公开(公告)号：US20210011890A1

公开(公告)日：2021-01-14

申请号：US16669033

申请日：2019-10-30

Applicant: EXFO Inc.

Inventor： Maha Mdini ,  Justin Whatley ,  Sylvain Nadeau

IPC: G06F16/21 ,  G06F16/22 ,  H04L12/24

Abstract: An embodiment may involve obtaining a set of data records including features characterizing operational aspects of a communication network. Each data record may include a feature vector and performance metrics of the communication network. Each feature vector may include a multiple elements corresponding to feature-value pairs. A first statistical analysis may be applied to the set of data records and their performance metrics to identify major contributors to degraded network performance. A second statistical analysis may be applied to identify elements that negatively influence the major contributors, and to discriminate between additive effects and incompatibilities as the source of negative influence. For each major contributor, a hierarchical dependency tree may be constructed with the major contributor as the root node and influencer elements as other nodes. Redundant dependencies may be removed, mutually dependent influencer elements grouped, and only the longest edges retained, in order to create dependency graph.

公开(公告)号：US11138163B2

公开(公告)日：2021-10-05

申请号：US16669033

申请日：2019-10-30

Applicant: EXFO Inc.

Inventor： Maha Mdini ,  Justin Whatley ,  Sylvain Nadeau

IPC: G06F16/00 ,  G06F16/21 ,  G06F16/22 ,  H04L12/24

Abstract: An embodiment may involve obtaining a set of data records including features characterizing operational aspects of a communication network. Each data record may include a feature vector and performance metrics of the communication network. Each feature vector may include a multiple elements corresponding to feature-value pairs. A first statistical analysis may be applied to the set of data records and their performance metrics to identify major contributors to degraded network performance. A second statistical analysis may be applied to identify elements that negatively influence the major contributors, and to discriminate between additive effects and incompatibilities as the source of negative influence. For each major contributor, a hierarchical dependency tree may be constructed with the major contributor as the root node and influencer elements as other nodes. Redundant dependencies may be removed, mutually dependent influencer elements grouped, and only the longest edges retained, in order to create dependency graph.