Journal of the Architectural Institute of Korea Structure & Construction (대한건축학회논문집:구조계)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning Models for Prediction and Control of an Ice Thermal Storage System in an Existing Building

빙축열 시스템의 익일 방냉량 예측 기계학습 모델 및 제어

  • Received : 2017.07.05
  • Accepted : 2017.09.28
  • Published : 2017.11.30
⟨ Previous Next ⟩

Abstract

In South Korea, an ice thermal storage system is popular because night-time electricity rate is cheaper than daytime rate. A spherical ice ball system is one of the most popular ice thermal storage systems used in Korea. However, it is difficult to estimate the degree of freezing and defrosting of the spherical ice ball system and thus, excessive icing commonly occurs in order to prevent any shortage of stored ice. If this rule-of thumb control can be replaced by a simulation model-based control, there would be significant potential for energy savings. In this study, the authors developed 25 machine learning simulation models for the spherical ice thermal storage system installed in a 30-story office building (gross floor area: $32,600m^2$) located in Seoul, Korea. Five different machine learning algorithms (Artificial Neural Network, Support Vector Machine, Gaussian Process, Random Forest, and Genetic Programming) were used for five different input scenarios, respectively. The 25 machine learning models are accurate enough to predict the amount of icing required for the following daytime. In addition, with the use of Model Predictive Control (MPC), 16.8% of excessive icing during overnight can be reduced and 15% of cooling energy (chiller, cooling tower, Brine pump, etc.) can be saved.

Keywords

Acknowledgement

Supported by : 한국에너지기술평가원(KETEP)

References

  1. Ahn, K. U., Kim, D. W., Kim, Y. J., Park, C. S., & Kim, I. H. (2015). Gaussian Process Model for Control of an Existing Building. Energy Procedia, 78, 2136-2141. https://doi.org/10.1016/j.egypro.2015.11.295
  2. Ahn, K. U., Kim, D. W., Kim, Y. J., Yoon, S. H., & Park, C. S. (2016). Issues to Be Solved for Energy Simulation of An Existing Office Building. Sustainability, 8(4), 345. https://doi.org/10.3390/su8040345
  3. Akaike, H. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19(6), 716-723. https://doi.org/10.1109/TAC.1974.1100705
  4. Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  5. Braun, J. E. (2007). A Near-Optimal Control Strategy for Cool Storage Systems with Dynamic Electric Rates. HVAC&R Research, 13(4), 557-580. https://doi.org/10.1080/10789669.2007.10390972
  6. Chen, H. J., Wang, D. W. P., & Chen, S. L. (2005). Optimization of an ice-storage air conditioning system using dynamic programming method. Applied Thermal Engineering, 25(2), 461-472. https://doi.org/10.1016/j.applthermaleng.2003.12.006
  7. D'Oca, S., & Hong, T. (2015). Occupancy schedules learning process through a data mining framework. Energy and Buildings, 88, 395-408. https://doi.org/10.1016/j.enbuild.2014.11.065
  8. Drucker, H., Burges, C. J. C., Kaufman, L., Smola, A., & Vapnik, V. (1997). Support vector regression machines. Advances in neural information processing systems, 9, 155-161.
  9. Eames, I. W., & Adref, K. T. (2002). Freezing and melting of water in spherical enclosures of the type used in thermal (ice) storage systems. Applied thermal engineering, 22(7), 733-745. https://doi.org/10.1016/S1359-4311(02)00026-1
  10. Foresee, F. D., & Hagan, M. T. (1997). Gauss-Newton approximation to Bayesian learning, Proceedings of the International Conference on Neural Networks, 1930-1935.
  11. Hajiah, A., & Krarti, M. (2012). Optimal control of building storage systems using both ice storage and thermal mass - Part I: Simulation environment. Energy Conversion and Management, 64, 499-508. https://doi.org/10.1016/j.enconman.2012.02.016
  12. Henze, G. P., Dodier, R. H., & Krarti, M. (1997). Development of a predictive optimal controller for thermal energy storage systems. HVAC&R Research, 3(3), 233-264. https://doi.org/10.1080/10789669.1997.10391376
  13. Henze, G. P., Krarti, M., & Brandemuehl, M. J. (2003). Guidelines for improved performance of ice storage systems. Energy and Buildings, 35(2), 111-127. https://doi.org/10.1016/S0378-7788(01)00140-2
  14. Henze, G. P., & Schoenmann, J. (2003). Evaluation of reinforcement learning control for thermal energy storage systems. HVAC&R Research, 9(3), 259-275. https://doi.org/10.1080/10789669.2003.10391069
  15. Kim, Y. J. (2016). Comparative study of surrogate models for uncertainty quantification of building energy model: Gaussian Process Emulator vs. Polynomial Chaos Expansion. Energy and Buildings, 133, 46-58. https://doi.org/10.1016/j.enbuild.2016.09.032
  16. Kim, Y. J., & Park, C. S. (2014). Nonlinear Predictive Control of Chiller System using Gaussian Process Model. Paper presented at the Proceedings of the 2nd Asia Conference of International Building Performance Simulation Association, Nagoya, Japan.
  17. Kim, Y. J., & Park, C. S. (2016). Stepwise deterministic and stochastic calibration of an energy simulation model for an existing building. Energy and Buildings, 133, 455-468. https://doi.org/10.1016/j.enbuild.2016.10.009
  18. KMA, Korea Meteorological Administration. (2017). Dong-Nae Forecast (Digital Forecast), Retrieved from http://www.kma.go.kr/weather/forecast/timeseries.jsp
  19. Lee, K. H., Choi, B. Y., Joo, Y. J., Lee, S. R., & Han, S. H. (2000). Optimal Scheduling of Ice Storage System with Prediction of Cooling Loads. Korean Journal of Air-Conditioning and Refrigeration Engineering, 12(11), 982-994.
  20. Louppe, G. (2014). Understanding random forests: From theory to practice, Doctoral dissertation, University of Liege, Liege, Belgium.
  21. MacKay, D. J. C. (1992). Bayesian interpolation. Neural computation, 4(3), 415-447. https://doi.org/10.1162/neco.1992.4.3.415
  22. Ra, S. J., Shin, H. S., Suh, W. J., Chu, H. G., & Park, C. S. (2017). Five machine learning models for HVAC system in an existing office building. Journal of the Architectural Institute of Korea Structure & Construction (under review).
  23. Ramsey, F., & Schafer, D. (2012). The Statistical Sleuth: A Course in Methods of Data Analysis. Boston, MA: Cengage Learning.
  24. Shin, H. S., & Park, C. S. (2017). Development of a Machine Learning Model for a Chiller using Random Forest Algorithm and Data Pre-processing. Journal of the Architectural Institute of Korea Structure & Construction, (accepted).
  25. Suh, W. J., & Park, C. S. (2012). Issues and Limitations on the Use of a Whole Building Simulation Tool for Energy Diagnosis of a Real-life Building. Journal of the Architectural Institute of Korea Planning & Design, 28(1), 273-283. https://doi.org/10.5659/JAIK_PD.2012.28.1.273
  26. Suh, W. J., & Park, C. S. (2016). Room air Temperature Prediction Model using Genetic Programming and BEMS Data. Journal of the Architectural Institute of Korea Planning & Design, 32(6), 105-112. https://doi.org/10.5659/JAIK_PD.2016.32.6.105
  27. Sun, K., Yan, D., Hong, T., & Guo, S. (2014). Stochastic modeling of overtime occupancy and its application in building energy simulation and calibration. Building and Environment, 79, 1-12.
  28. Suykens, J. A. K., & Vandewalle, J. (1999). Least squares support vector machine classifiers. Neural processing letters, 9(3), 293-300. https://doi.org/10.1023/A:1018628609742
  29. Thiem, S., Born, A., Danov, V., Vandersickel, A., Schäfer, J., & Hamacher, T. (2017). Automated identification of a complex storage model and hardware implementation of a model-predictive controller for a cooling system with ice storage. Applied Thermal Engineering, 121, 922-940. https://doi.org/10.1016/j.applthermaleng.2017.04.149
  30. Vetterli, J. & Benz, M. (2012). Cost-optimal design of an ice-storage cooling system using mixed-integer linear programming techniques under various electricity tariff schemes. Energy and Buildings, 49, 226-234. https://doi.org/10.1016/j.enbuild.2012.02.012
  31. Wang, H., & Hu, D. (2005). Comparison of SVM and LS-SVM for regression, Proceedings of the International Conference on Neural Networks and Brain, 1, 279-283.
  32. Winkler, S., Efendic, H., Del Re, L., Affenzeller, M., & Wagner, S. (2007). Online modelling based on Genetic Programming. International journal of intelligent systems technologies and applications, 2(2-3), 255-270. https://doi.org/10.1504/IJISTA.2007.012487
  33. Yang, Z., & Becerik-Gerber, B. (2014). The coupled effects of personalized occupancy profile based HVAC schedules and room reassignment on building energy use. Energy and Buildings, 78, 113-122. https://doi.org/10.1016/j.enbuild.2014.04.002
  34. Yu, Z., Huang, G., Haghighat, F., Li, H., & Zhang, G. (2015). Control strategies for integration of thermal energy storage into buildings: State-of-the-art review. Energy and Buildings, 106, 203-215. https://doi.org/10.1016/j.enbuild.2015.05.038