Data Center SLA Classification Using Failure, Impact, and Resilience Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting data center equipment failure risks and determining service level agreements (SLAs) are inadequate, as they fail to account for factors beyond component failure risk and are not predictive enough for SLA contract durations, leading to potential overpayment or underprovisioning of services.
Innovation Solution
A method that uses failure probability, impact, and resilience models, combined with a classifier model, to predict system failures, assess their impact on other systems, and map these into recommended SLA categories, considering data center topology, criticality, and customer support maturity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing failure prediction methods are used, then the prediction process is simple, but the prediction accuracy is insufficient for SLA contract durations
Solution Approach 1:
The system segments the failure prediction problem into three distinct models: failure probability model (predicts likelihood of failure), impact model (predicts effect on other systems), and resilience model (predicts mitigation capability). Each model focuses on a specific aspect, improving overall prediction accuracy while managing complexity through modular design.
Solution Approach 2:
The system transitions from traditional short-term failure prediction to long-term prediction suitable for SLA contract durations by incorporating multiple dimensions: time horizon (extended duration), system interdependencies (topology), criticality levels, and resilience factors. This multi-dimensional approach enables accurate long-term predictions.
2Measurement precision
If comprehensive failure analysis is performed, then SLA recommendations are more accurate, but computational resources and time increase
Solution Approach 1:
The system performs preliminary classification of systems into SLA categories based on their failure probability, impact, and resilience characteristics. This pre-classification enables faster subsequent analysis and recommendation generation, reducing overall analysis time while maintaining accuracy.
Solution Approach 2:
The system transforms complex multi-factor failure analysis into standardized SLA category parameters that can be processed efficiently. By converting diverse input factors (topology, criticality, resilience) into discrete SLA categories, the system achieves accurate recommendations with reduced computational overhead.
Data Source
AI summary
Using a failure probability model, a probability of a failure in a first system within a specified time period is predicted. Using an impact model, an impact of the failure on a second system is predicted. Using a resilience model, an impact reduction of the failure is predicted. The probability, the impact, and the impact reduction are mapped into a recommended service level agreement category for the first system, the mapping performed using a classifier model.