Cloud Deployment Cost Prediction Using Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The process of efficiently deploying cloud computing resources is arduous and costly, requiring significant manual intervention and computational resources, which can lead to inefficient deployment and increased expenses.

Innovation Solution

A computing system that retrieves resource data and cloud service provider data, uses machine learning models to generate cloud deployment data with predicted deployment costs, and automatically deploys preauthorized computing workloads to cloud service providers that meet certain criteria, while providing indications of predicted deployment costs for non-preauthorized workloads.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual intervention is used to apportion resources to cloud service providers, then deployment accuracy can be maintained, but the process becomes arduous and costly with excessive time expenditure

Engineering Contradiction:

Improvedeployment speedVSAvoidoperational complexity

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system enables self-service deployment by automatically analyzing cloud service provider data, evaluating deployment options, and executing resource apportionment without requiring manual intervention. The automated system performs what previously required human operators to review data and make deployment decisions, thereby increasing productivity while maintaining accuracy through consistent algorithmic evaluation.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual process of resource apportionment with an automated computational system. Instead of human operators manually analyzing data and making decisions, the system uses automated data processing and analysis mechanisms to evaluate cloud service providers and determine optimal deployment configurations, eliminating the need for manual intervention while maintaining or improving deployment accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If significant computational resources are allocated for resource analysis, then deployment accuracy improves, but excessive costs are incurred

Engineering Contradiction:

Improvecost analysis accuracyVSAvoidcomputational resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by focusing computational resources on the most critical analysis tasks rather than processing all possible data equally. It prioritizes evaluating key deployment factors and cloud service provider comparisons, allocating computational power selectively to where it provides the most value for accuracy while avoiding waste on less important calculations.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system dynamically adjusts analysis parameters and evaluation criteria based on the specific deployment context. By changing which parameters are prioritized for analysis depending on the workload characteristics and cloud provider options available, the system achieves high accuracy without consistently requiring maximum computational resource allocation for every analysis scenario.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If comprehensive cloud service provider data is collected and analyzed, then deployment optimization improves, but the complexity of the process increases

Engineering Contradiction:

Improvedeployment efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments the complex deployment analysis process into distinct modular components: data collection from cloud providers, data processing and validation, deployment option evaluation, and decision execution. Each segment handles a specific aspect of the analysis, making the overall complex process manageable and maintainable while still comprehensively evaluating all relevant factors for optimal deployment.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system implements a universal platform that handles multiple cloud service providers and various deployment scenarios through a single integrated architecture. Rather than creating separate analysis systems for each provider or deployment type, the universal system adapts to different providers and scenarios using the same core mechanisms, reducing overall system complexity while maintaining comprehensive analysis capabilities.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250077305A1Cost measurement and analytics for optimization on complex processing

Publication Date: 2025.03.06 BANK OF AMERICA CORP

AI summary

Aspects of the disclosure relate to using machine learning models to automatically deploy computing workloads. A computing system may retrieve resource data. The resource data may comprise deployment costs of computing workloads that are currently deployed, indications of computing workloads that are preauthorized for automatic deployment, and indications of computing workloads that are not preauthorized for automatic deployment. Cloud service provider data indicating cloud service provider costs may be retrieved, via an application programming interface (API) connector. Based on inputting the resource data and the cloud service provider data into machine learning models, cloud deployment data may be generated. The cloud deployment data may comprise predicted deployment costs of the cloud service providers. The computing workloads that are preauthorized for automatic deployment may be deployed. Indications of predicted deployment costs may be generated for each of the computing workloads that are not preauthorized for automatic deployment.