Research on power system fault prediction based on GA-CNN-BiGRU

Introduction: This paper proposes a power system fault prediction method that utilizes a GA-CNN-BiGRU model. The model combines a genetic algorithm (GA), a convolutional neural network (CNN), and a bi-directional gated recurrent unit network Bidirectional Gated Recurrent Unit to accurately predict and analyze power system faults. Methods: The proposed model employs a genetic algorithm for structural search and parameter tuning, optimizing the model structure. The CNN is used for feature extraction, while the bi-directional gated recurrent unit network is used for sequence modeling. This approach captures the correlations and dependencies in time series data and effectively improves the prediction accuracy and generalization ability of the model. Results and Discussion: Experimental validation shows that the proposed method outperforms traditional and other deep learning-based methods on multiple data sets in terms of prediction accuracy and generalization ability. The method can effectively predict and analyze power system faults, providing crucial support and aid for the operation and management of power systems.