论文信息 - Adaptive Failure Prediction Using Long Short-term Memory in Optical Network

Adaptive Failure Prediction Using Long Short-term Memory in Optical Network

We propose an adaptive failure prediction scheme based on LSTM leveraging actual datasets from network operator, the experimental results verify that the average accuracy of failure prediction is 93.8%.

[1] Min Zhang,et al. Failure prediction using machine learning and time series in optical network. , 2017, Optics express.

[2] Tingting Liu,et al. Fault Prediction for Satellite Communication Equipment Based on Deep Neural Network , 2018, 2018 International Conference on Virtual Reality and Intelligent Systems (ICVRIS).

[3] Lei Guo,et al. Path-based routing provisioning with mixed shared protection in WDM mesh networks , 2006, Journal of Lightwave Technology.

[4] Meiqin Liu,et al. Data-Based Line Trip Fault Prediction in Power Systems Using LSTM Networks and SVM , 2018, IEEE Access.

[5] Luying Zhou,et al. Best Effort Shared Risk Link Group (SRLG) Failure Protection in WDM Networks , 2008, 2008 IEEE International Conference on Communications.

[6] Jürgen Schmidhuber,et al. Learning to forget: continual prediction with LSTM , 1999 .