Anomaly Detection Using LSTM in IP Networks

A Long Short Term Memory network technique is being applied in the anomaly detection at Huawei in IP Network Performance Monitor. LSTM networks are trained and used to predict instant network traffic at port level. The output is sent to an anomaly identifier to detect abnormal traffic events. Good p...

Full description

Saved in:
Bibliographic Details
Published in2018 Sixth International Conference on Advanced Cloud and Big Data (CBD) pp. 334 - 337
Main Authors Qin, Gang, Chen, Ying, Lin, Yu-Xin
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2018
Subjects
Anomaly detection
IP networks
Logic gates
Long Short Term Memory network
Network Performance Monitor
Neural networks
Support vector machines
Tensorflow
Training
Online AccessGet full text
DOI10.1109/CBD.2018.00066

Cover

More Information
Summary:A Long Short Term Memory network technique is being applied in the anomaly detection at Huawei in IP Network Performance Monitor. LSTM networks are trained and used to predict instant network traffic at port level. The output is sent to an anomaly identifier to detect abnormal traffic events. Good precision and recall rate are achieved by using the traffic data from routers.
DOI:10.1109/CBD.2018.00066