Cloud Resource Scheduling Using Expected Cycles and Utilization Thresholds

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing computing resource scheduling in cloud computing is inefficient as it relies solely on user-ordered resources, lacking intelligence in optimizing utilization rates and performance.

Innovation Solution

A method and device for determining expected cycle numbers of computing resources based on utilization rate and performance thresholds, scheduling them within a remaining available time period to enhance utilization and performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If computing resources are scheduled solely based on user orders, then the scheduling process is simple, but the intelligence of resource scheduling is poor and utilization rates are suboptimal

Engineering Contradiction:

Improveintelligence of resource schedulingVSAvoidscheduling system complexity

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The system pre-calculates expected cycle numbers for computing resources based on historical data and performance metrics before actual scheduling occurs. This preliminary determination of resource cycles enables intelligent scheduling decisions to be made automatically without complex real-time computations, resolving the contradiction between scheduling intelligence and system complexity

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The scheduling system automatically determines expected cycle numbers and allocates resources based on predefined conditions and performance thresholds without requiring complex manual intervention or highly sophisticated algorithms. The system serves itself by using its own performance data to make scheduling decisions, improving intelligence while keeping the system relatively simple

Inventive Principle:

Principle #25Self-service

2Productivity

If computing resources are allocated to meet performance thresholds, then the total performance meets requirements, but the utilization rate of remaining available resources may be low

Engineering Contradiction:

Improvetotal performanceVSAvoidutilization rate of remaining available resources

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system determines expected cycle numbers that may exceed minimum performance requirements by utilizing remaining available resources. By allocating resources partially beyond what is strictly necessary to meet thresholds, the system ensures both performance requirements are met and resource utilization is maximized, preventing waste of available capacity

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The scheduling system continuously monitors performance metrics and utilization rates, using this feedback to adjust expected cycle numbers and resource allocation decisions. This closed-loop approach ensures performance thresholds are maintained while optimizing the utilization of remaining available resources across scheduling cycles

Inventive Principle:

Principle #23Feedback

3Productivity

If computing resources are operated according to expected cycle numbers to maximize utilization, then the utilization rate exceeds target rates, but the performance of individual resources may vary

Engineering Contradiction:

Improveutilization rateVSAvoidperformance consistency

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system applies different expected cycle numbers to different computing resources based on their individual characteristics, performance capabilities, and workload requirements. Rather than uniform allocation, each resource receives a customized cycle determination that considers its local properties, enabling high overall utilization while maintaining appropriate performance levels for each specific resource

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12572388B2Computing resource scheduling based on expected cycles

Publication Date: 2026.03.10 LENOVO (BEIJING) LTD

AI summary

A computing resource scheduling method includes determining expected cycle numbers of computing resources used in an application scenario based on a first condition and a second condition, and scheduling the computing resources in a remaining available time period according to the expected cycle numbers of the computing resources. The first condition includes that the computing resources are operated according to the expected cycle numbers to have a utilization rate of a remaining available object to be greater than a target utilization rate. The second condition includes that a total performance of the computing resources meets a threshold value when the computing resources are operated according to the expected cycle numbers, and a performance of any one computing resource is positively correlated with computing power of the computing resource.