Cloud VM Scheduling Using Resource Profiles to Avoid Host Contention

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In IaaS environments, high load stacking leads to resource contention and performance degradation due to multiple tenants with high resource requirements running on the same physical resources, necessitating improved resource scheduling to enhance utilization and reduce costs.

Innovation Solution

A resource scheduling method that utilizes deployment attribute information and historical operation data to generate virtual machine profiles, allowing for efficient allocation of virtual machines based on expected resource consumption, thereby avoiding high-resource virtual machines from being scheduled to the same host.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If multiple tenants with high resource requirements are centrally running on the same physical resource, then resource utilization ratio is improved, but resource contention and performance degradation occur

Engineering Contradiction:
Improveresource utilization ratioVSAvoidperformance degradation
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The system performs preliminary actions by generating virtual machine profiles based on historical operation data before actual deployment. These profiles include predicted resource consumption information that is used to pre-determine optimal host assignments, preventing resource contention before it occurs rather than reacting to it during operation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system utilizes historical operation data as feedback to generate virtual machine profiles. This feedback mechanism allows the scheduling system to learn from past performance patterns and adjust future resource allocation decisions, thereby optimizing the balance between resource utilization and performance reliability

Inventive Principle:
Principle #23Feedback

2Ease of operation

If virtual machines are scheduled based on deployment attribute information only, then scheduling simplicity is maintained, but resource consumption prediction accuracy deteriorates

Engineering Contradiction:
Improvescheduling simplicityVSAvoidresource consumption prediction accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary analysis of historical operation data to generate comprehensive virtual machine profiles that include predicted resource consumption information. This preliminary action enriches the basic deployment attribute information with predictive data, enabling more accurate resource consumption prediction while maintaining a relatively simple scheduling process

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes the parameters used for scheduling from simple deployment attributes to enhanced profiles that include predicted resource consumption data. This parameter transformation allows the system to maintain operational simplicity while significantly improving prediction accuracy through the use of historical data patterns

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4703881A1Resource scheduling method based on a cloud service platform and electronic device
Publication Date: 2026.03.04 BEIJING VOLCANO ENGINE TECH CO LTD
  • EP4703881A1 patent drawingFigure 1
  • EP4703881A1 patent drawingFigure 2
  • EP4703881A1 patent drawingFigure 3

AI summary

A resource scheduling method based on a cloud service platform, an electronic device, and a non-transitory computer-readable storage medium are provided. The method includes: acquiring deployment attribute information of a to-be-scheduled virtual machine that is applied for deployment by a tenant on a cloud service platform; acquiring a target virtual machine profile matching the deployment attribute information of the to-be-scheduled virtual machine from a virtual machine profile set of the cloud service platform, the virtual machine profile is used to describe deployment attribute information and resource consumption information corresponding to a virtual machine, and the resource consumption information is used to describe an expected consumption of at least one resource of a virtual machine matching the deployment attribute information of the virtual machine; and scheduling the to-be-scheduled virtual machine according to the resource consumption information in the target virtual machine profile.