Support Vector Regression with Multi-Strategy Artificial Bee Colony Algorithm for Annual Electric Load Forecasting

  • Siyang Zhang
  • Fangjun KuangEmail author
  • Rong Hu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 891)


A novel support vector regression (SVR) model with multi-strategy artificial bee colony algorithm (MSABC) is proposed for annual electric load forecasting. In the proposed model, MSABC is employed to optimize the punishment factor, kernel parameter and the tube size of SVR. However, in the MSABC algorithm, Tent chaotic opposition-based learning initialization strategy is employed to diversify the initial individuals, and enhanced local neighborhood search strategy is applied to help the artificial bee colony (ABC) algorithm to escape from a local optimum effectively. By comparison with other forecasting algorithms, the experimental results show that the proposed model performs higher predictive accuracy, faster convergence speed and better generalization.


Support vector regression Annual load forecasting Multi-strategy Artificial bee colony algorithm Parameter optimization 


  1. 1.
    Li, L.H., Mu, C.Y., Ding, S.H., et al.: A robust weighted combination forecasting method based on forecast model filtering and adaptive variable weight determination. Energies 9(1), 20–42 (2016). Scholar
  2. 2.
    Wang, J.J., Li, L., Niu, D.X., et al.: An annual load forecasting model based on support vec-tor regression with differential evolution algorithm. Appl. Energy 94(6), 65–70 (2012)CrossRefGoogle Scholar
  3. 3.
    Chen, T.: A collaborative fuzzy-neural approach for long-term load forecasting in Taiwan. Comput. Ind. Eng. 63(3), 663–670 (2012). Scholar
  4. 4.
    Bozkurt, Ö.Ö., Biricik, G., Tayşi, Z.C.: Artificial neural network and SARIMA based models for power load forecasting in Turkish electricity market. PLoS ONE 12(4), e0175915 (2017). Scholar
  5. 5.
    Zhao, H.R., Zhao, H.R., Guo, S.: Using GM(1,1) optimized by MFO with rolling mechanism to forecast the electricity consumption of inner Mongolia. Appl. Sci. 6(1), 20–38 (2016). Scholar
  6. 6.
    Wu, Q.: Hybrid model based on wavelet support vector machine and modified genetic algorithm penalizing Gaussian noises for power load forecasts. Expert Syst. Appl. 38(1), 379–385 (2011). Scholar
  7. 7.
    Hong, W.C.: Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm. Energy 36(9), 5568–5578 (2011). Scholar
  8. 8.
    Kuang, F.J., Zhang, S.Y., Jin, Z.: A novel SVM by combining kernel principal component analysis and chaotic particle swarm optimization for intrusion detection. Soft. Comput. 9(5), 1187–1199 (2015). Scholar
  9. 9.
    Karaboga, D., Basturk, B.: A comparative study of artificial bee colony algorithm. Appl. Math. & Comput. 214(1), 108–132 (2009). Scholar
  10. 10.
    Kuang, F.J., Zhang, S.Y.: A novel network intrusion detection based on support vector machine and tent chaos artificial bee colony algorithm. J. Netw. Intell. 2(2), 195–204 (2017)Google Scholar
  11. 11.
    China National Bureau of Statistics: China Energy Statistical Yearbook 2011. China Statistics Press, Beijing (2011)Google Scholar
  12. 12.
    Amiri, M., Davande, H., Sadeghian, A., et al.: Feedback associative memory based on a new hybrid model of generalized regression and self-feedback neural networks. Neural Netw. 23(9), 892–904 (2010). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Information EngineeringWenzhou Business CollegeWenzhouChina
  2. 2.Fujian University of TechnologyFuzhouChina

Personalised recommendations