ML-Based Microservice Deployment Across Multi-Cloud Platforms

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The complexity of selecting cloud providers and virtual environments for microservices deployment is increasing due to the large number of options and differences between cloud offerings, making it difficult to find optimal platforms that meet the requirements of microservices.

Innovation Solution

A microservices deployment platform using machine learning algorithms to predict and deploy microservices on optimal cloud providers and instances, leveraging a multi-cloud interface to abstract API complexities and automate deployment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual selection of cloud providers and virtual environments is used, then developers have control over deployment decisions, but the complexity and time required for selection increases significantly

Engineering Contradiction:

Improveease of cloud provider selectionVSAvoidcomplexity of cloud options

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically analyzing microservice features and selecting optimal cloud providers and virtual environments without requiring manual developer intervention. The machine learning model autonomously processes deployment requests, evaluates multiple cloud options, and makes informed selection decisions based on microservice characteristics.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical selection process with an automated machine learning-based system. Instead of developers manually evaluating and selecting from numerous cloud options, the system uses ML algorithms to automatically determine the optimal cloud provider and virtual environment configuration based on analyzed microservice features.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual analysis of cloud provider requirements is performed, then developers can ensure optimal platform selection, but the time required for deployment increases

Engineering Contradiction:

Improvedeployment speedVSAvoidtime for cloud provider selection

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-training machine learning models on cloud provider characteristics and microservice requirements before actual deployment occurs. The model is prepared in advance with knowledge of various cloud platforms and their suitable workloads, enabling rapid automated selection during deployment without requiring time-consuming analysis at execution time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces time-consuming manual analysis with automated machine learning inference. The trained ML model rapidly processes microservice features and returns optimal cloud provider recommendations almost instantly, eliminating the need for developers to manually review and compare cloud provider requirements in detail during deployment.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If standardization between cloud provider platforms is improved, then switching between cloud providers becomes easier, but the flexibility to choose specialized cloud options is reduced

Engineering Contradiction:

Improveflexibility in cloud provider choiceVSAvoidstandardization of cloud configurations

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system applies local quality by tailoring cloud provider recommendations to the specific characteristics of each microservice. Instead of applying a one-size-fits-all standardization approach, the machine learning model analyzes individual microservice features (such as computational requirements, memory needs, scalability requirements) and provides customized cloud provider and virtual environment selections that optimize performance for each specific workload.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent utilizes parameter changes by dynamically adjusting cloud provider selection based on varying microservice characteristics. The machine learning model processes different input parameters related to microservice requirements and translates them into appropriate cloud configuration recommendations, allowing the system to adapt to diverse deployment scenarios while maintaining a standardized automated selection process.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260023584A1Microservices deployments using machine learning

Publication Date: 2026.01.22 DELL PROD LP

AI summary

A method comprises receiving a request for cloud deployment of at least one microservice, wherein the request includes one or more features of the at least one microservice. The one or more features are analyzed using one or more machine learning algorithms. The method further comprises predicting, based at least in part on the analyzing: (i) a cloud platform of a plurality of cloud platforms to deploy the at least one microservice; and (ii) a cloud instance in which the at least one microservice is to be executed, and interfacing with the cloud platform to enable deployment of the at least one microservice.