DOI QR코드

DOI QR Code

Development of an Artificial Neural Network Model for a Predictive Control of Cooling Systems

건물 냉방시스템의 예측제어를 위한 인공신경망 모델 개발

  • Kang, In-Sung (School of Architectural and Building Science, Chung-Ang University) ;
  • Yang, Young-Kwon (School of Architectural and Building Science, Chung-Ang University) ;
  • Lee, Hyo-Eun (School of Architectural and Building Science, Chung-Ang University) ;
  • Park, Jin-Chul (School of Architectural and Building Science, Chung-Ang University) ;
  • Moon, Jin-Woo (School of Architectural and Building Science, Chung-Ang University)
  • Received : 2017.08.09
  • Accepted : 2017.08.29
  • Published : 2017.10.31

Abstract

Purpose: This study aimed at developing an Artificial Neural Network (ANN) model for predicting the amount of cooling energy consumption of the variable refrigerant flow (VRF) cooling system by the different set-points of the control variables, such as supply air temperature of air handling unit (AHU), condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. Applying the predicted results for the different set-points, the control algorithm, which embedded the ANN model, will determine the most energy efficient control strategy. Method: The ANN model was developed and tested its prediction accuracy by using matrix laboratory (MATLAB) and its neural network toolbox. The field data sets were collected for the model training and performance evaluation. For completing the prediction model, three major steps were conducted - i) initial model development including input variable selection, ii) model optimization, and iii) performance evaluation. Result: Eight meaningful input variables were selected in the initial model development such as outdoor temperature, outdoor humidity, indoor temperature, cooling load of the previous cycle, supply air temperature of AHU, condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. The initial model was optimized to have 2 hidden layers with 15 hidden neurons each, 0.3 learning rate, and 0.3 momentum. The optimized model proved its prediction accuracy with stable prediction results.

Acknowledgement

Supported by : 국토교통부, National Research Foundation (NRF)

