LAUSR

In this paper, in-depth analysis, and evaluation of the transient stability of a renewable energy power system are carried out, and a transient stability evaluation method based on stacked autoencoders is proposed. The method breaks through the traditional two-stage evaluation mode. The method proposes a deep network model with a multi-branch structure for different physical natures of different measured data. With the help of different sparse denoising coding networks (branches), features are extracted from each measurement separately and fused on top of the model to finally complete the transient stability assessment. The simulation results show that the method can effectively handle the simultaneous input of multiple measurements, and has the advantages of high accuracy and robustness in noisy environments. To effectively determine the model hyperparameters, the orthogonal test is used for model selection, which can significantly reduce the hyperparameter seeking space and save computational resources. The simulation results show that the method can effectively use multiple measurements to improve the accuracy of wind power prediction. Also, the input variable selection index based on mutual information can provide a good guide for further improvement of model performance.