인공신경망을 이용한 건물의 에너지 모델 최적화 알고리즘 개발 및 검증에 관한 연구 = Development of Optimization Algorithms for Building Energy Model Using Artificial Neural Networks

다국어 초록 (Multilingual Abstract)

This paper discusses the modeling methodologies and optimization methods for building energy system using time series auto regression artificial neural networks. The model can be integrated into energy solution tools for building energy assessment, optimization, and many other applications. The model predicts whole building energy consumptions as function of four input variables, dry bulb and wet bulb outdoor air temperatures, hour of day and type of day. To train and test the models, data from simulations are used for the analysis. Advanced computational methods are used for data analysis and preprocessing. Different neural network structures are tested along with various input and feedback delays to determine the one yielding the best results. The optimization method was also developed to automate the process of finding the best model structure that can produce the best accurate prediction against the actual data. The results show that the developed model can provide results sufficiently accurate for its use in various energy efficiency and saving estimation applications.

목차 (Table of Contents)

• Abstract
• 1. 서론
• 2. 빌딩에너지관리시스템(BEMS) 과 최적제어
• 3. 연구방법
• 4. 결과 및 분석
• 5. 결론
• REFERENCES

참고문헌 (Reference)

1 서동연, "인공지능에 의한 건축형태의 인지방법에 관한 연구" 대한건축학회 19 (19): 17-24, 2003

2 문진우, "인공지능망과 뉴로퍼지 모델을 이용한 주거건물 냉난방 시스템 조절 로직 및 예비 성능 시험" 한국주거학회 22 (22): 113-122, 2011

3 서원준, "유전프로그래밍과 BEMS 데이터를 이용한 실내온도 기계학습 모델" 대한건축학회 32 (32): 105-112, 2016

4 DOE, Department Of Energy, "Using DOE Commercial Reference Buildings for Simulation Studies" 2010

5 Kang, I., "Recent Research Trends of Artificial Intelligence in Buildings - Review of Domestic and International Journal Papers -" 36 (36): 635-647, 2016

6 Suh, W., "Real-time Optimal Control of Chiller using Genetic Programming" 36 (36): 627-628, 2016

7 Kim, Y., "Real-Time Optimal Control of Chiller Operation using Data driven Gaussian Process Model" 195-196, 2014

8 Kim, Y., "Optimized neural network for Real time Model-based Predictive Control" 159-160, 2015

9 Nassif, N., "Modeling and Optimization of HVAC systems using Artificial Neural Network and Genetic Algorithm" 7 (7): 237-245, 2014

10 Shin, H., "Machine Learning Model for Optimal Control of an Ice Thermal Storage System in an Existing Building" 36 (36): 629-630, 2016

11 Seong, N., "Development of module service on central HVAC system to applicate Building energy management system(BEMS)" 114-116, 2016

12 Ra, S., "Development and cross-comparison of five machine learning models for HVAC systems in an existing office building" 36 (36): 625-626, 2016

13 Nassif, N., "Development and Testing of Building Energy Model Using Non-Linear Auto Regression Neural Networks" 2016

14 Park, D., "Control of HVAC optimal start/stop using Artificial Neural Network" 395-396, 2013

15 Moon, J., "Comparative analysis on the thermal control performance of the different application level of artificial networkbased methods for the double skin envelope building" 14 (14): 84-85, 2014

16 Lee, H., "Artificial intelligence approach to architectural design methodology" 7 (7): 23-36, 1991

17 Yang, I., "A Study on the application of Artificial Neural Network for optimal operation of HVAC systems" 13 (13): 97-107, 1997