Machine Learning-assisted Management of a Virtualized Network

Toward proactive network management, machine learning is expected especially from enhancing fault management and sustaining automated system itself. This paper describes the motives for using machine learning, and provides some proof-of-concept demonstrations.

[1]  Rolf Stadler,et al.  Universal fault detection for NFV using SOM-based clustering , 2015, 2015 17th Asia-Pacific Network Operations and Management Symposium (APNOMS).

[2]  Hisashi Kashima,et al.  Eigenspace-based anomaly detection in computer systems , 2004, KDD.

[3]  Eduardo Pinheiro,et al.  Failure Trends in a Large Disk Drive Population , 2007, FAST.

[4]  Michiaki Hayashi,et al.  OPERAS: Operation record analysis system for continual improvement of operating workflows , 2011, 2011 13th Asia-Pacific Network Operations and Management Symposium.

[5]  Andreas Zeller,et al.  It's not a bug, it's a feature: How misclassification impacts bug prediction , 2013, 2013 35th International Conference on Software Engineering (ICSE).