Multi-Level Network Root Cause Analysis System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing analytics platforms face challenges in determining the root cause of network performance issues from correlated factors, making it difficult to identify and address the underlying cause of problems such as increased user request latency in webserver applications.
Innovation Solution
A multi-level process involving data collection, system metric generation, ranking, and conditional analysis using machine learning models to distinguish between correlated and root cause factors, providing a visual representation and allowing network operators to exclude irrelevant metrics for a more focused analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If existing analytics platforms capture all network traffic and application performance data from all network devices, then comprehensive data availability for analysis is improved, but the ability to determine root cause from collected data deteriorates due to information overload and difficulty in distinguishing correlated factors from actual causes
Solution Approach 1:
The patent segments the analysis process into multiple levels: first identifying correlated factors, then systematically eliminating them to isolate the root cause. This multi-level segmentation transforms the overwhelming comprehensive data into manageable analysis stages, where each level focuses on specific subsets of factors rather than analyzing all data simultaneously.
Solution Approach 2:
The patent extracts and removes correlated factors from the analysis by performing conditional analysis that excludes known non-causal factors. This extraction process isolates the remaining factors that are more likely to be the actual root cause, transforming the mixed data set into a refined set of potential causes.
2Measurement precision
If a multi-level process with conditional analysis and metric exclusion is implemented, then root cause identification accuracy is improved, but analysis time and process complexity increase
Solution Approach 1:
The patent performs preliminary identification of correlated factors in the first level of analysis, preparing a ranked list of potential root causes before conducting the more time-consuming conditional analysis. This preliminary action filters out obviously correlated factors early, reducing the scope and time required for subsequent detailed analysis.
Solution Approach 2:
The patent implements a dynamic, iterative analysis process where the analysis depth and scope can be adjusted based on initial findings. The multi-level structure allows the system to adaptively proceed through levels only as needed, enabling operators to stop at level one for quick correlated factor identification or continue to deeper levels only when root cause precision is critically required.
Data Source
AI summary
Disclosed herein is a multi-level analysis for determining a root cause of a network problem by performing a first level of the multi-level process that includes collecting data from one or more network components, generating a set of system metrics where each system metric of the set representing a portion of the data, ranking the set of system metrics based on a level of correlation of each system metric to the network problem to yield a ranked set of system metrics, and providing a visual representation of the first level of the multi-level process. A second level of the multi-level process includes receiving an input identifying one or more of the ranked set of system metrics to be excluded from analysis and performing a conditional analysis using only ones of the set of system metrics that are not identified for exclusion.