Combined interpolation model for wind speed measurement missing of wind farm

被引：0

作者：

Du, Jie ^{[1
,2
]}

Peng, Lixia ^{[3
]}

Liu, Yubao ^{[4
]}

Pan, Linlin ^{[4
]}

Wang, Lei ^{[5
]}

Cao, Yijia ^{[6
]}

机构：

[1] School of Computer & Software, Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing

[2] MOE Internet Innovation Platform, Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science & Technology, Nanjing

[3] College of Atmospheric Science, Nanjing University of Information Science & Technology, Nanjing

[4] National Center for Atmospheric Research, Boulder

[5] NARI Technology Co., Ltd., Nanjing

[6] College of Electrical and Information Engineering, Hunan University, Changsha

来源：

Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2015年 / 35卷 / 09期

基金：

中国国家自然科学基金;

关键词：

Combined interpolation; Measurements; Missing value; Wavelet neural network; Wind farms; Wind speed;

D O I：

10.16081/j.issn.1006-6047.2015.09.020

中图分类号：

学科分类号：

摘要：

Aiming at the simultaneous wind speed measurements missing of multiple adjacent wind turbines in wind farm, a combined interpolation algorithm based on wavelet neural network is proposed. Spatial nearest neighbour method, PCC (Pearson Correlation Coefficients) method and DTW (Dynamic Time Warping) method are adopted respectively to analyze the similarity of wind speed measurement between every two wind turbines. The wind speed measurements of several wind turbines with higher similarity are then extracted to build the wavelet neural network for the interpolation method research of the single model. The combined interpolation model based on entropy weight is proposed. Experimental results show that, DTW method is superior to PCC method in the nonlinear similarity analysis of wind speed, the neural network based on the wind speed similarity improves the performance and generalization ability of model, the accuracy and stability of the combined model are better than the single model, and the simulative experiment for each wind turbine of the wind farm improves the model universality. ©, 2015, Electric Power Automation Equipment Press. All right reserved.

引用

页码：125 / 129

页数：4

共 15 条

[1]

Cutler N.J., Outhred H.R., Macgill I.F., Using nacelle-based wind speed observations to improve power curve modeling for wind power forecasting, Wind Energy, 15, 2, pp. 245-258, (2012)

[2]

Cui M., Sun Y., Ke D., Et al., Short-term wind power forecasting based on atomic sparse decomposition theory, Electric Power Automation Equipment, 34, 1, pp. 120-127, (2014)

[3]

Zhang L., Lu J., Mei Y., Et al., Wind power forecasting based on different optimization criterions, Electric Power Automation Equipment, 35, 5, pp. 139-145, (2015)

[4]

Liu Y.B., Warner T., Liu Y.W., Et al., Simultaneous nested modeling from the synoptic scale to the LES scale for wind energy applications, Journal of Wind Engineering and Industrial Aerodynamics, 99, 4, pp. 308-319, (2011)

[5]

Hocaogglu F.O., Kurban M., The effect of missing wind speed data on wind power estimation, Intelligent Data Engineering and Automated Learning-IDEAL 2007, (2007)

[6]

Lin Q., Wang J., Vertically correlated echelon model for the interpolation of missing wind speed data, IEEE Transactions on Sustainable Energy, 5, 3, pp. 804-812, (2014)

[7]

Siripitayananon P., Chen H.C., Jin K.R., A modified nearest neighbors approach for estimating missing wind data, International Journal of Smart Engineering System Design, 5, 3, pp. 149-160, (2003)

[8]

Yang Z.L., Liu Y.Q., Li C.R., Interpolation of missing wind data based on ANFIS, Renewable Energy, 36, 3, pp. 993-998, (2011)

[9]

Carbone A., Algorithm to estimate the Hurst exponent of high-dimensional fractals, Physical Review E, 76, 5, pp. 1-7, (2007)

[10]

Fraser A.M., Swinney H.L., Independent coordinates for strange attractors from mutual information, Physical Review A, 33, 2, pp. 1134-1140, (1986)

← 1 2 →