Cloud Resource Scheduling for Mixed Task Types

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing resource scheduling methods in cloud data centers face challenges in optimizing resource utilization and reducing waste, particularly in public cloud scenarios where different types of tasks have varying resource requirements.

Innovation Solution

A resource scheduling method and apparatus that differentiate between first-type tasks (SLA sensitive, resource request-based) and second-type tasks (SLA insensitive, resource usage-based), allowing for dynamic scheduling and resource allocation across the same resource server, with mechanisms to monitor and adjust resource usage to prevent waste and ensure high utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If resource overcommitment technologies such as virtualization are used to schedule computing tasks of different tenants to a same computing facility, then resource utilization is improved, but resource waste occurs when first-type tasks request more resources than actually used

Engineering Contradiction:

Improveresource utilizationVSAvoidresource waste

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The patent implements dynamic resource scheduling by introducing two different scheduling strategies: one for first-type tasks (SLA-sensitive) that guarantees resource allocation based on requests, and another for second-type tasks (SLA-insensitive) that dynamically allocates resources based on actual usage and resource pool conditions. This dynamic approach allows the system to adapt resource allocation in real-time, improving utilization while preventing waste.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes the scheduling parameter from a single static strategy to a dual-strategy system with different allocation rules. For first-type tasks, resources are allocated based on requested quantities with guarantees. For second-type tasks, resources are allocated based on actual usage patterns and resource pool availability. This parameter change enables flexible resource management that balances utilization and waste prevention.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If a public cloud carrier purchases more hardware resources to meet peak demand, then service quality is improved, but service costs increase

Engineering Contradiction:

Improveservice qualityVSAvoidservice costs

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The patent makes resource servers universal by enabling them to serve both first-type tasks (requiring resource guarantees) and second-type tasks (using dynamic allocation) simultaneously. The same physical infrastructure can dynamically switch between different allocation modes, eliminating the need for separate hardware for different service levels and reducing overall purchasing costs while maintaining service quality.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system implements self-service through automatic resource allocation and adjustment. The scheduling system automatically monitors resource usage, determines task types, and allocates resources accordingly without manual intervention. This self-service capability allows the system to efficiently manage fluctuating demand using existing resources, reducing the need for additional hardware purchases.

Inventive Principle:

Principle #25Self-service

3Reliability

If first-type tasks are scheduled with guaranteed resource allocation based on requests, then service reliability is improved, but resource fragmentation increases when resources are not fully utilized

Engineering Contradiction:

Improveservice reliabilityVSAvoidresource fragmentation

Core Design Contradiction:

ReliabilityVSLoss of substance

Solution Approach 1:

The patent introduces a resource pool as an intermediary layer between first-type and second-type tasks. The resource pool acts as a buffer that collects unused resources from first-type tasks and makes them available for second-type tasks. This intermediary mechanism resolves resource fragmentation by redistributing idle resources without affecting the guaranteed allocation of first-type tasks.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments resource allocation into two distinct layers: guaranteed allocation for first-type tasks and dynamic allocation from the resource pool for second-type tasks. This segmentation allows the system to maintain reliability for critical tasks while separately managing and reducing fragmentation through the resource pool mechanism.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12293223B2Cloud computing resource based on type of tasks and resource load rate

Publication Date: 2025.05.06 HUAWEI TECH CO LTD

AI summary

This application provides a resource scheduling method, including: when a first scheduling request message is obtained, determining a first resource server from a resource pool based on a first quantity of resources requested by the first scheduling request message, and scheduling the first quantity of resources in the first resource server, where the resource pool includes at least one resource server, and the first scheduling request message requests a resource for a first-type task; and when a second scheduling request message is obtained, schedule a resource for a task corresponding to the second scheduling request message, determining a second resource server from the resource pool based on a second quantity of resources requested by the second scheduling request message, and scheduling a third quantity of resources in the second resource server, wherein the second scheduling request message requests a resource for a second-type task.