TSN Switch Queue Length Prediction Based on an Improved LSTM Network

Algorithm 1

PCA: network topology downscaling.

Input: //sample sets

Output:

1: ; //sample means

2: ; //sample variance

3: for from 1 to do

4: for from 1 to do

5: ;

6: end for

7: end for

8: //calculate the covariance matrix of the sample

9: //eigenvalue decomposition of the covariance matrix

10: //the first maximum eigenvalues are taken and normalized to the contribution rate

11: //unit eigenvectors

12: //the individual principal component scores of each evaluation object, i.e., the sum of the scores of the dimensionality-reduced dataset