ANN 기반 냉수 및 냉각수 온도 설정값 최적화 알고리즘의 실증 평가 및 에너지 절감 효과 분석 :In-situ application and energy saving effect of ANN-based chilled water and condenser water temperatures set-point optimization algorithm

강원희

추천

검색

자료유형: 학위논문

저자정보: 강원희 (고려대학교, 고려대학교 대학원)

지도교수: 이광호

발행연도: 2021

저작권: 고려대학교 논문은 저작권에 의해 보호받습니다.

이용수12

이 논문의 연구 히스토리 (3)

2021

ANN 기반 냉수 및 냉각수 온도 설정값 최적화 알고리즘의 실증 평가 및 에너지 절감 효과 분석

강원희 건축학과 2021.01 학위논문

2019

ANN 기반 공조설비 최적화 알고리즘의 냉방 에너지 절감 효과

강원희 , 이종만 , 이제헌 외 3명 대한설비공학회 학술발표대회논문집 2019.11 학술대회자료

냉수와 냉각수 온도 최적제어를 위한 실증용 ANN 모델 개발

강원희 , 이종만 , 이제헌 외 3명 대한설비공학회 학술발표대회논문집 2019.11 학술대회자료

이 논문의 후속연구가 궁금하신가요?
연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
이 논문의 연구 히스토리 확인하기

초록· 키워드

오류제보하기

문명의 발달에 따라 인류의 에너지 사용량은 급증하고 있고, 그로 인하여 인류는 더 많은 에너지를 필요로 한다. 국제에너지 기구인 IEA(International Energy Agency)의 “The Future of Cooling” 보고서에 의하면, 전 세계 에너지 수요는 경제의 발전과 지역의 냉방 및 난방 수요의 증가에 따라 지난 10년간 가장 빠른 속도로 증가하였고, 냉방을 유 지하기 위해 사용하는 전력에너지는 전 세계 건물의 약 20%를 차지한다고 발표하였다. 한국의 건물부문 에너지소비량은 한국 내의 에너지소비량의 약 23%를 차지하며, 건물은 한국에서 사용되는 전력의 약 45%를 차지한다. 이와 더불어 과학적 발전과 경제적 성장 으로 인한 최근 건물의 대형화·고층화, 생활 수준의 향상에 따른 건물 내에서의 쾌적 환 경 조성을 위한 냉·난방 및 조명의 전력사용량 증가, 설비 기기의 고급화, 겨울철 냉방기 기 가동 등으로 인하여 건물의 전력소비량은 점점 증가하고 있는 추세이다. 따라서, 본 연구에서는 상업용 건물의 HVAC 시스템의 에너지 소비를 줄이기 위해서, 인공신경망 (ANN:Artificial Neural Network) 기반의 실시간 모델 예측 제어(MPC:Model Predictive Control) 알고리즘 및 최적화 알고리즘을 개발하였다. 또한, 개발한 알고리즘을 실제 건물에 적용하였으며, 알고리즘을 통한 냉방 전력 에너지소비량 절감 효과를 분석하 기 위해 실측 데이터를 활용한 냉방에너지 절감에 대한 분석을 진행하였다. 이를 위한 시 스템 제어변수로 냉동기의 냉수 출수 온도와 냉각탑의 냉각수 출수 온도로 설정하였다. 에너지 절감 효과 분석 및 알고리즘 성능평가를 위한 방법으로는, 냉수 출수 온도 및 냉 각수 출수 온도를 가변 제어하는 ANN 제어를 적용하였을 때의 에너지소비량 및 COP와 냉수 출수 온도 및 냉각수 출수 온도를 고정하는 제어방식인 일반제어 방식일 때의 에너 지소비량 및 COP를 비교·분석하여 연구를 진행하였다. 연구의 결과는 다음과 같다. ANN 모델의 정확성은 Cv(RMSE) 4.9%로 우수한 결과를 나타냈으며, ANN 알고리즘 적 용 시의 에너지 절감 분석 결과, 냉동기 평균 에너지 절감률은 24.7%, 평균 COP 상승률 은 28.2%로써 우수한 절감 효과를 보였다. 최종적으로 ANN 기반 제어 알고리즘의 에너 지 절감 분석 결과, 냉동기와 냉각탑의 전체 평균 에너지 절감률은 7.4%, 전체 평균 COP 상승률은 9.4%인 결과를 확인하였다.

