IT Infrastructure Lifecycle Prediction Using AI

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current IT infrastructure management systems are inadequate in handling heterogeneous environments with varying hardware and software components, as they fail to accurately predict the lifespan of individual components, leading to inefficient maintenance and potential system failures.

Innovation Solution

A system that collects and analyzes data from hardware and software components to create qualitative values representing their status, using cognitive and artificial intelligence calculations to compute the probability of life expectancy, enabling proactive maintenance and extending the system's operational life.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If existing data center infrastructure management methods are used, then hardware replacements and software failures can be addressed, but the system cannot accurately predict component lifespan or extend operational life beyond supported EOL dates

Engineering Contradiction:

Improvesystem operational reliabilityVSAvoidcomponent lifespan prediction accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The system performs preliminary analysis of hardware and software components by collecting operational data, generating qualitative values, and computing life expectancy probabilities before actual failures occur. This enables proactive maintenance planning and extends operational life beyond manufacturer-supported EOL dates through predictive rather than reactive management.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously collects operational data from hardware and software components, processes this data through qualitative value generation and AI-based probability computation, and uses the results to update maintenance decisions and extend component operational life. This closed-loop feedback mechanism enables accurate lifespan prediction and reliability improvement.

Inventive Principle:

Principle #23Feedback

2Duration of action of stationary object

If analytical-based root cause analysis is implemented, then residual life can be estimated and extended, but the system complexity and computational requirements increase

Engineering Contradiction:

Improvecomponent operational durationVSAvoidsystem complexity

Core Design Contradiction:

Duration of action of stationary objectVSDevice complexity

Solution Approach 1:

The system segments the complex task of lifespan prediction into distinct modules: data collection from multiple sources, qualitative value generation for hardware and software components, probability computation using AI algorithms, and result presentation. This segmentation manages system complexity while enabling extended operational duration through comprehensive analysis.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces qualitative values as intermediary representations that bridge raw operational data and final life expectancy predictions. These qualitative values simplify the computational process by transforming complex multi-source data into standardized metrics that can be processed by AI algorithms, thereby managing system complexity while extending component operational life.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If comprehensive data collection from multiple sources is performed, then accurate life expectancy probability can be computed, but the data processing time and computational resources increase

Engineering Contradiction:

Improvelife expectancy prediction precisionVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary data collection and qualitative value generation continuously in the background before final probability computation is needed. This preliminary processing organizes and pre-processes operational data from multiple sources, reducing the time required for final life expectancy calculations while maintaining high prediction precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces traditional mechanical data processing methods with cognitive and artificial intelligence-based calculations for probability computation. This substitution enables efficient processing of comprehensive operational data from multiple sources, achieving accurate life expectancy predictions without excessive processing time through advanced computational algorithms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10585773B2System to manage economics and operational dynamics of IT systems and infrastructure in a multi-vendor service environment

Publication Date: 2020.03.10 KYNDRYL INC

AI summary

A method is provided to manage economics and operational dynamics of various information technology (IT) systems. A computer collects data indicative of operation of a plurality of hardware components and collects data indicative of operation of a plurality of software components. The computer creates a first qualitative value representing a hardware status of the plurality of the hardware components and a second qualitative value representing a software status of the plurality of the software components. The first and second qualitative values are displayed in graphical form for evaluation by a system operator, and the computer computes a probability of life expectancy for the plurality of hardware components and the plurality of software components based on said first and second qualitative values and utilizing cognitive and artificial intelligence based calculations to determine the probability.