Server Network Failure Correlation for Common Cause Mitigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack the ability to programmatically detect and mitigate common cause failures in server network performance issues, leading to exacerbation of these issues over time.
Innovation Solution
A method and system utilizing telemetry systems, AI/ML models, and graphical user interfaces to identify root causes and components at risk, dynamically updating network configurations to prevent and repair failures, and deploying new components to replace failing ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If server network specialists manually investigate and resolve performance issues, then immediate response to failures is achieved, but more severe server network performance issues arise over time as responses exacerbate existing problems
Solution Approach 1:
The system enables self-service through automated root cause analysis and mitigation actions. The AI/ML model continuously monitors network telemetry, identifies failures, determines root causes, and executes remediation actions without requiring manual intervention from server network specialists, allowing the system to resolve issues autonomously and prevent exacerbation of existing problems
Solution Approach 2:
The system implements continuous feedback loops where network performance data is collected via telemetry systems, analyzed by AI/ML models, and used to automatically adjust network configurations. This closed-loop feedback mechanism enables real-time detection and response to performance issues, preventing them from escalating while continuously improving network resilience
2Ease of operation
If manual investigation and resolution of server network issues is performed, then human expertise is utilized, but the process exacerbates server network performance issues over time
Solution Approach 1:
The patent replaces manual mechanical processes with automated AI/ML-based systems. The AI/ML model automatically analyzes network telemetry data, identifies failure patterns, determines root causes, and executes remediation actions, eliminating the need for human specialists to manually investigate and resolve issues, thereby preventing operational errors from exacerbating network performance problems
3Reliability
If no programmatic detection and mitigation technology is available, then current infrastructure remains simple, but common cause failures cannot be detected or prevented before occurrence
Solution Approach 1:
The system performs preliminary actions by continuously monitoring network telemetry data and using AI/ML models to predict potential failures before they occur. The model identifies patterns and correlations in network behavior that indicate impending failures, allowing the system to execute preventive mitigation actions in advance, thereby detecting and preventing common cause failures before they impact service availability
Solution Approach 2:
The AI/ML-based monitoring system provides multi-functional capabilities including real-time failure detection, root cause analysis, predictive failure detection, and automated mitigation action execution. This universal system handles multiple functions within a single integrated platform, improving failure detection capability while managing complexity through consolidation rather than proliferation of separate systems
Data Source
AI summary
A method for implementing a data server network infrastructure maintenance tool within a data server network. The method comprises obtaining an initial data server network configuration, extracting a set of correlations from at least one repository of historical network failure incident information, detecting a first set of failures via at least one telemetry system of the data server network, determining a current state of the data server network via the at least one telemetry system, generating an updated network configuration based on the first set of failures and the current state of the data server network, identifying a second set of components that is likely to fail, and at least one from among preventing and repairing at least one subsequent failure.