Determining Most Likely Links (MLL) for Network Fault Localization
We propose and evaluate a technique that learns the probability of a network transmission link experiencing a fault by using outlier flows (in the performance sense) as training data. This technique autonomously determines the most likely links causing performance degradation in a communications net...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10044186/ |
| _version_ | 1811160262052413440 |
|---|---|
| author | Christopher Mendoza Michael P. McGarry |
| author_facet | Christopher Mendoza Michael P. McGarry |
| author_sort | Christopher Mendoza |
| collection | DOAJ |
| description | We propose and evaluate a technique that learns the probability of a network transmission link experiencing a fault by using outlier flows (in the performance sense) as training data. This technique autonomously determines the most likely links causing performance degradation in a communications network; a critical feature of zero-touch network management. Our new Network Link Outlier Factor (NLOF) with most likely links (NLOF:MLL) is experimentally compared to the existing literature (including our original NLOF) using classification performance measures: recall, precision, <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula>-score, and time-to-detection. We utilize inferential statistics and a wide set of Mininet experiments to determine statistically significant performance differences. We find that our NLOF:MLL outperforms the existing literature wrt the important <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula>-score while exhibiting a competitive time-to-detection. |
| first_indexed | 2024-04-10T05:54:31Z |
| format | Article |
| id | doaj.art-e4c9031cf7b84ceebc96047f9d476c37 |
| institution | Directory Open Access Journal |
| issn | 2644-125X |
| language | English |
| last_indexed | 2024-04-10T05:54:31Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj.art-e4c9031cf7b84ceebc96047f9d476c372023-03-04T00:00:12ZengIEEEIEEE Open Journal of the Communications Society2644-125X2023-01-01465967010.1109/OJCOMS.2023.324468410044186Determining Most Likely Links (MLL) for Network Fault LocalizationChristopher Mendoza0Michael P. McGarry1https://orcid.org/0000-0002-4645-0379Department of Electrical and Computer Engineering, University of Texas at El Paso, El Paso, TX, USADepartment of Electrical and Computer Engineering, University of Texas at El Paso, El Paso, TX, USAWe propose and evaluate a technique that learns the probability of a network transmission link experiencing a fault by using outlier flows (in the performance sense) as training data. This technique autonomously determines the most likely links causing performance degradation in a communications network; a critical feature of zero-touch network management. Our new Network Link Outlier Factor (NLOF) with most likely links (NLOF:MLL) is experimentally compared to the existing literature (including our original NLOF) using classification performance measures: recall, precision, <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula>-score, and time-to-detection. We utilize inferential statistics and a wide set of Mininet experiments to determine statistically significant performance differences. We find that our NLOF:MLL outperforms the existing literature wrt the important <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula>-score while exhibiting a competitive time-to-detection.https://ieeexplore.ieee.org/document/10044186/Zero-touch network managementclusteringoutlier detectiondata streamingfault detectionfault localization |
| spellingShingle | Christopher Mendoza Michael P. McGarry Determining Most Likely Links (MLL) for Network Fault Localization IEEE Open Journal of the Communications Society Zero-touch network management clustering outlier detection data streaming fault detection fault localization |
| title | Determining Most Likely Links (MLL) for Network Fault Localization |
| title_full | Determining Most Likely Links (MLL) for Network Fault Localization |
| title_fullStr | Determining Most Likely Links (MLL) for Network Fault Localization |
| title_full_unstemmed | Determining Most Likely Links (MLL) for Network Fault Localization |
| title_short | Determining Most Likely Links (MLL) for Network Fault Localization |
| title_sort | determining most likely links mll for network fault localization |
| topic | Zero-touch network management clustering outlier detection data streaming fault detection fault localization |
| url | https://ieeexplore.ieee.org/document/10044186/ |
| work_keys_str_mv | AT christophermendoza determiningmostlikelylinksmllfornetworkfaultlocalization AT michaelpmcgarry determiningmostlikelylinksmllfornetworkfaultlocalization |