Dynamic Virtual Machine Duplication for Task-Driven Resource Allocation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In cloud environments, managing computing resources for parallel task processing is inefficient due to arbitrary virtual machine allocation, leading to suboptimal resource assignment and increased administrative load as the number of virtual machines increases.

Innovation Solution

An apparatus and method for dynamically generating duplicate devices based on the ratio of unprocessed tasks to processing-target tasks, allowing for optimal resource allocation and minimizing administrative load by assigning tasks to these devices, which can further generate secondary devices as needed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If virtual machines are arbitrarily determined and generated by administrator, then virtual machine generation is simple, but optimal computing resources cannot be assigned for the computation amount of tasks

Engineering Contradiction:

Improvecomputing resource allocation adaptabilityVSAvoidresource management complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system dynamically determines the number of virtual machines based on the computation amount of tasks rather than using fixed arbitrary values. The duplicate device manager continuously monitors task characteristics and adjusts virtual machine allocation in real-time, transforming the static resource allocation into a dynamic adaptive system that optimizes computing resources according to actual task requirements

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements feedback mechanisms where the duplicate device manager evaluates task computation amounts and uses this information to adjust virtual machine generation decisions. The system monitors the relationship between task characteristics and resource allocation outcomes, continuously refining its allocation strategy to achieve optimal resource assignment while maintaining manageable complexity through automated decision-making

Inventive Principle:

Principle #23Feedback

2Productivity

If administrator generates virtual machines one by one, then virtual machine generation is controllable, but increase in number of virtual machines causes additional load of running additional virtual machines

Engineering Contradiction:

Improvetask processing throughputVSAvoidadministrative management load

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system uses duplicate devices (virtual machines) that are generated by duplicating a base virtual machine template. The duplicate device manager creates copies of proven working configurations rather than manually configuring each virtual machine individually, enabling rapid scaling to handle increased task throughput while reducing administrative management load through automated duplication processes

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The duplicate device manager autonomously handles the generation, configuration, and management of virtual machines based on task requirements. The system self-regulates the number of virtual machines needed by evaluating task computation amounts and automatically provisioning resources without requiring continuous administrator intervention, thereby increasing productivity while minimizing administrative overhead

Inventive Principle:

Principle #25Self-service

3Productivity

If number of virtual machines is increased to process more tasks, then task processing capacity increases, but computing resource assignment becomes suboptimal

Engineering Contradiction:

Improveparallel task processing capacityVSAvoidresource assignment optimality

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system changes the parameter of virtual machine allocation from fixed arbitrary values to dynamic values determined by task computation amounts. The duplicate device manager adjusts the number and configuration of virtual machines based on varying task parameters, ensuring that resource assignment remains optimal even as parallel processing capacity scales to handle larger numbers of concurrent tasks

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS10740153B2Generating duplicate apparatuses for managing computing resources based on number of processing tasks

Publication Date: 2020.08.11 SAMSUNG SDS CO LTD

AI summary

An apparatus and a method for managing computing resources are disclosed. The apparatus for managing computing resources includes a task input interface configured to receive a plurality of processing-target tasks; a task processor configured to sequentially process the plurality of received processing-target tasks; and a duplicate device manager configured to generate one or more duplicate devices by duplicating the apparatus for managing computing resources based on at least one among a ratio of a number of unprocessed tasks to a number of processing-target tasks and the number of unprocessed tasks, and assign unprocessed tasks to the one or more generated duplicate devices.