A short-term wind speed forecast method for wind power generation
A wind speed and algorithm technology, applied in the field of short-term wind speed forecasting, to achieve high precision, accurate forecast, and reduce interference
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0023] Such as figure 1 Shown, the short-term wind speed forecast method based on CM-kNN algorithm (correlation matrix kNN algorithm) of the present invention, comprises
[0024] (1) Use the CM-kNN algorithm to preprocess the wind speed sample points. The specific operation steps of CM-kNN are:
[0025] a1) Use the training sample X to reconstruct each test sample Y, use the least squares loss function to represent the residual sum, and generate a sparse solution W, as follows:
[0026]
[0027] W=[w1,...,wm] represents the reconstruction coefficient or similarity matrix between the training sample and the test sample, and the L1-norm regularization term R 1 (W)=||W|| 1 =∑ i ∑ j |w ij |, has been shown to yield a sparse solution W.
[0028] a2) To remove the noise existing in the sample, consider the L2, 1-norm regularization term, which can make W generate the entire row of sparseness during the reconstruction process, that is, the row is sparse, defined as follows:...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More