Ultra-short-term forecast of wind speed and wind power based on morphological high frequency filter and double similarity search algorithm

Author(s):  
D.Y. Hong ◽  
T.Y. Ji ◽  
M.S. Li ◽  
Q.H. Wu
2014 ◽  
Vol 1008-1009 ◽  
pp. 137-143
Author(s):  
Ying Jie Qin ◽  
Shan Song ◽  
Bin Shi ◽  
Zhen Jian Xie ◽  
Li Wei Qiao

For power grid with large-scale wind energy, the short-term wind power prediction is important to the grid’s scheduling and stable operating. The overall short-term forecast for wind power connected to the grid relies on the wind velocity and historical power data. Firstly, K-means clustering is introduced to model the power grid, so that the relationship between wind velocity and power can be perfectly described. Considering that there are multiple factors contributing to the prediction of wind velocity and power, we use real data of 15 wind generating set to obtain dependable weight factors of all those dimensions. With the support of mass data, the prediction of power is proved by several measurements (ME, MRE, MAE, RMSE) to be accurate.


2019 ◽  
Vol 5 ◽  
pp. 1172-1184 ◽  
Author(s):  
Moniki Ferreira ◽  
Alexandre Santos ◽  
Paulo Lucio

Sign in / Sign up

Export Citation Format

Share Document