Automated Fault Correction via Pattern Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network management systems rely heavily on manual intervention by domain experts, leading to reactive rather than proactive fault identification and correction, resulting in service disruptions and customer dissatisfaction due to the inability to predict and automate fault resolution in large, dynamic networks.
Innovation Solution
A method for automated fault correction using machine learning techniques that identifies patterns in network events, generates substantiating data, and determines root causes based on occurrence probability, severity, and topological relationships, enabling self-healing actions and reducing manual effort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual fault identification and correction processes are used, then operators can resolve issues with human judgment, but service disruptions occur during the resolution time and operator workload increases
Solution Approach 1:
The system performs preliminary actions by proactively identifying potential faults before they cause service disruptions. The fault prediction module analyzes network data patterns to detect early signs of failures, allowing the system to take corrective actions in advance, such as isolating problematic components or rerouting traffic, thereby preventing service outages before they occur.
Solution Approach 2:
The system implements self-service through automated fault detection, analysis, and correction mechanisms. The fault prediction module automatically identifies potential issues, the root cause analysis module determines the source without human intervention, and the system executes corrective actions autonomously, reducing dependency on manual operator intervention and minimizing service disruption time.
2Productivity
If more network devices are deployed to handle increased traffic, then network capacity increases, but the complexity of monitoring and managing these devices increases
Solution Approach 1:
The fault prediction and management system serves multiple functions within a single integrated platform. It performs data collection from various network devices, pattern recognition across different device types, root cause analysis for diverse failure modes, and coordination of corrective actions across the network infrastructure, thereby simplifying the management of complex multi-device networks through a universal system.
3Loss of information
If operators manually monitor all network events, then detailed awareness of network status is achieved, but information overload occurs and response efficiency decreases
Solution Approach 1:
The system extracts and isolates only the most critical and relevant information from the vast amount of network data. The pattern recognition module filters out noise and identifies only significant anomalies, extracting key fault indicators and presenting them to operators in a simplified format, thereby maintaining comprehensive network awareness while reducing information overload and operator workload.
Data Source
AI summary
Automated fault correction in a network environment comprises identifying a pattern in a set of network events and generating a set of substantiating data for the identified patterns. The method can also identify an occurrence probability value for each network event and generate root cause data based on a ranking for the network events using a set of parameters including the occurrence probability. The method can also be directed to performing a regression of the root cause data against a set of historic data and selecting the root cause with a predefined accuracy as an acceptable candidate. The acceptable candidate is then provided for assisted learning for automated fault correction.