Mathematical Problems in Engineering

Research Article

A Fault and Capacity Loss Prediction Method of Wind Power Station under Extreme Weather

Table 2

Table of parameters and optimization settings for different models.
ModelParameter
setting		Hyperparameter optimization rangeOptimal parameter
SVM“kernel,” “C”[“linear,” “RBF,” “sigmod”];
[0.01, 0.03, 0.1, 0.3, 1, 3]		“linear”; 1
RF“n_estimators”;
“max_depth”;
“max_features”		[10, 50, 100, 500];
[3, 5–7, 5–7, 9, 12, 15];
[2, 4, 6, 8, 10, 12]		100; 9; 8
XGBoost“n_estimators”;
“learning_rate”;
“max_depth”		[10, 50, 100, 500];
[0.01, 0.025, 0.05, 0.1];
[3, 5–7, 5–7, 9, 12, 15]		100; 0.05; 7
LightGBM“n_estimators”;
“num_leaves”;
“learning_rate”;
“max_depth”		[10, 50, 100, 500];
[10, 20, 30; 50];
[0.01, 0.025, 0.05, 0.1];
[3, 5–7, 5–7, 9, 12, 15]		100; 20; 0.1; 6