TY - EJOU
AU - Guo, Zhenhua
AU - Zhang, Lixin
AU - Hu, Xue
AU - Chen, Huanmei
TI - Wind Speed Prediction Modeling Based on the Wavelet Neural Network
T2 - Intelligent Automation \& Soft Computing
PY - 2020
VL - 26
IS - 3
SN - 2326-005X
AB - Wind speed prediction is an important part of the wind farm management and
wind power grid connection. Having accurate prediction of short-term wind
speed is the basis for predicting wind power. This paper proposes a short-term
wind speed prediction strategy based on the wavelet analysis and the multilayer perceptual neural network for the Dabancheng area, in China. Four
wavelet neural network models using the Morlet function as the wavelet basis
function were developed to forecast short-term wind speed in January, April,
July, and October. Predicted wind speed was compared across the four models
using the mean square error and regression. Prediction accuracy of model 4
was high, satisfying the forecasting wind power industry requirements.
Therefore, the proposed algorithm could be applied for practical short-term
wind speed predictions.
KW - Artificial neural network
KW - forecasting
KW - wavelet transform
KW - wind speed
DO - 10.32604/iasc.2020.013941