| 논문명 |
기존건축물의 빙축열 시스템 최적 제어를 위한 기계학습 모델 / Machine Learning Model for Optimal Control of an Ice Thermal Storage System in an Existing Building / 추계-05. 건축환경및설비 |
| 저자명 |
신한솔(Shin, Han-Sol) ; 서원준(Suh, Won-Jun) ; 추한경(Chu, Han-Gyeong) ; 라선중(Ra, Seon-Jung) ; 박철수(Park, Cheol-Soo) |
| 수록사항 |
대한건축학회 학술발표대회 논문집, Vol.36 No.2 (2016-10) |
| 주제어 |
빙축열 시스템 ; 기계학습 ; 최적 제어 ; Ice Thermal Storage System ; Machine Learning ; Optimal Control |
| 요약2 |
The ice thermal storage system consisting of spherical ice balls is one of the most popular types in large office buildings. In practice, a freezing and defrosting operation for spherical ice balls is determined by a rule-of-thumb. If this rule-of thumb operation is replaced by a simulation model-based control, there is a significant potential for energy savings by keeping it from over freezing or under freezing. In this study, the authors developed a machine learning simulation model for the spherical ice thermal storage system installed in a 30-story office building (gross floor area: 32,600m2) in Seoul, Korea. Five different machine learning algorithms were chosen as follows: Artificial Neural Network, Support Vector Machine, Gaussian Process, Random Forest, and Genetic Programming. Based on the number of inputs used in the models, five prediction scenarios were made. It is shown that significant energy savings can be achieved. |
