Cloud Resource Provisioning Time Prediction Using Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional resource provisioning approaches in cloud environments rely on incomplete human knowledge and static rules, leading to inaccurate temporal estimates and customer dissatisfaction due to variations in delivery times.

Innovation Solution

Utilizing trained machine learning techniques to generate temporal predictions for cloud resource provisioning by analyzing historical data from order management, supply chain, and logistics systems, employing a deep neural network to predict delivery times accurately.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional resource provisioning approaches use static rules and incomplete human knowledge for temporal estimates, then the provisioning process can be managed with simple methods, but the accuracy of delivery time estimates deteriorates

Engineering Contradiction:

Improvedelivery time estimate accuracyVSAvoidprovisioning system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces conventional static rule-based estimation systems with machine learning models that dynamically predict delivery times. The ML models process historical data from multiple systems (order management, supply chain, logistics) to generate accurate temporal predictions, substituting the mechanical approach of fixed rules with an intelligent system that adapts to varying conditions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces machine learning models as intermediary components between the provisioning systems and the temporal estimation function. These models act as mediators that process data from multiple source systems (order management, supply chain, logistics) and translate it into accurate delivery time predictions, resolving the contradiction by adding intelligent processing layer.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If conventional approaches rely on static rules for provisioning estimates, then the system is easy to operate and implement, but customer satisfaction deteriorates due to inaccurate estimates

Engineering Contradiction:

Improvecustomer satisfactionVSAvoidprovisioning system operation

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent implements self-service through automated machine learning models that independently analyze historical data from multiple systems and generate delivery time predictions without human intervention. The system automatically trains models, processes data, and provides temporal estimates, reducing manual operation while improving reliability through data-driven accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent incorporates feedback mechanisms where machine learning models continuously learn from actual delivery outcomes and historical provisioning data. The models process feedback from multiple systems (order management, supply chain, logistics) to refine predictions, improving customer satisfaction through increasingly accurate estimates while maintaining automated operation.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If dynamic factors are incorporated into provisioning estimates, then delivery time accuracy improves, but the system complexity increases beyond conventional static rules

Engineering Contradiction:

Improvetemporal estimate accuracyVSAvoidprovisioning system architecture

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies universality by designing machine learning models that serve multiple functions: processing data from diverse systems (order management, supply chain, logistics), handling various temporal relationships, and generating predictions across different provisioning scenarios. This multi-functional approach consolidates complexity into unified models that accurately capture dynamic factors.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent utilizes parameter changes by transforming static rule-based parameters into dynamic variables that the machine learning models can process. Historical data from multiple systems provides varying parameters (delivery times, provisioning durations, logistical factors) that the models analyze to generate accurate temporal estimates, capturing dynamic relationships without requiring complex system architecture.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12566643B2Generating temporal predictions for provisioning cloud resources using trained machine learning techniques

Publication Date: 2026.03.03 DELL PROD LP

AI summary

Methods, apparatus, and processor-readable storage media for generating temporal predictions for provisioning cloud resources using trained machine learning techniques are provided herein. An example computer-implemented method includes training one or more machine learning techniques using historical data pertaining to cloud resource provisioning and related order information; obtaining data pertaining to at least one order related to one or more hardware components, wherein the at least one order includes one or more cloud resources; generating at least one temporal prediction for provisioning the one or more cloud resources, in fulfillment of the at least one order, by processing at least a portion of the obtained data using the one or more trained machine learning techniques; and performing one or more automated actions based at least in part on the at least one generated temporal prediction.