Browse > Article
http://dx.doi.org/10.6110/KJACR.2016.28.9.355

LS-SVM Based Modeling of Winter Time Apartment Hot Water Supply Load in District Heating System  

Park, Young Chil (Department of Electrical & Information Engineering, Seoul National University of Science and Technology)
Publication Information
Korean Journal of Air-Conditioning and Refrigeration Engineering / v.28, no.9, 2016 , pp. 355-360 More about this Journal
Abstract
Continuing to the modeling of heating load, this paper, as the second part of consecutive works, presents LS-SVM (least square support vector machine) based model of winter time apartment hot water supply load in a district heating system, so as to be used in prediction of heating energy usage. Similar, but more severely, to heating load, hot water supply load varies in highly nonlinear manner. Such nonlinearity makes analytical model of it hardly exist in the literatures. LS-SVM is known as a good modeling tool for the system, especially for the nonlinear system depended by many independent factors. We collect 26,208 data of hot water supply load over a 13-week period in winter time, from 12 heat exchangers in seven different apartments. Then part of the collected data were used to construct LS-SVM based model and the rest of those were used to test the formed model accuracy. In modeling, we first constructed the model of district heating system's hot water supply load, using the unit heating area's hot water supply load of seven apartments. Such model will be used to estimate the total hot water supply load of which the district heating system needs to provide. Then the individual apartment hot water supply load model is also formed, which can be used to predict and to control the energy consumption of the individual apartment. The results obtained show that the total hot water supply load, which will be provided by the district heating system in winter time, can be predicted within 10% in MAPE (mean absolute percentage error). Also the individual apartment models can predict the individual apartment energy consumption for hot water supply load within 10% ~ 20% in MAPE.
Keywords
District heating system; Hot water supply load model; Prediction of hot water supply load; LS-SVM;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Park, Y. C., 2015, Modeling of winter time apartment heating load in district heating system using reduced LS-SVM, Korean Journal of Air-Conditioning and Refrigeration Engineering, Vol. 27, No. 6, pp. 283-292.   DOI
2 Werner, S. E., 1984, The heat load in district heating systems, Ph.D. Thesis, Chalmers University of Technology, Sweden.
3 Heller, A. J., 2002, Heat load modeling for large systems, Applied Energy, Vol. 72, No. 1, pp. 371-387.   DOI
4 Koive, T. A. and Toode, A., 2006, Trends in domestic hot water consumption in Estonian apartment building, Proc. Estonian Academy of Science Engineering, Vol. 12, No. 1, pp. 72-80.
5 Evarts, J. C. and Swan, L. G., 2013, Domestic hot water consumption estimates for solar heating thermal sizing, Energy and Buildings, Vol. 58, pp. 58-65.   DOI
6 Suykens, J. A. K., 2002, Least square support vector machine, Singapore, World Science Pub.
7 Suykens et al., 2002, Weighted least squares support vector machines : robustness and space approximation, Neurocomputing, Vol. 48, No. 1-4, pp. 85-105.   DOI
8 Gavin et al., 2002, Improved sparse least squares support vector machines, Neurocomputing, Vol. 48, No. 1-4, pp. 1025-1031.   DOI
9 Vapnik, V., 1995, The Nature of Statistical Learning Theory, Springer.
10 Baudat, G. and Anouar, F., 2003, Feature vector selection and projection using kernels, Neurocomputing, Vol. 55, No. 1-2, pp. 21-38.   DOI
11 An, S., Liu, W., and Venkatesh, S., 2007, Fast cross validation algorithms for least squares support vector machines and kernel ridge regression, Pattern Recognition, Vol. 40, No. 8, pp. 2154-2162.   DOI