Multimedia Tools and Applications

, Volume 71, Issue 1, pp 293–307 | Cite as

Real-time cooling load forecasting using a hierarchical multi-class SVDD

  • Jaehak Yu
  • Byung-Bok Lee
  • DaeHeon ParkEmail author


In this paper, we propose a real-time cooling load forecasting system in order to overcome the problems of the conventional methods. The proposed system is a new load forecasting model that hierarchically combines Support Vector Data Descriptions (SVDDs). The proposed system selects an optimal attribute subset by our cooling load forecasting system that enables real-time load data generation and collection. The system is composed of two layers: The first layer predicts the time slots in three representative forms: morning, midday and afternoon. The second layer performs specialized prediction of each individual time slot. Since the proposed system enables both coarse-and fine-grained forecasting, it can efficient cooling load management. Moreover, even when a new time slot emerges, it can be easily adapted for incremental updating and scaling. The performance of the proposed system is validated via experiments which confirm that the recall and precision measures of the method are satisfactory.


Cooling load forecasting Real-time prediction Support vector machine Support vector data description 



This work was Development of Smart Plant Safety Framework based on Reliable-Secure USN(10035310-2010-35), Development of the Integrated Environment Control S/W Platform for Constructing an Urbanized Vertical Farm(10040125-2011-199) funded by the Ministry of Knowledge Economy, and Development of USN/WoT Convergence Platform for Internet of Reality Service Provision(13ZC1130).


  1. 1.
    Cover, T., Thomas, J.: Elements of information theory. WILEY, (1991)Google Scholar
  2. 2.
    Dong B, Cao C, Lee S (2005) Applying support vector machines to predict building energy consumption in tropical region. J Energy and Buildings 37(5):545–553CrossRefGoogle Scholar
  3. 3.
    Erman, J., Mahanti, A., Arlitt, M.: Internet traffic identification using machine learning. In: 2006 IEEE Global Telecommunications Conference, pp. 1--6 (2006)Google Scholar
  4. 4.
    Fleuret F (2004) Fast binary feature selection with conditional mutual information. J Machine Learning Research 5:1531–1555zbMATHMathSciNetGoogle Scholar
  5. 5.
    Haida T, Muto S (1994) Regression based peak load forecasting using a transformation technique. J IEEE Trans on Power Systems 9(4):1788–1794CrossRefGoogle Scholar
  6. 6.
    Hall, M.: Correlation-based feature selection for machine learning. In: PhD Diss., Department of Computer Science. Waikato University, Hamilton, NZ (1998)Google Scholar
  7. 7.
    Han, J., Kamber, M.: Data mining: concept and techniques, Morgan Kaufmann Publishers, 2nd Ed., (2007)Google Scholar
  8. 8.
    Lee, H., Song, J., Park, D.: Intrusion detection system based on multi-class SVM. In: Lecture Notes in Artificial Intelligence, pp. 511--519 (2005)Google Scholar
  9. 9.
    Leung M, Norman C, Lai L, Chow T (2012) The use of occupancy space electrical power demand in building cooling load prediction. J of Energy and Buildings 55:151–163CrossRefGoogle Scholar
  10. 10.
    Li, X., Ding, L., Li, L.: A novel building cooling load prediction based on SVR and SAPSO. In: 2010 International Symposium on Computer Communication Control and Automation, pp. 528--532 (2010)Google Scholar
  11. 11.
    Li Q, Meng Q, Cai J, Yoshino H, Mochida A (2009) Applying support vector machine to predict hourly cooling load in the building. J Applied Energy 86(10):2249–2256CrossRefGoogle Scholar
  12. 12.
    Machine Learning Lab in The University of Waikato, http://www.cs.waikato.
  13. 13.
    Ok V (1992) A procedure for calculating cooling load due to solar radiation: the shading effects from adjacent or nearby buildings. J Energy and buildings 19(1):11–20CrossRefGoogle Scholar
  14. 14.
    Rodgers J, Nicewander W (1988) Thirteen ways to look at the correlation coefficient. The American Statistician 42(1):59–66CrossRefGoogle Scholar
  15. 15.
    Senjyu T, Takara H, Uezato K, Funabashi T (2002) One-hour-ahead load forecasting using neural network. J IEEE Trans on Power Systems 17(1):113–118CrossRefGoogle Scholar
  16. 16.
    Seok I, Lee J, Moon B (2006) Hybrid genetic algorithms for feature selection. J IEEE Transactions on Pattern Analysis and Machine Intelligence 26(11):1424–1437Google Scholar
  17. 17.
    Sharifi M, Okhovvat M (2012) Scate: A scalable time and energy aware actor task allocation algorithm in wireless sensor and actor networks. ETRI Journal 34(3):330–340CrossRefGoogle Scholar
  18. 18.
    Song K, Baek Y, Hong D, Jang G (2005) Short-term load forecasting for the holidays using fuzzy linear regression method. J IEEE Trans on Power Systems 20(1):96–101CrossRefGoogle Scholar
  19. 19.
    Sun, Y., Li, J.: Iterative RELIEF for feature weighting. In: Proceedings of the 23rd International Conference on Machine Learning, pp.913--920 (2006)Google Scholar
  20. 20.
    Suykens J, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Processing Letters 9(3):293–300CrossRefMathSciNetGoogle Scholar
  21. 21.
    Vapnik V (1995) The nature of statistical learning theory. Springer-Verlag, New YorkCrossRefzbMATHGoogle Scholar
  22. 22.
    Vapnik V (1998) Statistical learning theory. John Wiley, New YorkzbMATHGoogle Scholar
  23. 23.
    Xuemei, L., Jin-hu, L., Lixing, D., Gang, X., Jibin, L.: Building cooling load forecasting model based on LS-SVM. In: 2009 Asia-Pacific Conference on Information Processing, pp. 55--58 (2009)Google Scholar
  24. 24.
    Xunsheng, J.: Monthly power load predicting by WT and LS-SVM. In: 2011 Third International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), pp. 640--643 (2011)Google Scholar
  25. 25.
    Yao Y, Lian Z, Liu S, Hou Z (2004) Hourly cooling load prediction by a combined forecasting model based on analytic hierarchy process. J Thermal Sciences 43(11):1107–1118CrossRefGoogle Scholar
  26. 26.
    Yu J, Lee H, Im Y, Kim M, Park D (2010) Real-time classification of internet application traffic using a hierarchical multi-class SVM. J KSII Transactions on Internet and Information Systems 3(5):859–876Google Scholar
  27. 27.
    Yu J, Lee H, Kim M, Park D (2008) Traffic flooding attack detection with SNMP MIB using SVM. J Computer Communications 31:4212–4219CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Electronics and Telecommunications Research InstituteDaejeonKorea

Personalised recommendations