The Research of Building Indoor Temperature Prediction Based on Support Vector Machine

  • Wenbiao Wang
  • Qi CaiEmail author
  • Siyuan Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8866)


Aiming at the problems for predicting the building indoor temperature so as to set up a reasonable indoor environment, four building indoor temperature prediction models were established in this paper. The theory of Support Vector Machine (SVM) and the LibSVM toolbox were used to predict the indoor temperature. The experimental results shown that the prediction effect of the model which the input are the outdoor temperature, the solar radiation, the wind speed and the time series, the output is the indoor temperature is the best. It’s really effective to use the support vector regression (SVR) model to predict the building indoor temperature. This predicting method based on SVM can be promoted and applied in the field of prediction.


Building indoor temperature Time series prediction SVM Kernel function LibSVM toolbox 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Li, J.H., Luo, X., Huang, C., Song, Y.: Block Model and Numerical Simulation for Predicting Indoor Temperature Distributions. Journal of Engineering Thermophysics 28(2), 124–126 (2007)zbMATHGoogle Scholar
  2. 2.
    Ji, X.L., Li, G.Z., Dai, Z.Z.: Influencing Factors and The Research Progress on Forecasting and Evaluating Indoor Thermal Comfort. Journal of Hygiene Research 32(3), 295–299 (2003)Google Scholar
  3. 3.
    Sun, B., Yao, H.T.: The Short-term Wind Speed Forecast Analysis Based on The PSO-LSSVM Predict Model. Journal of Power System Protection and Control 40(5), 85–89 (2012)Google Scholar
  4. 4.
    Yang, J.F., Cheng, H.Z.: Application of SVM to Power System Short-term Load Forecast. Journal of Electric Power Automation Equipment 24(2), 30–32 (2004)Google Scholar
  5. 5.
    Wang, H.Q., Lei, G.: A Method for Forecasting Wind Speed by LIBSVM. Journal of Science Technology and Engineering 11(22), 5440–5442 (2011)Google Scholar
  6. 6.
    Tang, W.H., Li, W.F.: Application of Support Vector Machines Based on Time Sequence in Logistics Forecasting. Journal of Logistics Science Technology 28(113), 8–11 (2004)Google Scholar
  7. 7.
    Zhang, Q., Yang, Y.Q.: Research on The Kernel Function of SVM. Journal of Electric Power Science and Engineering 28(5), 42–45 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.School of Information Science and TechnologyDalian Maritime UniversityDalianChina

Personalised recommendations