Proactive Fault Prediction for SaaS Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting and resolving issues in remote data storage used by SaaS systems are manual, time-consuming, and costly, often resulting in sub-optimal system performance due to their reactive nature.
Innovation Solution
A fault prediction system that models faults using source data from computing and remote data storage systems, and generates predictions based on current data, enabling proactive fault avoidance recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual problem detection and resolution is used, then human expertise can be applied to identify root causes and select resolutions, but the process is time-consuming and costly, resulting in sub-optimal system performance
Solution Approach 1:
The system performs preliminary actions by continuously monitoring storage metrics and predicting potential faults before they occur. The fault prediction model analyzes historical data and current trends to forecast future storage issues, enabling proactive intervention rather than reactive response to manual problem detection.
Solution Approach 2:
The system implements self-service through automated fault prediction and recommendation generation. The AI/ML model autonomously analyzes storage metrics, identifies potential faults, and provides resolution recommendations without requiring manual intervention from experienced engineers, thereby reducing time loss while maintaining system performance.
2Reliability
If manual problem detection and resolution is used, then engineers can identify root causes and select suitable resolutions, but the process is costly due to requiring experienced engineers
Solution Approach 1:
The system replaces manual engineer intervention with an automated AI/ML-based fault prediction system. The model autonomously analyzes storage metrics, predicts potential faults, and generates resolution recommendations, eliminating the need for expensive expert engineers while maintaining high-quality problem resolution through data-driven insights.
Solution Approach 2:
The patent substitutes the mechanical system of manual engineer analysis with an automated AI/ML-based prediction system. The fault prediction model uses machine learning algorithms to process storage metrics and generate recommendations, replacing the manual cognitive process of experienced engineers and reducing both cost and complexity.
3Productivity
If reactive problem resolution is used, then issues are addressed after occurrence, but system performance remains sub-optimal for the significant period of time between occurrence and resolution
Solution Approach 1:
The system performs preliminary actions by continuously monitoring storage metrics and predicting potential faults before they occur. The fault prediction model analyzes historical data and current trends to forecast future storage issues, enabling proactive intervention rather than reactive response, thereby maintaining optimal system performance throughout the time period.
Solution Approach 2:
The system implements continuous feedback through ongoing monitoring of storage metrics and iterative refinement of the fault prediction model. The model learns from historical fault data and current system state, providing continuously updated predictions that enable timely intervention and maintain optimal performance by reducing the time between fault detection and resolution.
Data Source
AI summary
Current data from a SaaS system and associated remote data storage system is used to automate proactive fault avoidance. Machine learning models are used to predict faults. Rules are used with a rules engine to calculate corresponding fault avoidance recommendations. The model and rules are trained and created using source data from the SaaS system and remote data storage system with which the model and rules will be used. Current data from those systems is used to predict future faults and calculate recommendations to avoid the predicted faults. Implementation of a recommendation triggers a re-test to determine whether the predicted fault is still likely to occur.