Operation Management Device Centrality Degree Fault Cause Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing operation management systems face challenges in accurately determining the fault cause due to the influence of correlation destruction and noise, especially when using the number or ratio of correlations as abnormality degrees in invariant analysis.
Innovation Solution
An operation management apparatus and method that calculates a centrality degree to estimate the center of correlation destruction distribution, using correlation destruction degrees between metrics, to accurately identify the fault cause.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the number or ratio of correlations is used as abnormality degree in invariant analysis, then the fault detection capability is improved, but the accuracy of fault cause judgment deteriorates due to influence of correlation destruction caused by other faults or noise
Solution Approach 1:
The patent changes the parameter used for fault cause judgment from simple correlation count or ratio to a weighted abnormality degree that incorporates correlation strength. By multiplying the number of correlations by the average correlation strength, the system transforms the evaluation parameter to reflect both quantity and quality of correlations, thereby improving judgment accuracy while maintaining detection capability
Solution Approach 2:
The patent creates a composite evaluation metric by combining multiple factors: the number of correlations, the strength of each correlation, and the abnormality degree of related metrics. This composite approach integrates multiple dimensions of analysis to produce a more accurate fault cause identification that is resilient to noise and other fault influences
2Adaptability or versatility
If correlation destruction detection is performed using multiple metrics, then the coverage of fault detection is improved, but the complexity of analysis increases making it difficult to identify the true fault cause
Solution Approach 1:
The patent applies local quality by calculating abnormality degrees specifically for metrics that are directly correlated with the detected correlation destruction. Instead of uniformly analyzing all metrics, the system focuses computational resources on locally relevant metrics that have direct correlation relationships with the faulty metric, thereby reducing overall analysis complexity while maintaining comprehensive fault detection coverage
Solution Approach 2:
The patent segments the analysis process into distinct steps: first detecting correlation destruction between metric pairs, then identifying affected metrics, and finally calculating abnormality degrees only for those affected metrics. This segmentation of the analysis process reduces complexity by breaking down the overall task into manageable, sequential stages rather than performing comprehensive analysis on all metrics simultaneously
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In the invariant analysis, a fault cause is judged correctly. A correlation model storing unit (112) of an operation management apparatus (100) stores a correlation model including one or more correlation functions each of which indicates a correlation between two metrics different each other among a plurality of metrics in a system. The correlation destruction detecting unit (103) detects correlation destruction of the correlation which is included in the correlation model by applying newly inputted values of the plurality of metrics to the correlation model. The abnormality calculation unit (104) calculates and outputs a centrality degree which indicates a degree to which a first metric is estimated to be center of distribution of correlation destruction on the basis of a correlation destruction degree of one or more correlations between each of one or more second metrics having a correlation with the first metric and each of one or more metrics other than the first metric among the plurality of metrics.