Please use this identifier to cite or link to this item: https://ktisis.cut.ac.cy/handle/10488/12644
Title: A probabilistic approach for failure localization
Authors: Panayiotou, Tania 
Chatzis, Sotirios P. 
Ellinas, Georgios 
Keywords: Fiber optic networks;Learning systems;Orthogonal frequency division multiplexing;Transparent optical networks
Category: Electrical Engineering - Electronic Engineering - Information Engineering
Field: Engineering and Technology
Issue Date: 23-Jun-2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: International Conference on Optical Network Design and Modeling, 2017, Budapest, Hungary, 15-18 May
Conference: International Conference on Optical Network Design and Modeling (ONDM) 
Abstract: This work considers the problem of fault localization in transparent optical networks. The aim is to localize single-link failures by utilizing statistical machine learning techniques trained on data that describe the network state upon current and past failure incidents. In particular, a Gaussian Process (GP) classifier is trained on historical data extracted from the examined network, with the goal of modeling and predicting the failure probability of each link therein. To limit the set of suspect links for every failure incident, the proposed approach is complemented with the utilization of a Graph-Based Correlation heuristic. The proposed approach is tested on a dataset generated for an OFDM-based optical network, demonstrating that it achieves a high localization accuracy. The proposed scheme can be used by service providers for reducing the Mean-Time-To-Repair of the failure.
URI: http://ktisis.cut.ac.cy/handle/10488/12644
ISBN: 978-3-901882-93-7 (online)
DOI: 10.23919/ONDM.2017.7958555
Rights: © 2017 IEEE.
Type: Conference Papers
Appears in Collections:Δημοσιεύσεις σε συνέδρια/Conference papers

Show full item record

SCOPUSTM   
Citations

1
checked on Aug 13, 2019

Page view(s)

43
Last Week
1
Last month
4
checked on Aug 19, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.