Combined General Vector Machine for Single Point Electricity Load Forecast

  • Binbin Yong
  • Yongqiang Wei
  • Jun Shen
  • Fucun Li
  • Xuetao Jiang
  • Qingguo ZhouEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 551)


General Vector Machine (GVM) is a newly proposed machine learning model, which is applicable to small samples forecast scenarios. In this paper, the GVM is applied into electricity load forecast based on single point modeling method. Meanwhile, traditional time series forecast models, including back propagation neural network (BPNN), Support Vector Machine (SVM) and Autoregressive Integrated Moving Average Model (ARIMA), are also experimented for single point electricity load forecast. Further, the combined model based on GVM, BPNN, SVM and ARIMA are proposed and verified. Results show that GVM performs better than these traditional models, and the combined model outperforms any other single models for single point electricity load forecast.


General Vector Machine Electricity load forecast Time series forecast Combined model 



This work was partially supported by National Natural Science Foundation of China under Grant No. 61402210, The Fundamental Research Funds for the Central Universities under Grant No. lzujbky-2018-k12, Ministry of Education - China Mobile Research Foundation under Grant No. MCM20170206, Major National Project of High Resolution Earth Observation System under Grant No. 30-Y20A34-9010-15/17, State Grid Corporation Science and Technology Project under Grant No. SGGSKY00FJJS1700302, No. 52272218002K and No. SGGSKY00FJJS1800403, Program for New Century Excellent Talents in University under Grant No. NCET-12-0250, and Strategic Priority Research Program of the Chinese Academy of Sciences with Grant No. XDA03030100.


  1. 1.
    Laouafi, A., Mordjaoui, M., Dib, D.: One-hour ahead electric load and wind-solar power generation forecasting using artificial neural network. Renew. Energy Congr. 1–6 (2015)Google Scholar
  2. 2.
    Hawkins, D.M.: The problem of overfitting. Cheminform 35(19), 1 (2004)CrossRefGoogle Scholar
  3. 3.
    Gao, Y., Kong, X., Hu, C., Zhang, Z., Li, H., Hou, L.: Multivariate data modeling using modified kernel partial least squares. Chem. Eng. Res. Des. 94, 466–474 (2015)CrossRefGoogle Scholar
  4. 4.
    Cortes, C., Vapnik, V.: Support-Vector Networks. Kluwer Academic Publishers, Dordrecht (1995)CrossRefGoogle Scholar
  5. 5.
    Sch, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: International Conference on Pattern Recognition, vol. 3, pp. 32–36 (2004)Google Scholar
  6. 6.
    Cao, L.J., Tay, F.E.H.: Support vector machine with adaptive parameters in financial time series forecasting. IEEE Trans. Neural Netw. 14(6), 1506–1518 (2004)CrossRefGoogle Scholar
  7. 7.
    Hinton, G.E., Osindero, S., Teh, Y.W.: A Fast Learning Algorithm for Deep Belief Nets. MIT Press, Cambridge (2006)CrossRefGoogle Scholar
  8. 8.
    Ren, J.: Ann vs. SVM: which one performs better in classification of MCCs in mammogram imaging. Knowl.-Based Syst. 26, 144–153 (2012)CrossRefGoogle Scholar
  9. 9.
    Ahmad, A.S., Hassan, M.Y., Abdullah, M.P., Rahman, H.A., Hussin, F., Abdullah, H., Saidur, R.: A review on applications of ann and SVM for building electrical energy consumption forecasting. Renew. Sustain. Energy Rev. 33(2), 102–109 (2014)CrossRefGoogle Scholar
  10. 10.
    Zhao, H.: General vector machine, arXiv preprint (2016)Google Scholar
  11. 11.
    Yong, B., Li, F., Lv, Q., Shen, J., Zhou, Q.: Derivative-based acceleration of general vector machine. Soft. Comput. 23(3), 987–995 (2019)CrossRefGoogle Scholar
  12. 12.
    Yong, B., Xu, Z., Shen, J., Chen, H., Tian, Y., Zhou, Q.: Neural network model with Monte Carlo algorithm for electricity demand forecasting in Queensland, vol. 47, pp. 1–7 (2017)Google Scholar
  13. 13.
    Yong, B., Shen, J., Shen, Z., Chen, H., Wang, X., Zhou, Q.: GVM based intuitive simulation web application for collision detection. Neurocomputing 279(2), 63–73 (2017)Google Scholar
  14. 14.
    Yong, B., Huang, L., Li, F., Shen, J., Wang, X., Zhou, Q.: A research of Monte Carlo optimized neural network for electricity load forecast. J. Supercomput. 1–14 (2019)Google Scholar
  15. 15.
    Yang, C., Deconinck, G., Gui, W.: An optimal power-dispatching control system for the electrochemical process of zinc based on backpropagation and hopfield neural networks. IEEE Trans. Ind. Electron. 50(5), 953–961 (2003)CrossRefGoogle Scholar
  16. 16.
    Suganyadevi, M.V., Babulal, C.K.: Support vector regression model for the prediction of loadability margin of a power system. Appl. Soft Comput. J. 24, 304–315 (2014)CrossRefGoogle Scholar
  17. 17.
    Selakov, A., Mellon, S., Bekut, D.: Hybrid PSO-SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank. Appl. Soft Comput. 16(3), 80–88 (2014)CrossRefGoogle Scholar
  18. 18.
    Zahedi, G., Azizi, S., Bahadori, A., Elkamel, A., Alwi, S.R.W.: Electricity demand estimation using an adaptive neuro-fuzzy network: a case study from the Ontario Province - Canada. Energy 49(1), 323–328 (2013)CrossRefGoogle Scholar
  19. 19.
    Morris, P., Vine, D., Buys, L.: Application of a Bayesian network complex system model to asuccessful community electricity demand reduction program. Energy 84, 63–74 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Binbin Yong
    • 1
    • 2
  • Yongqiang Wei
    • 1
  • Jun Shen
    • 3
    • 4
  • Fucun Li
    • 3
  • Xuetao Jiang
    • 1
  • Qingguo Zhou
    • 1
    Email author
  1. 1.School of Information Science and EngineeringLanzhou UniversityLanzhouChina
  2. 2.School of Physical Science and TechnologyLanzhou UniversityLanzhouChina
  3. 3.School of Information Systems and TechnologyUniversity of WollongongWollongongAustralia
  4. 4.Department of EE and CS, Research Lab of ElectronicsMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations