Correlation Model for Automated System Failure Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current system operations management technologies require significant expertise and burden system administrators with complex tasks, such as predicting and preventing system failures, due to the need for manual analysis and understanding of system structures and behaviors, leading to increased workload and potential errors.
Innovation Solution
A system operations management apparatus that generates and uses correlation models to automatically detect abnormalities in performance information, reducing the administrative burden by analyzing time-series data and providing summarized failure points and causes, allowing for automated handling of system issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis and understanding of system structures and behaviors is performed by system administrators, then detection precision of system failures is improved, but device complexity and ease of operation deteriorate due to requiring significant expertise and complex tasks
Solution Approach 1:
The patent introduces a correlation model as an intermediary between system performance data and failure detection. The model automatically analyzes time-series performance information and correlates multiple parameters to detect failures, eliminating the need for administrators to manually understand complex system structures while maintaining high detection precision through learned relationships
Solution Approach 2:
The system performs self-diagnosis by automatically analyzing its own performance data through the correlation model. The model learns from historical performance information and autonomously detects abnormalities and failures without requiring external expert intervention, thereby improving ease of operation while maintaining detection accuracy
2Measurement precision
If manual analysis and understanding of system structures and behaviors is performed by system administrators, then detection precision of system failures is improved, but productivity deteriorates due to increased workload
Solution Approach 1:
The system performs self-monitoring and self-diagnosis automatically using the correlation model that analyzes performance data in real-time. This eliminates the need for administrators to spend time on manual failure analysis while maintaining high detection precision, thereby significantly improving productivity
Solution Approach 2:
The patent replaces the mechanical process of manual analysis by administrators with an automated computational system. The correlation model computationally analyzes performance data and detects failures, substituting human labor with automated processing that maintains precision while dramatically improving productivity
3Ease of operation
If automated detection using correlation models is implemented, then ease of operation and productivity are improved, but measurement precision may deteriorate without proper model generation
Solution Approach 1:
The system performs preliminary learning by training the correlation model on historical performance data before actual failure detection. This preliminary action establishes accurate correlation relationships between multiple performance parameters, ensuring that subsequent automated detection maintains high measurement precision while providing ease of operation
Solution Approach 2:
The system incorporates feedback mechanisms where detection results and actual system states are used to continuously refine and improve the correlation model. This feedback loop ensures that the automated system maintains and improves measurement precision over time while preserving ease of operation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In a system operations management apparatus, a burden to a system administrator when providing a decision criterion in detection of a failure in the future is reduced. The system operations management apparatus 1 includes a performance information accumulation unit 12. a model generation unit 30 and an analysis unit 31. The performance information accumulation unit 12 stores performance information including a plurality of types of performance values in a system in time series. The model generation unit 30 generates a correlation model including one or more correlations between, the different types of performance values stored in the performance information accumulation unit 12 for each of a plurality of periods having one of a plurality of attributes. The analysis unit 31 performs abnormality detection of the performance information of the system which has been inputted by using the inputted performance information and the correlation model corresponding to the attribute of a period in which the inputted performance information has been acquired.