Predictive Analytics System for Proactive Disaster Recovery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing natural disaster prediction models lack the capability to automatically invoke proactive measures to maintain high availability of computing environments, relying on manual human intervention which is time and cost inefficient.

Innovation Solution

Implementing a predictive analytics system that uses data structures to assess the likelihood and cost of natural disasters, automatically invoking proactive measures such as workload shifting and unscheduled backups to maintain high availability, leveraging existing natural disaster prediction models for cost-benefit analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual human intervention is used to invoke proactive measures, then flexibility and control are maintained, but time efficiency and response speed deteriorate

Engineering Contradiction:

Improvemanual controlVSAvoidresponse time

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system pre-configures multiple proactive measures with associated cost-benefit thresholds before disasters occur. When a disaster prediction is received, the system automatically compares the prediction against pre-set thresholds and invokes appropriate measures without requiring manual human intervention, thereby reducing response time while maintaining operational control through pre-established rules.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system enables self-service automation by implementing an algorithm that autonomously evaluates disaster predictions, determines appropriate proactive measures, and executes them without human intervention. The system serves itself by automatically managing the entire workflow from prediction reception to measure invocation, eliminating delays associated with manual decision-making.

Inventive Principle:

Principle #25Self-service

2Reliability

If more proactive measures are invoked, then high availability is improved, but cost increases

Engineering Contradiction:

Improvehigh availabilityVSAvoidcost

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system changes the parameter of measure selection by introducing cost-benefit analysis thresholds. Instead of invoking all possible proactive measures or relying on manual judgment, the system automatically adjusts which measures are invoked based on pre-configured cost-benefit parameters. This ensures that only measures with acceptable cost-benefit ratios are executed, optimizing both reliability and cost efficiency.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system applies partial action by selectively invoking only those proactive measures that meet the cost-benefit threshold criteria rather than implementing all possible measures. This partial invocation strategy maintains high availability where necessary while avoiding unnecessary costs for measures with poor cost-benefit ratios, achieving an optimal balance between reliability and cost.

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If automated systems are implemented, then response speed and efficiency are improved, but system complexity increases

Engineering Contradiction:

Improveresponse efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The automated system is segmented into distinct functional modules: a prediction reception module, a cost-benefit analysis module with pre-configured thresholds, and a measure invocation module. This segmentation reduces system complexity by creating independent, manageable components that can be developed, tested, and maintained separately, while still achieving automated response efficiency.

Inventive Principle:

Principle #1Segmentation

4Loss of energy

If cost-benefit analysis is performed, then resource allocation is optimized, but processing time increases

Engineering Contradiction:

Improveresource optimizationVSAvoidprocessing time

Core Design Contradiction:

Loss of energyVSLoss of time

Solution Approach 1:

The cost-benefit analysis thresholds are pre-configured and stored in the system before disaster predictions are received. When a prediction arrives, the system performs a simple threshold comparison rather than conducting complex real-time cost-benefit calculations. This preliminary setup approach optimizes resource allocation while minimizing processing time during actual disaster response.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10169139B2Using predictive analytics of natural disaster to cost and proactively invoke high-availability preparedness functions in a computing environment

Publication Date: 2019.01.01 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Using predictive analytics of natural disaster in a proactive manner to proactively invoke appropriate action(s) to prepare for an impending disaster, in view of a cost of such action(s), to maintain high availability of a computing environment and/or to facilitate disaster recovery therein. Existing natural disaster prediction model(s) are leveraged to provide input to an assessment of cost/benefit, such that proactive measures can be selected for automatic invocation within the computing environment.