Power System Events Classification Technology Based on Deep-Learning

As the complexity of the power system continues to increase, the frequency of the power system anomalies is on the rise. These anomalies have significant and widespread impacts on the stability of the power grid. Therefore, the rapid and accurate classification of these anomalies is crucial in preventing their further propagation and mitigating potential economic losses. This study presents an algorithm based on Phasor Measurement Unit (PMU) data for monitoring the state of power systems and identifying the types of anomalies. First, a dataset for anomaly event classification is created based on PMU data, which is used to train and validate the anomaly event classification model. Subsequently, a robust anomaly event classification model is constructed, consisting of a residual module with one-dimensional Convolutional Neural Networks (CNN) and a cascaded fully connected neural network classifier. This algorithm has undergone rigorous testing in the IEEE New England 39 bus test system, demonstrating exceptional event recognition accuracy.