.25, No.1 |
|---|
| 년도 | 2025 |
|---|
| 추가 문구 | - |
|---|
| 등록 일시 | 2025-12-30 17:18:13 |
|---|
