Detecting and predicting outages in mobile networks with log data.

Gurbani, Vijay K.; Kushnir, Dan; Mendiratta, Veena B.; Phadke, Chitra; Falk, Eric; State, Radu

doi:10.1109/ICC.2017.7996706

Reference : Detecting and predicting outages in mobile networks with log data.


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/32826

Title :	Detecting and predicting outages in mobile networks with log data.
Language :	English
Author, co-author :	Gurbani, Vijay K. [Nokia Bell Labs]
	Kushnir, Dan [Nokia Bell Labs]
	Mendiratta, Veena B. [Nokia Bell Labs]
	Phadke, Chitra [Nokia Bell Labs]
	Falk, Eric [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	State, Radu [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Publication date :	May-2017
Main document title :	IEEE International Conference on Communications, ICC 2017
Pages :	1-7
Peer reviewed :	Yes
On invitation :	No
Audience :	International
ISBN :	978-1-4673-8999-0
Event name :	IEEE International Conference on Communications, ICC 2017
Event date :	from 21-05-2017 to 25-05-2017
Event organizer :	IEEE
Abstract :	[en] Modern cellular networks are complex systems offering a wide range of services and present challenges in detecting anomalous events when they do occur. The networks are engineered for high reliability and, hence, the data from these networks is predominantly normal with a small proportion being anomalous. From an operations perspective, it is important to detect these anomalies in a timely manner, to correct vulnerabilities in the network and preclude the occurrence of major failure events. The objective of our work is anomaly detection in cellular networks in near real-time to improve network performance and reliability. We use performance data from a 4G LTE network to develop a methodology for anomaly detection in such networks. Two rigorous prediction models are proposed: a non-parametric approach (Chi-Square test), and a parametric one (Gaussian Mixture Models). These models are trained to detect differences between distributions to classify a target distribution as belonging to a normal period or abnormal period with high accuracy. We discuss the merits between the approaches and show that both provide a more nuanced view of the network than simple thresh- olds of success/failure used by operators in production networks today.
Research centres :	Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Services and Data management research group (SEDAN) ; Nokia Bell Labs
Permalink :	http://hdl.handle.net/10993/32826
DOI :	10.1109/ICC.2017.7996706

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Limited access	07996706.pdf		Publisher postprint	681 kB	Request a copy

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices