Browse > Article
http://dx.doi.org/10.5659/JAIK_PD.2014.30.7.211

Gaussian Process Model for Real-Time Optimal Control of Chiller System  

Kim, Young-Jin (선문대학교, 건축사회환경학부)
Park, Cheol-Soo (성균관대학교 건축토목공학부)
Publication Information
Journal of the Architectural Institute of Korea Planning & Design / v.30, no.7, 2014 , pp. 211-220 More about this Journal
Abstract
For Model-Predictive Control (MPC) to be implemented in real application, data driven inverse models are advantageous since they are easily constructed as well as relatively fast and accurate, compared to first principle based models (simplified calculation [ISO 13790], dynamic simulation [EnergyPlus, ESP-r, TRNSYS, etc.], state space models, etc.). Gaussian Process Model (GPM), one of the inverse methods, can be beneficially used for real time stochastic optimal control of nonlinear building systems, since the GPM consumes much less computational time and does not require significant efforts. The GPM is a black-box model based on Bayesian approach based on measured in-output dataset. For real-time optimal control of chiller operation, this paper presents a coupling between the GPM and an optimization routine in MATLAB optimization toolbox. The two control parameters studied in the paper are the outlet temperatures of chilled water loop and cooling tower loop. In particular, Genetic Algorithm (GA), one of the meta-heuristic methods, was applied to find optimal control strategy. It is elaborated in the paper that GPM produces reliable control results reflecting probabilistic natures of the chiller system.
Keywords
Model Predictive Control(MPC); Inverse model; Gaussian Process; Bayesian approach; Genetic Algorithm;
Citations & Related Records
Times Cited By KSCI : 5  (Citation Analysis)
연도 인용수 순위
1 Lepore, R., Renotte, C., Frere, M. and Dumont, E., Energy Consumption Reduction in Office Buildings using Model-based Predictive Control, Proceedings of the 13th IBPSA Conference, August 26-28, Chambery, France, p.p.2459-2465, 2013
2 Neal, R.M., Bayesian Learning for Neural Networks, Springer, New York, Lecture Notes in Statistics 118, 1996
3 Nouidui, T., Wetter, M. and Zuo, W., Functional Mock-up Unit for Co-simulation Import in EnergyPlus, Journal of Building Performance Simulation, 7(3), p.p.192-202, 2014   DOI
4 Park, C.S. and Augenbroe, G., Local vs. Integrated Control Strategies for Double-Skin Systems, Automation in Construction, Vol.30, p.p.50-56, 2013   DOI   ScienceOn
5 Rasmussen, C.E., Gaussian Processes in Machine Learning, Technical report, Max Planck Institute for Biological Cybernetics, 72076 Tubingen, Germany, 2004
6 Rasmussen, C.E. and Williams, C.K.I., Gaussian Processes for Machine Learning, the MIT Press, ISBN 026218253X, 2006
7 Schaffer, J.D., Multi objective optimization with vector evaluated genetic algorithms, Proceedings of the First International Conference on Genetic Algorithms, Hillsdale, New Jersey, p.p.93-100, 1985
8 Wouters, P., Heijmans, N. and Loncour, X., Outline for a General Framework for the Assessment of Innovative Ventilation Systems, RESHYVENT report, 2004
9 Suter, G., Icoglu, O., Mahdavi, A. and Spasojevic, B., Position Uncertainty in Space Scene Reconstruction for Simulation-based Lighting Control, Proceedings of the 9th IBPSA Conference, August 15-18, EcolePolytechnique de Montreal, Montreal, Canada, p.p.1191-1198, 2005
