Network Fault Prediction Based on CNN-LSTM Hybrid Neural Network

The network brings convenience and efficiency to people's life and work, and at the same time, the network will also cause loss to human beings because of failures, so it is particularly important to predict faults before the faults occur. The fault prediction technology can prepare the staff to repair the faults in advance, reduce the repair time of the fault, and thus reduce the loss caused by the faults. Therefore, this paper proposes a network log-based CNN-LSTM hybrid prediction model for wireless network faults: firstly, the network log is preprocessed, the sample is extracted by two-level time window, then the sample features are extracted by CNN, and finally, the extracted features are input into LSTM for prediction. To demonstrate the superiority of the CNN-LSTM hybrid neural network prediction model, in this experiment, it is compared with CNN and Random Forest. The result shows that the prediction performance of CNN-LSTM is better than the other two models.