Predictive Pipeline Analytics for Network Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network management systems face challenges in efficiently identifying and presenting relevant metrics to administrators for troubleshooting network service events, often requiring manual review of vast amounts of data, which is time-consuming and inefficient.
Innovation Solution
A controller device configured to use an intent model to determine relevant network configuration metrics by identifying a subset of routes and interfaces most likely to be of interest, based on telemetry data and intent models, and presenting these metrics in a user-friendly interface, reducing the time administrators spend reviewing data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If network management systems collect and store comprehensive telemetry data from all network devices, then the completeness and accuracy of network monitoring is improved, but the volume of data requiring manual review increases significantly
Solution Approach 1:
The patent extracts only the most relevant metrics from the comprehensive telemetry data by using intent models to identify and select specific configuration elements and metrics that are most likely to be related to network service events, thereby reducing data volume while maintaining monitoring effectiveness
Solution Approach 2:
The patent segments the network monitoring function by separating relevant metrics from irrelevant data through intent-based filtering, organizing the vast telemetry data into manageable segments that correspond to specific network services and configurations
2Loss of information
If network management systems present all collected metrics to administrators, then the comprehensiveness of information availability is improved, but the time required for root cause analysis increases
Solution Approach 1:
The patent performs preliminary action by pre-filtering and pre-organizing telemetry data according to intent models before administrators need to analyze network events, so that only pre-selected relevant metrics are presented when issues arise
Solution Approach 2:
The patent introduces intent models as an intermediary layer between the comprehensive telemetry data and the administrator's analysis needs, translating raw data into relevant, pre-filtered metrics that directly address the at-hand network service event
3Reliability
If network management systems manually review all telemetry data for events, then the thoroughness of data examination is improved, but the operational efficiency decreases
Solution Approach 1:
The patent enables the system to self-service by automatically filtering, selecting, and presenting relevant metrics based on intent models without requiring manual intervention for data preparation, thereby maintaining examination thoroughness while significantly improving operational efficiency
Data Source
AI summary
A controller device includes a memory and one or more processors coupled to the memory. The memory stores instructions that, when executed, cause the one or more processors to receive a query indicating a first time and a network service, determine a first set of configuration elements using telemetry data associated with the first time and the network service, and determine a second set of configuration elements using an intent model. The instructions further cause the one or more processors to determine one or more first metrics that occur at the first time using the first set of configuration elements and the second set of configuration elements, determine one or more second metrics at a second time using telemetry data received from the plurality of network devices, and generate data representing a user interface presenting the one or more first metrics and the one or more second metrics.