10 Vanhatalo, J., Riihimaki, J., Hartikainen, J. and Vehtari, A., Bayesian Modeling with Gaussian Processes using the MATLAB toolbox GPstuff. submitted, 2011
11 Wetter, M., Co-simulation of Building Energy and Control Systems with the Building Controls Virtual Test Bed, Journal of Building Performance Simulation, 4(3), p.p.185-203, 2011   DOI
12 Yoon, S.H., Park, C.S. and Augenbroe, G., On-line Parameter Estimation and Optimal Control Strategy of a Double-Skin System, Building and Environment, 46(5), p.p.1141-1150, 2011   DOI   ScienceOn
13 Zhang, Y., O'Neill, Z., Wanger, T. and Augenbroe, G., An Inverse Model with Uncertainty Quantification to Estimate the Energy Performance of an Office Building, Proceedings of the 13th IBPSA Conference, August 26-28, Chambery, France, p.p.614-621, 2013
14 Zhao, J., Lam, K.P. and Ydstie, B.E., Energyplus Model-based Predictive Control (EMPC) by using MATLA/SIMULINK and MLE+, Proceedings of the 13th IBPSA Conference, August 26-28, Chambery, France, p.p.2466-2473, 2013
15 윤경수, 박철수, 이중 외피 시스템의 수준별 제어, 대한건축학회논문집, 26(11), p.p.317-326, 2010
16 윤성환, 박철수, 이중외피 시스템의 정적 및 동적 제어 전략, 대한건축학회논문집, 25(2), p.p.223-231, 2009
17 김영진, 윤경수, 박철수, 패턴 서치 알고리즘과 유전자 알고리즘을 이용한 이중외피 시스템의 최적 제어, 대학건축학회논문집, 27(7), p.p.239-248, 2011
18 김영진, 박철수, 김인한, 몬테카를로 빌딩 시뮬레이션의 샘플링 방법과 모집단 추정, 대학건축학회논문집 28(6), p.p.227-238, 2012
19 Abushakra, B., An Inverse Model to Predict and Evaluate the Energy Performance of Large Commercial and Institutional Buildings, IBPSA Conference Proceedings, Prague, Czech Republic, 1997
20 윤성환, 박철수, 기존 건축물을 위한 x-Ray 개념의 에너지 모델 작성과 평가, 대한건축학회논문집, 30(1), p.p.235-244, 2014
21 Afram, A. and Janabi-Sharifi, F., Theory and Applications of HVAC Control Systems-A Review of Model Predictive Control (MPC), Building and Environment, Vol.72, p.p.343-355, 2014   DOI   ScienceOn
22 ASHRAE, Guideline14-Measurement of energy and demand savings, American Society of Heating, Refrigerating, and Air-Conditioning Engineers, Atlanta, GA, 2002
23 Augenbroe, G., Brown, J., Heo1, Y.S., Kim, S.H., Li, Z., McManus, S. and Zhao, F., Lessons from an Advanced Building Simulation Course, The Third National Conference of IBPSA-USA, Berkeley, California, July 30-August 1, 2008
24 Bazjanac, V., BIM that Supports Life Cycle of Buildings, BuildingSMART Korea International Forum 2010, Seoul, Korea, April 21, 2010
25 de Wit, S., Uncertainty in Prediction of Thermal Comfort in Buildings, Ph.D. thesis, Tu Delft Netherlands, 2001
26 Bernal, W., Madhur, B., Truong, N. and Rahul, M., MLE+: A Tool for Integrated Design and Deployment of Energy Efficient Building Controls, 4th ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings, Toronto, 2012
27 Breesch, H. and Janssens, A., Building Simulation to Predict the Performances of Natural Night Ventilation: Uncertainty and Sensitivity Analysis, Proceedings of the 9th IBPSA Conference, August 15-18, Ecole Polytechnique de Montreal, Montreal, Canada, p.p.115-122, 2005
28 Gilks, W. R., Richardson, S. and Spiegelhalter, D., Markov Chain Monte Carlo in Pratice, Chapman and Hall, 1995
29 de Wilde, P. and Tian, W., Predicting the Performance of an Office under Climate Change: A Study of Metrics, Sensitivity and Zonal Resolution, Energy and Buildings, Vol.42, p.p.1674-1684, 2010   DOI   ScienceOn
