http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
유전프로그래밍과 BEMS 데이터를 이용한 실내온도 기계학습 모델
서원준(Suh, Won Jun),박철수(Park, Cheol Soo) 대한건축학회 2016 대한건축학회논문집 Vol.32 No.6
Recently, BEMS(Building Energy Management Systems) are widely adopted in large existing buildings and there is a growing interest in applying model-assisted optimal control based on the BEMS data. Unfortunately, current BEMS are used only for measurement, data collection and rule-based operation. It would be ideal if a building’s data-driven energy model can be automatically generated out of BEMS data and is used for real-time optimal control. This paper presents such approach that a data-driven genetic programming can be beneficially utilized for automatic development of a room air temperature prediction model. In this study, the room air temperature prediction model was developed and successfully validated using the genetic programming and actual BEMS data. In the paper, pros and cons of the genetic programming approach is discussed.
발견적해법과 유전알고리즘을 이용한 우체국 건물 에너지 최적화
서원준(Suh Won-Jun),박철수(Park Cheol-Soo) 한국건축친환경설비학회 2011 한국건축친환경설비학회 학술발표대회 논문집 Vol.2011 No.3
In last year 2010, there was an energy saving design competition hosted by a South Korean government agency. In this design competition, important simulation parameters were given by the client such as density and schedule of lights, occupants, equipment, building operation, ventilation rate, the angle of blind slats, etc. Thus, the simulationists are not allowed to make a significant change to the original design of the building. The design options that the simulationists can propose are as follows: insulation thickness, location of blinds, addition of LED lights, and glazing type. In this paper, the practical heuristic approach based on experience, expertise and intuition with a whole building simulation tool, EnergyPlus, is discussed in comparison with the academic solution so-called a meta heuristic method derived from genetic algorithm in terms of the difference in energy savings, causes of those differences.
건물 에너지 진단을 위한 시뮬레이션 적용시 쟁점과 한계
서원준(Suh, Won-Jun),박철수(Park, Cheol-Soo) 대한건축학회 2012 대한건축학회논문집 Vol.28 No.1
This paper reports difficulties and issues to develop a whole building simulation model for energy diagnosis of a campus library building. This work was initiated to assess energy performance of the real-life building in collaboration with the campus facility management department. In the paper, the following are reported: 1) issues in data gathering: building, occupants, operation schedules, energy metering, 2) development and calibration of an energy simulation model, 3) comparison of the simulation results with measurements. In data gathering, even though many relevant information (drawings, documents, specifications, records of building operation, energy bills) were provided by the facility managers, the authors faced many problems to find accurate information for simulation runs. In this section, what issues and difficulties exist and how to deal with those (e.g., treatment of missing and uncertain data) are addressed. Secondly, the issues in the process of developing a building energy simulation model are discussed, such as how to zone the real-complex atypical building (7 storey with a vertical atrium in the center), how to model 2 chillers, 13 AHUs serving different zones, how to convert local weather data for EnergyPlus weather data format, etc. Lastly, the simulation results are compared with the measured energy use. With this comparison, it is discussed the difference between simulation prediction and measurement, what parameters cause uncertainty in simulation prediction, how to minimize the uncertainty by inspecting the process of real-life project.