Windspeed prediction method based on SVR and multi-parameter optimization of GA

被引：0
作者：
Zhu X.-X. [1 ]
Xu B.-C. [1 ]
Jiao H.-C. [1 ]
Han Z.-H. [1 ]
机构：
[1] Department of Power Engineering, North China Electric Power University, Baoding
来源：
Xu, Bo-Chao | 1600年 / Editorial Department of Electric Machines and Control卷 / 21期
关键词：
Genetic algorithms; Multiobjective optimization; Space reconstruction; Support vector machines; Wind speed prediction;
D O I：
10.15938/j.emc.2017.02.009
中图分类号：
学科分类号：
摘要：
Phase space reconstruction was used to apply in the prediction of wind speed time series for characteristic factors extraction. After several experiments, embedding dimension E and time delay τ, which were typical parameters of phase space reconstruction, might not be the optimum values for support vector regression model. For solving this problem, a multi-parameter optimization method based on genetic algorithm was proposed to optimize embedding dimension E, time delay τ and other support vector regression model parameters (penalty parameter C, kernel function parameter γ) synchronously. Two groups of wind speed time series were predicted by using this method and the prediction errors are 6.56% and 7.74%. The errors of the contrast method (optimize C, γ only) are 12.00% and 9.30%. The results show that the optimal selection of E, τ, C, γ is necessary. Compared with the contrast model, this method can greatly improve the prediction accuracy. © 2017, Harbin University of Science and Technology Publication. All right reserved.
引用
收藏
页码：70 / 75
页数：5
相关论文
共 15 条
  • [1] Wang X., Wu Y., He C., Simulation of wind speed estimation for MPPT control, Electric Machines and Contorl, 14, 2, pp. 20-24, (2010)
  • [2] Li H., Ceng Y., Li Y., Et al., Impact of DFIG-based wind farms interconnected to power grid on subsynchronous oscillation of turbogenerator, Electric Machines and Contorl, 19, 6, pp. 47-54, (2015)
  • [3] Li J., Li S., Kuang H., Small signal stability analysis of doubly-fed wind power system participated in frequency regulation, Electric Machines and Contorl, 16, 8, pp. 1-10, (2012)
  • [4] Wu Z., Ma B., Zhunag S., Research on terminal sliding mode control for double-fed wind power system, Electric Machines and Contorl, 16, 8, pp. 94-100, (2012)
  • [5] Shi Z., Song Q., Ma M., Fault diagnosis of steam turbine based on MPSO-SVM algorithm, Journal of Chinese Society of Power Engineering, 32, 6, (2012)
  • [6] Tang C., Cao L., Et al., SVR optimized by DE optimization algorithm for remaining capacity forecasting, Journal of Chongqing University of Technology (Natural Soience), 25, 3, pp. 92-96, (2011)
  • [7] Han Z., Xu W., The wind speed forecast of support vector machine based onchaotic phase-space reconstruction, Renewable Energy Resources, 30, 6, pp. 31-34, (2012)
  • [8] Lu T., Tang W., Suo L., Prediction of short-term wind speed in wind farm based on chaotic phase space reconstruction theory, Power System Protection and Control, 38, 21, pp. 113-117, (2010)
  • [9] Xu Y., Yong G., Liu H., GA optimization method based on Gauss kernel function parameters, Electric Power Automation Equipment, 28, 6, pp. 52-54, (2008)
  • [10] Takens F., Determing strang attractors in turbulence, Lecture notes in Math, 898, pp. 361-381, (1981)
12