30 Dijk, H. and Spiekman, M., Energy Performance of Buildings; Outline for Harmonised EP Procedures. Final report EU SAVE ENPER project, Task B6. TNO Building and Construction Research, Delft(NL), June 29, 2004 (http://www.enper.org)
31 Heo, Y.S. and Zavala, V.M., Gaussian Process Modeling for Measurement and Verification of Building Energy Savings, Energy and Buildings, Vol.53, p.p.7-18, 2012
32 Herzog, S., Atabay, D., Jungwirth, J. and Mikulovic, V., Self-adapting Building Models for Model Predictive Control, Proceedings of the 13th IBPSA Conference, August 26-28, Chambery, France, p.p.2489-2493, 2013
33 Hopfe, C.J., Uncertainty and Sensitivity Analysis in Building Performance Simulation for Decision Support and Design Optimization. PhD thesis, Technische Universiteit Eindhoven, 2009
34 Kim, Y.J., Ahn, K.U., Park, C.S. and Kim, I.H., Gaussian Emulator for Stochastic Optimal Design of a Double Glazing System, Proceedings of the 13th IBPSA Conference, August 25-28, Chambery, France, p.p.2217-2224, 2013a
35 Hyun, S.H., Park, C.S. and Augenbroe, G., Analysis of Uncertainty in Natural Ventilation Predictions of High-rise Apartment Buildings, Building Services Engineering Research and Technology, 29(4), p.p.311-326, 2008   DOI   ScienceOn
36 ISO 13790, Energy Performance of Buildings-Calculation of Energy Use for Space Heating and Cooling, 2008
37 Kocijan, J., Murray-Smith, R., Rasmussen, C.E. and Likar, B., Predictive Control with Gaussian Process Models, Proceedings of IEEE, Region 8 Eurocon 2003: Computer as a Tool, Piscataway, NJ, USA, September, pp.352-356, 2003
38 Kim, D.W. and Park, C.S., A Heterogeneous System Simulation of a Double Skin Facade, Proceedings of the 12th IBPSA Conference, November 14-16, Sydney, Australia, p.p.601-608, 2011
39 Kim, Y.J., Yoon, S.H. and Park, C.S., Stochastic Comparison between Simplified Energy Calculation and Dynamic Simulation, Energy and Buildings, Vol.64, p.p.332-342, 2013b   DOI
40 Kim, Y.J., Ahn, K.U. and Park, C.S., Decision Making of HVAC System using Bayesian Markov Chain Monte Carlo method, Energy and Buildings, Vol.72, p.p.112-121, 2014   DOI   ScienceOn
41 Kocijan, J. and Murray-Smith, R., Nonlinear Predictive Control with a Gaussian Process Model, Switching and Learning, LNCS 3355, p.p.185-200, 2005
42 Kotek, P., Jordan, F., Kabele, K. and Hensen, J., Technique of Uncertainty and Sensitivity Analysis for Sustainable Building Energy Systems Performance Calculations, Proceedings of the 10th IBPSA Conference, September 3-6, Beijing, China, p.p.629-636, 2007
43 Monfet, D. and Zmeureanu, R., Identification of the Electric Chiller Model for the EnergyPlus Program using Monitored Data in an Existing Cooling Plant, Proceedings of the 12th IBPSA Conference, November 14-16, Sydney, Australia, p.p.530-537, 2011
44 Lee, K.P. and Cheng, T.A., A Simulation-optimization Approach for Energy Efficiency of Chilled Water System, Energy and Buildings, Vol.54, p.p.290-296, 2012   DOI   ScienceOn
45 MacDonald, I.A., Quantifying the Effects of Uncertainty in Building Simulation, Ph.D. thesis, University of Strathclyde, Scotland, 2002
46 ASHRAE, ASHRAE Fundamentals, American Society of Heating, Refrigerating, and Air-Conditioning Engineers, Atlanta, GA, 2013