Since the wind speed fluctuation could cause large instability in wind energy systems it is crucial to develop a method for precise estimation of the wind speed fluctuation. Fractal interpolation of the wind speed could be used to improve the accuracy of the estimation of the wind speed fluctuation. Based on the self-similarity feature, the fractal interpolation could be established from internal to external interval. In this article fractal interpolation was used to improve the wind speed fluctuation estimation by soft computing methods. Artificial neural network (ANN) with different training algorithms were used in order to estimate the wind speed fluctuation based on the fractal interpolation
Flow Measurement and Instrumentation, 2017, 54, 172-176
Publisher:
Elsevier
Note:
This is the peer-reviewed version of the article: Petković, D., Nikolić, V., Mitić, V.V., Kocić, L., 2017. Estimation of fractal representation of wind speed fluctuation by artificial neural network with different training algorothms. Flow Measurement and Instrumentation 54, 172–176. https://doi.org/10.1016/j.flowmeasinst.2017.01.007
TY - JOUR
AU - Petković, Dalibor
AU - Nikolić, Vlastimir
AU - Mitić, Vojislav V.
AU - Kocić, Ljubiša
PY - 2017
UR - http://dais.sanu.ac.rs/123456789/4612
AB - Since the wind speed fluctuation could cause large instability in wind energy systems it is crucial to develop a method for precise estimation of the wind speed fluctuation. Fractal interpolation of the wind speed could be used to improve the accuracy of the estimation of the wind speed fluctuation. Based on the self-similarity feature, the fractal interpolation could be established from internal to external interval. In this article fractal interpolation was used to improve the wind speed fluctuation estimation by soft computing methods. Artificial neural network (ANN) with different training algorithms were used in order to estimate the wind speed fluctuation based on the fractal interpolation
PB - Elsevier
T2 - Flow Measurement and Instrumentation
T1 - Estimation of fractal representation of wind speed fluctuation by artificial neural network with different training algorothms
SP - 172
EP - 176
VL - 54
DO - 10.1016/j.flowmeasinst.2017.01.007
ER -
@article{
author = "Petković, Dalibor and Nikolić, Vlastimir and Mitić, Vojislav V. and Kocić, Ljubiša",
year = "2017",
url = "http://dais.sanu.ac.rs/123456789/4612",
abstract = "Since the wind speed fluctuation could cause large instability in wind energy systems it is crucial to develop a method for precise estimation of the wind speed fluctuation. Fractal interpolation of the wind speed could be used to improve the accuracy of the estimation of the wind speed fluctuation. Based on the self-similarity feature, the fractal interpolation could be established from internal to external interval. In this article fractal interpolation was used to improve the wind speed fluctuation estimation by soft computing methods. Artificial neural network (ANN) with different training algorithms were used in order to estimate the wind speed fluctuation based on the fractal interpolation",
publisher = "Elsevier",
journal = "Flow Measurement and Instrumentation",
title = "Estimation of fractal representation of wind speed fluctuation by artificial neural network with different training algorothms",
pages = "172-176",
volume = "54",
doi = "10.1016/j.flowmeasinst.2017.01.007"
}
Petković D, Nikolić V, Mitić VV, Kocić L. Estimation of fractal representation of wind speed fluctuation by artificial neural network with different training algorothms. Flow Measurement and Instrumentation. 2017;54:172-176
Petković, D., Nikolić, V., Mitić, V. V.,& Kocić, L. (2017). Estimation of fractal representation of wind speed fluctuation by artificial neural network with different training algorothms.
Flow Measurement and InstrumentationElsevier., 54, 172-176.
https://doi.org/10.1016/j.flowmeasinst.2017.01.007
Petković Dalibor, Nikolić Vlastimir, Mitić Vojislav V., Kocić Ljubiša, "Estimation of fractal representation of wind speed fluctuation by artificial neural network with different training algorothms" 54 (2017):172-176,
https://doi.org/10.1016/j.flowmeasinst.2017.01.007 .
