Short-Term Load Forecasting of LSSVM Based on Improved PSO Algorithm

  • Qianhui Gong
  • Wenjun Lu
  • Wenlong Gong
  • Xueting Wang
Part of the Communications in Computer and Information Science book series (CCIS, volume 483)


Based on the empirical, the precision of the forecasting will directly affect the reliability, economy and quality of power supply in power system. An improved particle swarm optimizer (IPSO) is proposed to be used on the least squares support vector machine (LSSVM) algorithm, which optimized the initialization parameters and improved the accuracy of short-term load forecasting. This thesis use the historical data of a certain grid to set up the short-term load forecasting model based on the optimization algorithm. While the data had comprehensive consideration the meteorology, weather, date, type and other factors which influencing the load. Compare with the LSSVM algorithm and the standard PSO-LSSVM, the empirical results show that IPSO-LSSVM model is more applicable in terms of convergence effect, accurate prediction and fast speed. The IPSO not only improves the accuracy of load forecasting, but also prevents LSSVM from great reliance on empirical results and random selection.


load forecasting improved particle swarm optimization least square support vector machine parameter selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Xie, H., Wei, J.-P., Liu, H.-L.: Parameter selection and optimization method of SVM model for Short-term Load Forecasting. Proceedings of the CSEE 26(22), 17–22 (2006)Google Scholar
  2. 2.
    Shevade, S.K., Keerthi, S.S., Bhattacharyy, C., et al.: Improvements to the SMO algorithm for SVM regression. IEEE Trans. on Neural Network 11(5), 1188–1193 (2000)CrossRefGoogle Scholar
  3. 3.
    Chen, S., Zhu, J.-N., Pan, J.: Parameters Optimization of LS-SVM and Its Application. Journal of East China University of Science and Technology (Natural Science Edition) 34(2), 278–282 (2008)Google Scholar
  4. 4.
    Wang, D.-Y., Yang, Z., Yang, G.-Q.: Short-Term Load Forecasting Based on Chaotic Characteristic of Loads and Least Squares Support Vector Machines. Power System Technology 32(7), 66–71 (2008) (in Chinese)Google Scholar
  5. 5.
    Cheng, Y., Han, X.-S., Han, L.: Short-Term Load Forecasting Based on Least Squares Support Vector Machines. Power System Technology 32(18), 72–76 (2008)Google Scholar
  6. 6.
    Tang, J.-N., Liu, J.-Y., Yang, K., et al.: Short-Term Load Combination Forecasting by Grey Model and Least Square Support Vector Machine. Power System Technology 33(3), 63–68 (2009)Google Scholar
  7. 7.
    Li, Y., Fang, T., Zhen, G.: Wavelet support vector machines for short-term load forecasting. Journal of university ofscience and technology of China 33(6), 726–732 (2003) (in Chinese)Google Scholar
  8. 8.
    Cherkassky, V., Ma, Y.: Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks 17(1), 113–126 (2004)CrossRefzbMATHGoogle Scholar
  9. 9.
    Sun, B., Yao, H.-T.: The short-term wind speed forecast analysis based on the PSO-LSSVM predict model. Power System and Control 40(5), 85–89 (2012), (in Chinese)Google Scholar
  10. 10.
    Chen, Z.-M.: Improved PSO and its application to SVM parameter optimization. Computer Engineering and Applications 47(10), 38–40 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Qianhui Gong
    • 1
  • Wenjun Lu
    • 1
  • Wenlong Gong
    • 2
  • Xueting Wang
    • 1
  1. 1.College of Electrical and Information EngineeringHunan UniversityChangshaChina
  2. 2.State Grid Chongqing Electric Power CO. Yongchuan Power Supply CompanyChongqingChina

Personalised recommendations