인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록·키워드
The Building Energy Management System (BEMS) continuously monitors and analyzes real-time energy consumption data such as electricity and gas to optimize efficiency and propose energy-saving strategies. However, communication failures, device malfunctions, and system updates can lead to missing or abnormal data, necessitating effective data recovery methods. Addressing these data gaps is crucial for maintaining reliability of energy analysis. Traditionally, simple linear interpolation has been used for data recovery. However, this method is prone to substantial inaccuracies. In addition, it is insufficient for complexities of energy systems. The power consumption of a building is heavily influenced by heating and cooling loads, which are closely related to outdoor conditions. To restore missing power consumption data, we proposed a method that could identify a day with similar changes in outdoor enthalpy variation - a function of temperature and humidity - as the day with missing data. Power consumption pattern from this similar day was then used to reconstruct lost data. The efficacy of the proposed method was evaluated using CV-RMSE (Coefficient of variation of root mean square error), demonstrating a high degree of accuracy, with recovered data showing a deviation of just 3.1% from actual values. This enhanced methodology not only can improve data recovery accuracy, but also can reinforce robustness of energy consumption analysis, thereby supporting more reliable energy management decisions.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-25-02-092457316
