Virtual Computing Node Performance Engineering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face challenges in efficiently utilizing cloud computing services as they often select more powerful virtual computing nodes to ensure application performance, leading to suboptimal resource usage due to varying computing demands over time.

Innovation Solution

A system that monitors performance across different virtual computing node combinations, adjusts node types and models dynamically based on demand, and uses predictive models to optimize resource allocation, ensuring efficient use of computing resources while maintaining user-specified performance parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If users select more powerful virtual computing nodes to ensure application performance, then application performance is improved, but resource utilization efficiency deteriorates

Engineering Contradiction:
Improveapplication performanceVSAvoidresource utilization efficiency
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system dynamically adjusts the configuration and number of virtual computing nodes based on real-time monitoring of application performance metrics and resource utilization. The performance engineering system continuously collects data from multiple sources including application logs, system metrics, and user feedback, then automatically modifies computing node specifications to match actual demand, preventing both over-provisioning and under-provisioning

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements continuous feedback loops where performance metrics from running applications are monitored and fed back to the provisioning system. This feedback mechanism enables the system to learn from actual usage patterns and adjust virtual computing node allocations accordingly, ensuring optimal performance while minimizing resource waste through data-driven decision-making

Inventive Principle:
Principle #23Feedback

2Reliability

If users select more powerful virtual computing nodes, then application performance is improved, but computing cost increases

Engineering Contradiction:
Improveapplication performanceVSAvoidcomputing cost
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The system dynamically changes parameters such as CPU cores, memory size, storage capacity, and network bandwidth of virtual computing nodes based on actual application requirements. By adjusting these parameters in real-time rather than maintaining fixed high-specification nodes, the system achieves necessary performance levels while minimizing computing costs through precise resource matching

Inventive Principle:
Principle #35Parameter changes

3Loss of energy

If the system continuously monitors and adjusts virtual computing node configurations, then resource utilization efficiency is improved, but system complexity increases

Engineering Contradiction:
Improveresource utilization efficiencyVSAvoidsystem complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The performance engineering system operates autonomously by automatically monitoring application performance, analyzing resource utilization patterns, and adjusting virtual computing node configurations without requiring manual intervention. The system self-manages the entire lifecycle from data collection to decision-making and implementation, reducing the operational burden while maintaining high resource efficiency

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3614264B1Performance engineering
Publication Date: 2022.12.21 ACCENTURE GLOBAL SOLUTIONS LTD
  • EP3614264B1 patent drawingFigure 1
  • EP3614264B1 patent drawingFigure 2
  • EP3614264B1 patent drawingFigure 3

AI summary

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing performance engineering are disclosed. In one aspect, a method includes the actions of providing, to a cloud computing system that is configured to implement multiple different types of virtual computing nodes, an instruction to execute an application on a virtual computing node that is a first type of virtual computing node of the multiple different types of virtual computing nodes. The actions further include determining computing performance parameters of the virtual computing node. The actions further include determining to execute the application on both the virtual computing node and an additional virtual computing node. The actions further include selecting, from among the multiple different types of virtual computing nodes, a second type of virtual computing node. The actions further include executing the application on the virtual computing node and the additional virtual computing node.