Detecting Network Soft-failures with the Network Link Outlier Factor (NLOF)

06/14/2019
by   Christopher Mendoza, et al.
0

In this paper, we describe and experimentally evaluate the performance of our Network Link Outlier Factor (NLOF) for detecting soft-failures in communication networks. The NLOF is computed using the throughput values derived from NetFlow records. The flow throughput values are clustered in two stages, outlier values are determined within each cluster, and the flow outliers are used to compute the outlier factor or score for each network link. When sampling NetFlow records across the full span of a network, NLOF enables the detection of soft-failures across the span of the network; large NLOF scores correlate well with links experiencing failure.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/15/2019

MSD-Kmeans: A Novel Algorithm for Efficient Detection of Global and Local Outliers

Outlier detection is a technique in data mining that aims to detect unus...
research
11/05/2019

Detecting Point Outliers Using Prune-based Outlier Factor (PLOF)

Outlier detection (also known as anomaly detection or deviation detectio...
research
08/01/2021

A Reinforcement Learning Approach for Scheduling in mmWave Networks

We consider a source that wishes to communicate with a destination at a ...
research
08/18/2018

Impact of Link Failures on the Performance of MapReduce in Data Center Networks

In this paper, we utilize Mixed Integer Linear Programming (MILP) models...
research
12/30/2019

Outlier Detection and Data Clustering via Innovation Search

The idea of Innovation Search was proposed as a data clustering method i...
research
02/15/2021

Sub-Graph p-cycle formation for span failures in all-Optical Networks

p-Cycles offer ring-like switching speed and mesh-like spare capacity ef...
research
01/14/2019

CFOF: A Concentration Free Measure for Anomaly Detection

We present a novel notion of outlier, called the Concentration Free Outl...

Please sign up or login with your details

Forgot password? Click here to reset