With the development of civilization, humanity''s energy use is increasing rapidly, and as a result, humanity needs more energy. According to the report of “The Future of Cooling” by the International Energy Agency (IEA), the global energy demand has increased at the fastest rate in the past decade due to economic development and local cooling and heating demand. In addition, It is announced that the electric energy
it uses to maintain cooling accounts for about 20% of buildings worldwide. Building energy consumption in Korea accounts for about 23% of energy consumption, and buildings account for about 45% of electric energy used. In addition, larger/higher buildings due to scientific development and economic growth, increasing power consumption of cooling, heating and lighting to create a comfortable environment in the building according to the improvement of living standards, high-end equipment, operation of air conditioners in winter, etc. As a result, the power consumption of buildings is gradually increasing. Therefore, in this study, in order to reduce the energy consumption of HVAC systems in commercial buildings, an artificial neural network (ANN) based real-time model predictive control (MPC) algorithm and an optimization algorithm
were developed. In addition, the developed algorithm was applied to an actual building, and an analysis of cooling energy reduction using in-situ data was conducted to analyze the effect of reducing cooling electric energy consumption through the algorithm. The system control variables for this were set as the
chilled water outlet temperature of the chiller and the condenser water outlet temperature of the cooling tower. In order to analyze the energy saving effect and evaluate the performance of the algorithm, energy consumption and COP analysis were conducted by comparing the control method when ANN is applied
and the control method without ANN. The results of the study are as follows. The accuracy of the ANN model was Cv(RMSE) 4.9%, showing excellent results, and as a result of energy saving analysis when the ANN algorithm was applied, the average chiller energy saving rate was 24.7% and the average COP increase
rate was 28.2%, showing excellent savings. Finally, as a result of energy saving analysis of the ANN-based control algorithm, the overall average energy saving rate of the chiller and cooling tower was 7.4%, and the overall average COP increase rate was 9.4%.

#Chilled water temperature #Condenser water temperature #Cooling energy #COP #Artificial neural network

목 차
第Ⅰ 章서 론
1.1 연구의 배경 ····································································································································1
1.2 연구의 필요성 및 목적 ················································································································4
1.3 기존 연구분석 ································································································································6
1.3.1 국내 문헌 연구 ·····················································································································6
1.3.2 국외 문헌 연구 ·····················································································································7
1.4 연구의 방법 및 범위 ····················································································································9
第2 章연구의 이론적 배경
2.1 대상 건물 및 공조시스템 개요 ································································································12
2.1.1 건물에너지관리시스템(BEMS) ························································································12
2.1.2 중앙공조시스템 일반제어 개요 ·······················································································14
2.1.3 대상 건물 ·····························································································································15
2.1.4 대상 건물의 공조시스템 ···································································································16
2.2 Machine Learning 기반의 ANN 제어 개요 ·········································································18
2.2.1 ANN(인공신경망, Artificial Neural Network) ····························································18
2.2.2 프로그래밍 언어 ·················································································································20
第3 章ANN 예측 모델링 조건 및 구축방법
3.1 데이터 실증 ··································································································································21
3.2 ANN 예측모델 개요 ··················································································································21
3.3 ANN 예측모델 최적화 및 결정 ······························································································23
3.4 예측모델 최적 지점 탐색 ··········································································································28
第4 章최적화 알고리즘의 실증 성능평가
4.1 현장 운전데이터 수집 개요 ······································································································29
4.2 운전데이터 정리 및 재구성 ······································································································30
4.3 처리 열량 및 COP 계산식 산출 ······························································································31
第5 章결과 분석
5.1 ANN 모델 에너지 저감 효과 검증 개요 ··············································································33
5.2 냉동기 결과 분석 ························································································································33
5.2.1 냉동기 전력소비량 분석 ···································································································33
5.2.2 냉동기 COP 분석 ··············································································································34
5.2.3 냉동기 부하 구간별 에너지 절감 효과 분석 ·······························································36
5.3 시스템 결과 분석 ························································································································38
5.3.1 시스템 전력소비량 분석 ···································································································38
5.3.2 시스템 COP 분석 ··············································································································39
5.3.3 시스템 부하 구간별 에너지 절감 효과 분석 ·······························································41
第6 章연구의 추가 보완사항 및 검토
6.1 ANN 모델 제어 검토 및 보완사항 ························································································44
6.2 학습데이터 부족으로 인한 이상 예측값 ················································································44
6.3 외기습구온도에 따른 냉각수 설정 온도 제한 ······································································46
6.4 소결 및 요약 ································································································································49
第7 章결론 ········································································································································52
참고문헌 ·················································································································································55

최근 본 자료

전체보기

구분	그룹	데이터 항목
AI 학습용 데이터	원문	원문 PDF 파일
AI 학습용 데이터	원문 + 메타 (기본/상세)	원문 PDF 파일 및 서지정보 CSV
대량 구매용 데이터	B2B 구독 방식	특정 자료 한정으로 원문 접근 권한 부여
대량 구매용 데이터	URL 전달 방식	바로 PDF 뷰어를 열람할 수 있는 URL 제공

구분	그룹	데이터 항목
AI 학습용 데이터	기본 메타	발행기관명, 간행물명, 권호명, 권(vol), 호(issue), 통권, 발행연도, 발행월, 논문명, 저자명, 시작페이지, 종료페이지, 전체페이지, 상세페이지URL
상세 메타 데이터	발행기관 메타	발행기관 이명, 영문명, 창립연도, 홈페이지URL, 발행기관 소개
	간행물 메타	부제목, 간행물 유형, ISSN, ISBN, 최초발행연도, 폐간연도, 간행빈도, 발행주기, 등재사항, 이용수, 피인용수, 권호수, 논문수, 표지이미지
	논문 메타	작성 언어, 부제목, 대등제목, 목차, 키워드, 초록, 이미지, 참고문헌, 이용수, 피인용수, 논문활용도, DBpia통합주제분류, KDC분류, DDC분류, 한국연구재단분류, UCI, DOI
	저자 메타	소속기관, 소속부서, 직급, 연구분야, 연구키워드, 이용수, 피인용수, 저자 논문활용도

구분	그룹	데이터 항목
※ 결합형/맞춤형 메타 데이터는 신청 내용에 따라 다양하게 제공 가능
이용순위 정보	주제분야별 많이 이용된 논문	“인문학”에서 많이 이용된 논문 TOP100
	이용기관별 많이 이용된 논문	“중고등학교”에서 많이 이용된 논문 TOP100
	세부기관별 많이 이용된 논문	“서울대학교”에서 많이 이용된 논문 TOP100
	키워드별 많이 이용된 논문	“Chat GPT”에서 많이 이용된 논문 TOP100
키워드 정보	많이 이용된 키워드	특정기간/분야/저널 내 많이 이용된 키워드
	많이 발행된 키워드	특정기간/분야/저널 내 많이 발행된 키워드
	많이 검색된 키워드	특정기간/분야/저널 내 많이 검색된 키워드
	연구 트렌드 키워드	특정 키워드 연관 연구동향 분석 데이터 키워드

논문 기본 정보

이 논문의 연구 히스토리 (3)

초록· 키워드

목차

최근 본 자료

댓글(0)