AI Data Recovery Prioritization for Storage Devices

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current backup and disaster recovery solutions face challenges in efficiently predicting server or environment failures and unsuccessful recoveries, leading to high costs due to resource-intensive test data recoveries, which are not feasible for frequent or all servers in an environment.

Innovation Solution

A method using machine learning algorithms to analyze storage device parameters, calculate probabilities of failure and recovery success, and allocate computing resources based on normalized priority levels to recommend devices for test data recovery procedures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If frequent test data recoveries are performed on all servers, then reliability of recovery process is improved, but resource consumption and cost increase significantly

Engineering Contradiction:

Improverecovery process reliabilityVSAvoidcomputing resource consumption

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

Instead of performing test data recoveries on all servers (excessive action), the system applies machine learning to identify and prioritize only those servers with higher failure risk (partial action). This selective approach maintains recovery reliability for critical systems while reducing overall resource consumption by excluding low-risk servers from frequent testing.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system changes the parameter of test recovery frequency from a uniform approach (all servers tested equally) to a dynamic, risk-based approach. By using machine learning models to assess failure probabilities and recovery success likelihoods, the system adjusts testing parameters (frequency, resource allocation) based on individual server characteristics and risk profiles.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If manual monitoring and test recoveries are performed on all devices, then detection precision of recovery issues is improved, but time consumption and operational complexity increase

Engineering Contradiction:

Improverecovery issue detection accuracyVSAvoidtime for test recoveries

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system replaces manual monitoring and mechanical test recovery processes with an automated machine learning-based prediction system. The ML models automatically analyze device parameters, historical data, and system states to predict failures and recommend test recoveries, eliminating the need for manual intervention while maintaining or improving detection accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the machine learning model to autonomously identify at-risk devices and generate test recovery recommendations without human intervention. The automated system continuously monitors device health metrics and independently determines which devices require testing, reducing both time consumption and operational complexity.

Inventive Principle:

Principle #25Self-service

3Quantity of substance

If test data recoveries are performed uniformly across all servers, then coverage is improved, but resource allocation efficiency deteriorates

Engineering Contradiction:

Improvenumber of devices coveredVSAvoidresource allocation efficiency

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The system applies local quality by allocating computing resources differently based on individual server characteristics and risk profiles. Instead of uniform resource distribution, the ML model identifies specific devices with higher failure probabilities and directs more testing resources to those locations, while reducing or eliminating testing for low-risk devices, thereby optimizing overall resource allocation efficiency.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11561875B2Systems and methods for providing data recovery recommendations using A.I

Publication Date: 2023.01.24 ACRONIS INT

AI summary

Disclosed herein are methods and systems for providing data recovery recommendations. In an exemplary aspect, a method may comprise identifying a plurality of storage devices. For each respective device of the plurality of storage devices, the method may comprise extracting a respective input parameter indicative of a technical attribute of the respective device, inputting the respective input parameter into a machine learning algorithm configured to output both a first likelihood of the respective device needing a data recovery and a second likelihood that the data recovery will fail, and determining a respective priority level of the respective device based on the first likelihood and the second likelihood. The method may comprise normalizing each respective priority level, and recommending a device of the plurality of storage devices for a test data recovery procedure based on each normalized priority level.