Service Affinity Scheduling for Parallel Cloud Deployment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Service delivery in cloud environments is time-consuming and error-prone due to sequential deployment and unbalanced scheduling, leading to resource waste and frequent node switching.

Innovation Solution

A method for service delivery that involves static and dynamic analysis to determine dependency relationships and priorities, allowing services to be scheduled based on affinity and resource usage, thereby improving deployment efficiency and reducing failures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If services are deployed sequentially in multiple phases, then deployment errors are reduced, but delivery time increases significantly

Engineering Contradiction:

Improvedeployment error reductionVSAvoiddelivery time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent performs static analysis and dependency relationship determination before deployment begins. By pre-calculating service dependencies, affinities, and optimal scheduling sequences, the system prepares deployment plans in advance, enabling parallel execution of independent services while maintaining reliability constraints.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent dynamically adjusts deployment scheduling based on service dependencies and resource availability. The scheduling algorithm adapts the deployment sequence and parallelization degree according to the determined dependency relationships, optimizing delivery time while ensuring reliable deployment of dependent services in correct order.

Inventive Principle:

Principle #15Dynamics

2Productivity

If services are deployed in parallel, then delivery efficiency improves, but deployment failures increase due to ignoring dependency relationships

Engineering Contradiction:

Improvedelivery efficiencyVSAvoiddeployment failure rate

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent segments services into independent deployable units based on their dependency relationships. By identifying services with no dependencies or whose dependencies are already satisfied, the system can safely deploy these segments in parallel, while maintaining proper sequencing for dependent services.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent uses static analysis to determine dependency relationships and uses this information as feedback to control the deployment process. The scheduling algorithm continuously checks dependency satisfaction status and adjusts parallelization accordingly, ensuring that services are only deployed when their dependencies are met.

Inventive Principle:

Principle #23Feedback

3Device complexity

If unbalanced scheduling is used, then resource allocation is simpler, but resource wastage and node switching increase

Engineering Contradiction:

Improvescheduling complexityVSAvoidresource wastage

Core Design Contradiction:

Device complexityVSLoss of energy

Solution Approach 1:

The patent determines service affinity for specific nodes based on local resource characteristics and service requirements. By matching services to nodes with appropriate resource profiles (CPU, memory, storage, network), the system optimizes resource utilization locally, reducing wastage and minimizing node switching while maintaining manageable scheduling complexity.

Inventive Principle:

Principle #3Local quality

4Ease of operation

If sequential deployment is used, then resource utilization is easier to manage, but delivery time increases and node switching frequency increases

Engineering Contradiction:

Improveresource management easeVSAvoiddelivery time

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The patent performs comprehensive static analysis and dependency determination before deployment, preparing scheduling information in advance. This preliminary action enables the system to manage resource allocation effectively while allowing parallel deployment of independent services, reducing delivery time without sacrificing operational simplicity.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12632294B2Service scheduling using static and dynamic service affinities

Publication Date: 2026.05.19 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A computer-implemented method, a system, and a computer program product for service delivery are disclosed. In the method, a static analysis can be performed on a plurality of services to be deployed in an environment comprising a plurality of nodes, to determine dependency relationships among the plurality of services. The plurality of services can be deployed in the environment based on the dependency relationships, a predefined priority for each of the plurality of services, and deployment time for each of the plurality of services. Also, the plurality of services can be scheduled into corresponding nodes in the environment.