Dynamic Virtual Machine Provisioning for Cloud Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud-based software applications face suboptimal performance due to static virtual machine configurations that do not adapt to time-variant characteristics such as network congestion, latency, and power consumption, leading to inefficiencies and potential disruptions in user experience.
Innovation Solution
A dynamic provisioning method that queries a multi-tiered pool of virtual machines to identify classes with favorable time-variant characteristics, allowing for the swapping of virtual machines to maintain optimal performance, ensuring continuous operation without disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If virtual machines are statically configured, then system stability is maintained, but adaptability to changing conditions deteriorates
Solution Approach 1:
The patent implements dynamic virtual machine provisioning by continuously monitoring time-variant characteristics (TVCs) such as network congestion, latency, and power consumption, and automatically swapping VMs based on real-time conditions. This transforms the static VM configuration into a dynamic system that adapts to changing environmental factors, directly resolving the contradiction between stability and adaptability.
Solution Approach 2:
The system employs feedback mechanisms by querying the pool manager for TVC values and comparing them against threshold criteria. Based on this feedback loop, the system intelligently determines when and which VMs to swap, enabling adaptive behavior while maintaining operational stability through controlled, criterion-based changes.
2Productivity
If virtual machines are dynamically swapped based on TVCs, then performance optimization is improved, but system complexity increases
Solution Approach 1:
The system performs self-service by automatically monitoring its own performance metrics and TVCs, then autonomously making provisioning decisions without external intervention. The selection server independently queries the pool manager, evaluates TVCs against criteria, and executes VM swaps based on predetermined rules, optimizing performance while managing complexity through automation.
Solution Approach 2:
The patent changes the operational parameters of virtual machines by dynamically adjusting which VMs are active based on TVC thresholds. Instead of manually configuring VM parameters, the system automatically changes the deployment state of VMs according to real-time measurements of network congestion, latency, and power consumption, achieving performance optimization through parameter-driven automation.
3Adaptability or versatility
If multiple virtual machine classes are maintained in the pool, then versatility is improved, but resource management complexity increases
Solution Approach 1:
The pool manager serves as a universal resource that manages multiple VM classes with different TVC profiles. Instead of requiring separate management systems for each VM type, the pool manager provides a unified interface that handles allocation, monitoring, and swapping across diverse VM configurations, maintaining versatility while simplifying resource management through centralized control.
Data Source
AI summary
A technique for dynamically provisioning virtual machines for running a cloud-based software application includes querying a pool manager of a multi-tiered pool of virtual machines to identify a set of classes of virtual machines, which meet a specified size criterion, and a respective TVC (time-variant characteristic) for each class. If an identified one of the set of classes has a smaller TVC than a TVC of one of the virtual machines currently running the application, the technique proceeds to swap the current virtual machine for a virtual machine having the identified class.