Mixed Instance Catalogs for Cloud VM Resource Allocation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Cloud computing systems face inefficiencies in resource allocation and energy usage due to the fixed pricing of virtual machines based on hourly rates, leading to wasted computational resources when machines are powered on but not fully utilized, especially with adhesive service sessions that occupy capacity without allowing other sessions to run.

Innovation Solution

Implementing a mixed instance catalog system that includes virtual machines of varying capacities, where larger capacity machines handle base loads and smaller capacity machines handle peak loads, with a power manager to dynamically power on/off machines based on demand and usage thresholds.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If virtual machines are powered on to handle service sessions, then service availability is improved, but energy consumption and computational resource waste increase when machines are not fully utilized

Engineering Contradiction:

Improveservice availabilityVSAvoidenergy consumption

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system dynamically powers virtual machines on and off based on real-time demand. When service sessions are requested, VMs are activated; when no sessions are needed, they are powered down. This dynamic operation resolves the contradiction by making the system adaptive to actual usage patterns rather than maintaining static power states.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system pre-configures virtual machine images with necessary software and settings, allowing rapid deployment when needed. This preliminary preparation enables quick activation without requiring continuous operation, reducing energy consumption while maintaining service availability when required.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If larger capacity virtual machines are used, then base load handling capability is improved, but resource utilization efficiency decreases when demand is low

Engineering Contradiction:

Improvebase load handling capabilityVSAvoidresource utilization efficiency

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system segments virtual machine capacities into multiple sizes (small, medium, large) and distributes service sessions across them based on demand patterns. This segmentation allows the system to use appropriately-sized VMs for different load conditions, avoiding the waste of always running large-capacity VMs when only small capacity is needed.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes operational parameters by adjusting the number and capacity of active virtual machines based on demand thresholds. When demand is low, fewer or smaller VMs are activated; when demand increases, more or larger VMs are brought online, optimizing resource utilization efficiency while maintaining productivity.

Inventive Principle:

Principle #35Parameter changes

3Loss of energy

If smaller capacity virtual machines are used, then energy consumption is reduced, but ability to handle peak loads decreases

Engineering Contradiction:

Improveenergy consumptionVSAvoidpeak load handling capability

Core Design Contradiction:

Loss of energyVSProductivity

Solution Approach 1:

The system dynamically scales virtual machine capacity by activating additional VMs or upgrading existing ones when peak load thresholds are detected. This dynamic response allows the system to maintain energy efficiency during normal operation while rapidly expanding capacity to handle peak demands without permanent over-provisioning.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system pre-configures multiple virtual machine images of varying capacities, allowing rapid deployment of larger-capacity VMs when peak loads are anticipated or detected. This preliminary preparation enables quick scaling without requiring continuous operation of all possible capacity levels.

Inventive Principle:

Principle #10Preliminary action

4Ease of operation

If fixed hourly pricing is used for virtual machines, then pricing simplicity is maintained, but operational costs increase due to wasted computational resources

Engineering Contradiction:

Improvepricing simplicityVSAvoidoperational costs

Core Design Contradiction:

Ease of operationVSLoss of energy

Solution Approach 1:

The system implements feedback mechanisms that monitor service session demand and automatically adjust virtual machine allocation accordingly. This feedback loop enables the system to respond to actual usage patterns, powering down or reducing capacity of VMs when demand is low, thereby reducing operational costs while maintaining pricing simplicity through automated management.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11500685B2Mixed instance catalogs

Publication Date: 2022.11.15 CITRIX SYSTEMS INC

AI summary

Methods and systems for providing services using mixed instance catalogs are described herein. A catalog may comprise a plurality of first virtual machines and a plurality of second virtual machines. The capacity of a first virtual machine may be larger than the capacity of a second virtual machine. Connection requests to access a service associated with the catalog may be distributed among the plurality of first virtual machines and the plurality of second virtual machines.