References

  1. 왕광익, 노경식, "신기후변화체제에 대비한 도시정책 방향", 국토연구원, 국토정책 Brief 608, 2017 // (Wang, Kwang-Ik, Noh, Kyung-Sik, "Urban Policy Direction for the New Climate Change Regime", Korea Research Institute for Human Settlements, 2017)
  2. 장향인, 조영흠, 조재훈, "건물에 설치된 신재생에너지관리시스템의 적용 현황 및 개선 방향", 대한건축학회논문집, 제 29권 제 2호, 2013 // (Jang, Hyang-In, Cho, Young-Hum, Jo, Jae-Hun, "Application and Improvement of the Renewable Energy Management System in Existing Buildings", Journal of the architectural institute of Korea, Vol. 29, No. 2, 2013)
  3. 에너지경제연구원, "2014년도 에너지총조사 보고서", 에너지경제연구원 통계정보시스템, 2014 // (Korea Energy Economics Institute, "Energy Consumption Survey 2014", 2014)
  4. 에너지경제연구원, "건물에너지소비 상설표본조사 연구", 에너지경제연구원 통계정보시스템, 2016 // (Korea Energy Economics Institute, "Building Energy Consumption Standing Sampling Survey", 2016)
  5. 지식경제부, "2016 에너지기술개발 실행계획", 2015 // (Ministry of Trade Industry and Energy, "2016 Energy Technology Development Plan", 2015)
  6. 국토교통부, "제1차 녹색건축물 기본계획", 2014 // (Ministry of Land, Infrastructure and Transport, "The 1st green building basic plan", 2014)
  7. 문현준, 김정원, "쾌적제어 알고리즘 기반 VRF 시스템의 냉방기 제어특성 실험", 한국건축친환경설비학회논문집, 제 9권 제 3호, 2015 // (Moon, Hyeun-Jun, Kim, Jeong-Won, "An Experimental Study on the Performance of a VRF Air Conditioning System with a Thermal Comfort Control Algorithm", Journal of KIAEBS Vol. 9, No. 3, 2015)
  8. 기현승, 박준원, 강기남, 김주욱, 송두삼, "TRNSYS 시뮬레이션을 통한 VRF시스템의 구현과 타당성 검증", 대한설비공학회 하계학술발표대회논문집, 2011 // (Ki, Hyun-Seung, Park, Jun-Won, Kang, Ki-Nam, Kim, Joo-Wook, Song, Doo-Sam, "Development of VRF System Module and Verification by TRNSYS Simulation", Journal of The Society of Air-conditioning and Refrigerating Engineers of Korea, 2011)
  9. 손재호, 김청융, "교육시설의 개념단계 공사비예측을 위한 인공신경망 모델 개발에 관한 연구", 한국건설관리학회 논문집, 제 7권 제 4호, 2006 // (Kim, Chung-Yung, Son, Jae-Ho, "A Study on the Model of Artificial Neural Network for Construction Cost Estimation of Educational Facilities at Conceptual Stage", Korea Journal of Construction Engineering and Management, Vol. 7, No. 4, 2006)
  10. ASHRAE Guideline 14, Measurement of Energy and Demand Savings, 2002
  11. McCulloch and Walter Pitts, A Logical Calculus of Ideas Immanent in Nervous Activity, Bulletin of Mathematical Biophysics, 1943
  12. Moon, Jin-Woo and Kim, Jong-Jin, Application of ANN in Residential Thermal Control, 11TH International Building Performance Simulation Association Conference, Building Simulation, 2009
  13. Moon, Jin-Woo and Kim, Jong-Jin, ANN-based Thermal Control Models for Residential Buildings, Building and Environment, 2010
  14. 이슬기, 정성관, 이우성, 박경훈, "인공신경망을 이용한 도시기온 예측 모형 구축", 대한국토계획학회지, 제 46권 제 1호, 2011 // (Lee, Seul-Gi, Jung, Sung-Gwan, Lee, Woo-Sung, Park, Kyung-Hun, "Predictive Model for Urban Temperature Using the Artificial Neural Network", Journal of Korea Planning Association, Vol. 46, No. 1, 2011)
  15. 이병옥, 태준성, 최재혁, "오류역전파 알고리즘을 이용한 사출성형금형 냉각회로 최적화", 한국공작기계학회지, 제 18권 제 4호, 2009 // (Rhee, Byung-Ok, Tae, Jun-Sung, Choi, Jae-Hyuk, "Injection Mold Cooling Circuit Optimization by Back-Propagation Algorithm, Journal of the Korean Society of Machine Tool Engineers, Vol.18, No.4, 2009)
  16. Randall C. O'Reilly and Yuko Munakata, Computational Explorations in Cognitive Neuroscience, MIT Press, 2000
  17. 권한솔, "인공신경망을 이용한 부하 예측 기반 대형 건물의 복합 냉동기 최적운영 방안", 박사학위논문 서울시립대학교, 2013 // (Kwon, Han-Sol, "Optimal Operating Strategy of a Hybrid Chiller Plant Utilizing Artificial Neural Network based Load Prediction in a Large Building Complex", Doctor's thesis in University of Seoul, 2013)
  18. 한도영, 윤형범, "건물부하예측을 이용한 공조기 운전제어 알고리즘에 관한 연구", 대한설비공학회 하계학술발표대회 논문집, 2002 // (Han, Do-Young, Youn, Hyoung-Bum, "Study on Air Handling Unit Control Algorithms by Using Building Load Prediction", Journal of The Society of Air-conditioning and Refrigerating Engineers of Korea, 2002)
  19. 이제헌, 송영학, 윤현진, 최동석, 태상진, 김익근, "수냉식 VRF 시스템 대상 설정값 제어 알고리즘 개발 및 효과 검증에 관한 연구", 대한설비공학회 하계학술발표대회 논문집, 2016 // (Lee, Je-Hyeon, Song, Young-Hak, Yoon, Hyun-Jin, Choi, Dong-Suk, Tae, Sang-Jin, Kim, Ik-Keun, "Development of VRF System Module and Verification by TRNSYS Simulation", Journal of The Society of Air-conditioning and Refrigerating Engineers of Korea, 2016)
  20. Chirag Deb, Lee Siew Eang, Junjing Yang and Mattheos Santamouris, Forecasting Diurnal Cooling Energy Load for Institutional Buildings using Artificial Neural Networks, Energy and Buildings 121, 2016
  21. Radu Platon, Vahid Raissi Dehkordi and Jacques Martel, Hourly Prediction of a Building's Electricity Consumption using Case-based Reasoning, Artificial Neural Networks and Principal Component Analysis, Energy and Buildings 92, 2015
  22. Pedro A. Gonzalez and Jesus M. Zamarreno, Prediction of Hourly Energy Consumption in Buildings based on a Feedback Artificial Neural Network, Energy and Buildings 37, 2005
  23. The U.S. D.O.E., EnergyPlus Engineering Reference Ver. 8.5; The Reference to EnergyPlus Calculations, 2011
  24. Samsung Electorincs Co., DVM S Water Technical Data Book, 2015
  25. Yang, In-Ho and Kim, Kwang-Woo, Prediction of the Time of Room Air Temperature Descending for Heating Systems in Buildings, Building and Environment, 2004
  26. Moon, Jin-Woo, Kim, Kyung-Jae and Min, Hyun-Suk, ANN-Based Prediction and Optimization of Cooling System in Hotel Rooms, Energies, 2015.
  27. 매스웍스코리아, https://kr.mathworks.com

Cited by

  1. Development of a Data-Driven Predictive Model of Supply Air Temperature in an Air-Handling Unit for Conserving Energy vol.11, pp.2, 2018, https://doi.org/10.3390/en11020407