Offshore Wind Speed Load Predicting Based on GA-SVM

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 218)


The accurate measurement of the effective wind speed is the basis of the wind generation system operation. The effective wind speed cannot be directly measured accurately. Because offshore wind farm is a three-dimensional time-varying environment, the wind speed distribution is different on the plane of blade rotation in the wind generation system. This paper uses support vector machine with genetic algorithm (GA-SVM) to estimate the effective wind speed. The simulation results show that this model has high prediction accuracy, which the mean error of the training data can reach 0.5689 m/s. This model can improve the control capability of the wind generation system, when the wind speed changes in a wide range.


Wind generation system Effective wind speed Support vector machine Genetic algorithm 



This paper was supported by Shandong Science and Technology Fund (2011GGH20411) and Shandong Excellent Young Scientist Research Award Fund (BS2010NJ001).


  1. 1.
    Lin Y, Zhang P, Fang M (2010) Research on construction system of large scale non-grid connected wind power offshore wind farms. In: Worle non-grid-connected wind power and energy conference, vol 26(2) pp 1–5Google Scholar
  2. 2.
    Cheng QM, Cheng YM, Wang MM, Wang YF (2010) Development of wind speed measuring technologies in wind power generation. Process Autom Instrum 31(7):1–4Google Scholar
  3. 3.
    Simoes MG, Bose BK, Spiegel RJ (1997) Fuzzy logic based intelligent control of a variable speed cage machine wind generation system. Power Electron 12(1):87–95Google Scholar
  4. 4.
    Ren YF, Mao KF, Bao GQ (2009) Research on control strategy of maximum wind energy capture of direct-drive wind turbine generator based on neural-network. Electron automat 31(6):42–45Google Scholar
  5. 5.
    Wang XS, Wu YX, He C (2010) Simulation of wind speed estimation for MPPT control. Electron Mach Control 14(2):20–24Google Scholar
  6. 6.
    Lin KP, Chen MS (2011) On the design and analysis of the privacy-presercing SVM Classifier. Knowl Data Eng 23(11):1704–1708CrossRefGoogle Scholar
  7. 7.
    Yao XJ, Liu YM, Bao JQ, Zing ZX (2008) Research and simulation of direct drive wind turbine VSCF characteristic. Int Conf Autom Logist (ICAL) 9(8):1683–1687Google Scholar
  8. 8.
    Feng R, Shen W, Shao HH (2003) A soft sensor modeling approach using support vector machines. Ame Control Conf 5(37):2–7Google Scholar
  9. 9.
    Li H, Zhang YX (2009) An algorithm of soft fault diagnosis for analog circuit based on the optimized SVM by GA. Electro Meas Instr (ICEMI) 9(6):16–19Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.Department of Electrical EngineeringHarbin Institute of TechnologyWeihaiChina

Personalised recommendations