Prediction of Critical Clearing Time for Transient Stability Based on Ensemble Extreme Learning Machine Regression Model

To improve the accuracy of critical clearing time (CCT) prediction model, an ensemble regression learning method is employed, and a CCT prediction method based on the ensemble extreme learning machine regression model is proposed. First, the static power flow values are utilized as the original feature set, and the least absolute shrinkage selection operator (Lasso) is used for determining the input features. The extreme learning machine, regarded as the base learner, is used to establish the mapping relationship between the input features and CCT value. On this basis, the AdaBoost.RT algorithm is employed as the ensemble regression learning framework to construct multiple base learners. When performing CCT prediction, the predicted values of each base learner are weight integration to obtain the final prediction result. Simulation results on New England 39-bus system demonstrate the effectiveness of the proposed method.