Network Auto-Healing via Knowledge-Based AI Root Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network auto-healing systems lack coordination between troubleshooting and resolution methods, and do not utilize intelligence models, leading to inefficiencies in identifying root causes and resolving network errors.
Innovation Solution
Implementing a knowledge-based artificial intelligence (AI) model to determine root cause analysis (RCA) and generate resolutions for network errors, with a loop protection mechanism to prevent infinite loops and improve decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a knowledge-based AI model is implemented to generate RCA and resolutions, then the productivity and reliability of network error resolution is improved, but the device complexity increases
Solution Approach 1:
A knowledge-based AI model is introduced as an intermediary component between the alarm reception module and the resolution execution module. This AI model processes alarm information, generates root cause analyses, and determines resolution steps, thereby improving resolution speed and reliability while adding controlled complexity through a specialized intelligence layer
Solution Approach 2:
Traditional manual troubleshooting mechanisms are replaced with an automated knowledge-based AI model that uses predefined knowledge bases and inference rules. This substitution eliminates manual intervention requirements and accelerates the resolution process by using intelligent algorithms instead of mechanical procedural checks
2Device complexity
If manual troubleshooting procedures are used, then the device complexity is lower, but the productivity and time required for resolution increase
Solution Approach 1:
The system implements self-service automation where the knowledge-based AI model independently performs root cause analysis and resolution determination without human intervention. The system automatically receives alarms, processes them through the AI model, executes resolutions, and monitors outcomes, thereby reducing resolution time while maintaining manageable complexity through standardized automated procedures
3Device complexity
If existing RCA procedures are used without AI enhancement, then the device complexity is lower, but the reliability of error resolution decreases
Solution Approach 1:
The system incorporates feedback mechanisms where the outcomes of resolution executions are monitored and fed back into the knowledge-based AI model. This feedback loop enables continuous improvement of the AI model's accuracy in generating root cause analyses and resolutions, thereby enhancing reliability while maintaining system simplicity through iterative learning rather than complex architectural changes
Data Source
AI summary
A method of network auto-healing performed by at least one processor includes receiving an indication that an alarm corresponding to an error in a network is triggered, determining whether an existing root cause analysis (RCA) corresponds to the error, based on determining that an existing RCA does not correspond to the error, generating, by a knowledge-based artificial intelligence (AI) model, a first RCA for resolving the error, and identifying a first resolution to the error based on the first RCA.