http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
건물 에너지 분석 및 예측에서의 시뮬레이션과 데이터드리븐 기법의 융합에 관한 연구
손은조(Sohn Eun-jo),김기석(Kim Gi-seok),이승복(Leigh Seung-b) 대한설비공학회 2018 대한설비공학회 학술발표대회논문집 Vol.2018 No.6
Building energy simulation has been developed over the last decades. Substantial attempts have been made to enhance its capability and analysis and prediction. Despite these efforts, the simulation tools require an enormous amount of input data so that it is difficult to handle and it takes much time for modeling. We call these models as detailed physical modeling. On the other hand, there are data-driven models such as neural network which estimates forward energy consumption based on actual data. Advanced researches proved estimation accuracy but there is a limitation with identifying data which influences the result at specific part. The Convergence model can advance these shortcomings. The convergence model can reduce time for modeling and possible identify factor which influence result in specific part. This study suggest way to analyze and predict building energy more accurately and economically in new and built buildings by using convergence modeling.
Change Point Model을 활용한 건물의 에너지 소비패턴 분석 방법
정성혁(Jeong, Seong-Hyeok),손은조(Sohn, Eun-Jo),이승복(Leigh, Seung-Bok) 대한건축학회 2021 대한건축학회 학술발표대회 논문집 Vol.41 No.1
In the field of building energy, the Change Point Model or Inverse Model is used as the easiest and most fundamental way to analyse energy consumption patterns or derive energy savings. In Korea, which mainly uses the 5-Parameter Change Point Model, many studies have been conducted to find cooling sensitivity and heating sensitivity, but unfortunately, it is hard to find a study that accurately calculates and utilises the values of cooling starting point, heating starting point, and base energy. Therefore, in this study, we present a methodology for finding all five parameters of the Change Point Model through the Modified Grid-search Method. Based on this study, we hope that the Change Point Model will be more widely used in the building energy sector.