딥러닝 기반 냉방 부하 및 표면 온도 예측을 위한 주요인자 분석
Analysis of Essential Factors in Deep Learning-based Prediction of Cooling Load and Surface Temperature
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Radiant floor heating systems ensure a uniform thermal distribution indoors and can provide better thermal comfort to occupants compared to convection systems. In Korea’s hot and humid climate, however, the use of radiant cooling systems involves some risks of condensation and overcooling. Integrated prediction of building load and surface temperature is essential to resolve these problems. Although various sensors are required for an integrated prediction, an excessive number of sensors can also reduce the practical applicability of a model. To enhance the applicability of predictions, we identified essential input variables to predict building loads and surface temperatures using SHapley Additive exPlanations (SHAP), which is one of the most accurate eXplainable artificial intelligence (XAI) techniques.
Abstract
Radiant floor heating systems ensure a uniform thermal distribution indoors and can provide better thermal comfort to occupants compared to convection systems. In Korea’s hot and humid climate, however, the use of radiant cooling systems involves some risks of condensation and overcooling. Integrated prediction of building load and surface temperature is essential to resolve these problems. Although various sensors are required for an integrated prediction, an excessive number of sensors can also reduce the practical applicability of a model. To enhance the applicability of predictions, we identified essential input variables to predict building loads and surface temperatures using SHapley Additive exPlanations (SHAP), which is one of the most accurate eXplainable artificial intelligence (XAI) techniques.