Coefficient Determination Service for Cloud Performance Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies face challenges in accurately assessing and replicating the performance of production computing resources in networked environments, particularly when these resources include unique or unsupported operating systems or custom hardware components, making it difficult to find equivalent resources in hosted environments.

Innovation Solution

A coefficient determination service is used to simulate the performance of production hardware and software by transmitting resource metrics from a target computing environment, executing a workload in both the target and networked environments, and calculating a coefficient of equivalency to predict performance and identify suitable networked environments that match the target's performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If production computing resources include unique or unsupported operating systems or custom hardware components, then the system maintains specialized functionality and performance, but it becomes difficult to find equivalent resources in hosted network environments

Engineering Contradiction:
Improveperformance accuracyVSAvoidenvironment compatibility
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent creates virtual copies of production computing resources by capturing their performance characteristics, resource metrics, and behavioral patterns. These copies are stored as templates that can be replicated in hosted network environments, enabling resources with unique operating systems or custom hardware to be represented as virtual instances that maintain their original performance characteristics while being compatible with standardized hosting infrastructure

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system transforms physical resource parameters (hardware specifications, operating system details) into virtual performance parameters (resource metrics, performance characteristics). By changing the representation from physical to virtual parameters, the system enables specialized resources to be ported to different hosted environments while maintaining performance equivalence through coefficient-based matching

Inventive Principle:
Principle #35Parameter changes

2Productivity

If virtualization technologies are used to allow dynamic creation and deletion of virtual machines, then resource utilization efficiency increases, but accurately assessing performance and finding equivalent resources becomes more complex

Engineering Contradiction:
Improveresource utilization efficiencyVSAvoidperformance assessment complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces a coefficient determination service as an intermediary between virtualized resources and hosted environments. This service calculates equivalence coefficients that bridge the gap between dynamic virtual machine performance and static hosted resource specifications, simplifying the assessment process by providing a standardized metric rather than requiring complex direct comparisons

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates a universal performance assessment framework that works across different virtualization platforms and hosted environments. By defining standardized resource metrics and equivalence coefficients that can be applied universally, the system enables consistent performance assessment regardless of the underlying virtualization technology or hosting infrastructure

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10601690B2Assessing performance of networked computing environments
Publication Date: 2020.03.24 AMAZON TECH INC
  • US10601690B2 patent drawing
  • US10601690B2 patent drawing
  • US10601690B2 patent drawing

AI summary

Systems and methods are described for accurately determining which of a set of networked computing environments most closely approximates a target computing environment. The determination is based on executing a reference workload in the target computing environment and calculating a coefficient of equivalency for each of the networked computing environments, which relates the performance of one or more computing resources in the target computing environment to the corresponding resources in the networked computing environments. The coefficient of equivalency may further be used to determine which of a set of networked computing environments will provide a target level of performance when executing the workload. The target computing environment may be assessed in terms of time, cost, percentage of capacity utilized, or other criteria.