Network Motif Mining for Root Cause Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current network systems rely on SLA thresholds to assess Quality of Experience (QoE), which are inadequate for complex impairments and fail to capture all network issues, leading to unnoticed degradations in application performance.

Innovation Solution

A network-based mining approach that identifies and roots causes impactful timeseries motifs by correlating device-level telemetry data with performance metrics across multiple paths, enabling predictive application aware routing to proactively optimize network performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If SLA thresholds are used to assess Quality of Experience, then network performance monitoring is simplified, but complex impairments and network issues go unnoticed

Engineering Contradiction:

Improvenetwork performance monitoringVSAvoiddetection of network impairments

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments network performance analysis into multiple dimensions: aggregate SLA metrics at the network level and device-level telemetry data at the individual device level. This segmentation allows simultaneous monitoring of overall network health and detailed device-specific issues, resolving the contradiction between simplified monitoring and precise impairment detection

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent adds a new dimension of analysis by introducing device-level telemetry data alongside traditional SLA thresholds. This multi-dimensional approach enables detection of complex impairments that single-threshold mechanisms miss, while maintaining the simplicity of SLA-based monitoring for overall network assessment

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Reliability

If predictive failure detection and proactive routing are implemented, then application performance is improved, but unnecessary traffic rerouting occurs negatively impacting user experience

Engineering Contradiction:

Improveapplication performanceVSAvoidunnecessary traffic rerouting impact

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent implements preliminary action by detecting predictive failure patterns in network metrics before actual SLA violations occur. By identifying emerging impairments early through device-level telemetry correlation, the system can take proactive routing decisions only when genuinely needed, avoiding unnecessary rerouting while maintaining application performance

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent establishes feedback mechanisms that continuously monitor both SLA metrics and device-level telemetry. This feedback loop enables the system to learn from actual network conditions and refine predictive models, ensuring routing decisions are based on accurate impairment detection rather than false positives, thus preventing harmful unnecessary rerouting

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12015518B2Network-based mining approach to root cause impactful timeseries motifs

Publication Date: 2024.06.18 CISCO TECHNOLOGY INC

AI summary

In one embodiment, a device identifies a timeseries motif present in a plurality of timeseries of performance metrics for a plurality of paths in a network. The device retrieves, based on the timeseries motif, device-level telemetry data from networking devices along the plurality of paths. The device determines a root cause of the timeseries motif by correlating the timeseries motif with the device-level telemetry data. The device provides an indication of the timeseries motif and its root cause for display by a user interface.