Open AccessNetwork Anomaly Sequence Prediction Method Based on LSTM and Two-layer Window Features
Author(s) -
Hongcheng Li,
Yuan Gao,
Bing Wang,
Yuewei Ming,
Zhong Zhao
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2216/1/012063
Subject(s) - window (computing) , sliding window protocol , anomaly (physics) , computer science , sequence (biology) , series (stratigraphy) , anomaly detection , algorithm , time series , layer (electronics) , pattern recognition (psychology) , time sequence , artificial intelligence , data mining , machine learning , condensed matter physics , operating system , paleontology , chemistry , physics , organic chemistry , biology , genetics
To solve the over-fitting problem in the prediction algorithm caused by the small number of features that arise during the network anomaly prediction process, an LSTM algorithm for network anomaly predictions based on two-layer time window features was proposed. Firstly, the network alarm data sequence was divided according to the observation time window and prediction time window. Secondly, considering that the time series of the anomaly alarm data can be somewhat periodic, a time window sequence dataset was created with the periodic features and statistical features in the two-layer windows. Finally, one-shot and feedback models of the LSTM algorithm were employed to predict network anomalies. The experiment showed that the best prediction accuracy for this method is over 80% with both one-shot and feedback models, when the prediction time window is 12h.