Machine Learning Data Migration Segmentation for Lower Downtime

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Migrating enterprise networks from on-premise platforms to cloud-based platforms is a manual, resource-intensive process with high unpredictability and failure risks, leading to significant disruptions and inefficiencies in data transfer.

Innovation Solution

An automated machine learning-based system that segments data into smaller units for migration, using predictive models to optimize execution time, segment size, and column selection, enabling controlled pauses and restarts to minimize downtime and resource wastage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If data migration is performed manually without automation, then resource consumption can be controlled, but migration time and operational complexity increase significantly

Engineering Contradiction:

Improvemigration speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically predicting migration times, segmenting data, and executing migrations without manual intervention. The machine learning model autonomously analyzes data characteristics and generates migration plans, eliminating the need for manual resource allocation and migration orchestration while maintaining controlled resource consumption through automated decision-making

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes parameters dynamically by using machine learning models to predict migration times based on data characteristics, then adjusting segment sizes and migration strategies accordingly. This allows the system to optimize migration speed for different data types and volumes while automatically managing resource allocation, resolving the contradiction between productivity and complexity

Inventive Principle:

Principle #35Parameter changes

2Productivity

If data is migrated in large single batches, then migration throughput is high, but failure impact and restart overhead increase

Engineering Contradiction:

Improvemigration throughputVSAvoidfailure resilience

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system divides large datasets into smaller segments based on predicted migration times and data characteristics. Each segment can be migrated independently with controlled resource allocation, allowing the system to maintain high throughput by processing multiple segments in parallel while limiting failure impact to individual segments rather than the entire migration

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts segment sizes and migration strategies based on real-time predictions from machine learning models. Segment boundaries are determined by analyzing data distribution patterns and predicting optimal chunk sizes that maximize throughput while ensuring each segment can complete within acceptable timeframes and resource limits, thereby balancing productivity and reliability

Inventive Principle:

Principle #15Dynamics

3Manufacturing precision

If migration execution time is extended, then data can be processed more thoroughly, but operational downtime and resource allocation periods increase

Engineering Contradiction:

Improvemigration accuracyVSAvoiddowntime

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by using machine learning models to predict migration times and optimal segment sizes before actual migration begins. This pre-analysis allows the system to plan migration strategies that achieve high accuracy in data transformation while minimizing execution time, as the predictive models have already identified efficient processing paths and resource allocation strategies

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces manual mechanical migration processes with machine learning-based predictive systems. Instead of using fixed, conservative migration parameters that require extended execution times to ensure accuracy, the ML models dynamically optimize migration parameters based on data characteristics, achieving high precision migration in shorter timeframes by substituting intelligent prediction for traditional trial-and-error approaches

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12461784B2Cloud data migration using machine learning prediction models

Publication Date: 2025.11.04 ACCENTURE GLOBAL SOLUTIONS LTD

AI summary

An automated machine learning-based system and method of managing content for data migrations. The system can process bulk tabular datasets and real-time legacy application parameters. The data can then be segmented into segments based on an estimated time for execution of the data migration for the given dataset generated by a machine learning model. In some embodiments, the system can automatically generate a code that can perform the data migration based on the proposed segment segmentation. The proposed embodiments are effective in reducing downtime during migrations as well as limiting the impact of failure events on the process.