Adaptive KPI Thresholds for Data Center Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern data centers face challenges in processing and indexing large volumes of machine-generated data due to its unstructured nature, making it difficult to apply semantic meaning and effectively monitor service-level performance.
Innovation Solution
The implementation of adaptive thresholds for key performance indicators (KPIs) that can be configured and adjusted using training data, allowing for dynamic association of entities with services and creation of entity and service definitions to normalize heterogeneous machine data, enabling efficient monitoring and visualization of service performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If adaptive thresholds are configured using training data, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary action by using training data to pre-configure adaptive thresholds before actual KPI monitoring begins. The threshold configuration module analyzes historical training data to establish initial threshold values, which are then refined during operation. This preliminary configuration reduces the complexity of real-time decision-making while maintaining high measurement precision.
Solution Approach 2:
The system implements self-service through automatic threshold adjustment mechanisms. The threshold configuration module continuously monitors KPI values and automatically adjusts thresholds based on observed patterns and training data, eliminating the need for manual intervention. This self-adjusting capability improves measurement precision while the automation reduces operational complexity.
2Manufacturing precision
If machine data is normalized to create entity and service definitions, then manufacturing precision is improved, but loss of time increases
Solution Approach 1:
The system applies preliminary action by pre-processing and normalizing machine data during the training phase before production monitoring begins. Entity and service definitions are established in advance using training data, creating a ready-to-use framework that accelerates real-time processing while maintaining high normalization accuracy.
Solution Approach 2:
The data normalization process is segmented into distinct phases: training data processing, entity definition creation, service definition creation, and operational monitoring. This segmentation allows complex normalization tasks to be performed systematically during off-peak training periods, reducing the time burden on production systems while maintaining high precision.
Data Source
AI summary
Techniques are disclosed for providing adaptive thresholding technology for Key Performance Indicators (KPIs) that are updated using training data. Adaptive thresholding technology may automatically assign new values or adjust existing values for one or more thresholds of one or more time policies. Assigning threshold values using adaptive thresholding may involve identifying training data (e.g., historical data, simulated data, or example data) for the time frames and analyzing the training data to identify variations within the data (e.g., patterns, distributions, trends). A threshold value may be determined based on the variations and may be assigned to one or more of the thresholds without additional user intervention.