Distributed Architecture for Performance Parameter Determination

Solution Overview

Problem

Information handling systems face challenges in efficiently allocating resources due to power, speed, and time constraints, which limits their ability to enhance system performance and handle varying technological and informational demands.

Innovation Solution

Implementing a distributed system that uses complex machine learning and artificial intelligence algorithms to analyze usage parameters across multiple information handling systems, allowing for the adjustment of performance parameters such as processing cores, memory usage, and resource allocation to optimize system performance, thereby reducing power consumption and increasing concurrent task capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If complex machine learning and artificial intelligence algorithms are implemented to analyze usage parameters and determine performance adjustments, then system performance enhancement capability is improved, but power consumption and processing resource requirements increase

Engineering Contradiction:

Improvesystem performance enhancement capabilityVSAvoidpower consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent segments the complex analysis task into two parts: local collection of usage parameters by individual information handling systems, and centralized analysis by a cloud-based system. This division allows complex AI/ML processing to occur remotely in the cloud rather than consuming local device power and resources, while still enabling performance optimization for each device.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a cloud-based intermediary system that receives usage parameters from multiple information handling systems, performs the computationally intensive AI/ML analysis, and returns performance adjustments. This intermediary handles the power-intensive processing centrally, allowing individual devices to maintain low power consumption while benefiting from sophisticated performance optimization.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If complex machine learning and artificial intelligence algorithms are implemented to analyze usage parameters, then system performance enhancement capability is improved, but processing resource requirements increase

Engineering Contradiction:

Improvesystem performance enhancement capabilityVSAvoidprocessing resource requirements

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the complex analysis task into two parts: local collection of usage parameters by individual information handling systems, and centralized analysis by a cloud-based system. This division allows complex AI/ML processing to occur remotely in the cloud rather than consuming local device power and resources, while still enabling performance optimization for each device.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a cloud-based intermediary system that receives usage parameters from multiple information handling systems, performs the computationally intensive AI/ML analysis, and returns performance adjustments. This intermediary handles the power-intensive processing centrally, allowing individual devices to maintain low power consumption while benefiting from sophisticated performance optimization.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If performance parameters are adjusted based on real-time usage analysis, then system performance is enhanced, but latency is reduced when using distributed calculations

Engineering Contradiction:

Improvesystem performanceVSAvoidlatency

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent implements preliminary action by continuously collecting and storing usage parameters locally at each information handling system before analysis is needed. This pre-collection eliminates delays associated with real-time data gathering during performance optimization events, allowing the cloud system to quickly retrieve historical data and generate performance adjustments with minimal latency.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent employs periodic action by implementing continuous monitoring and periodic analysis cycles. Usage parameters are collected continuously and periodically transmitted to the cloud system for batch analysis, enabling performance optimization to occur at regular intervals rather than requiring instantaneous real-time processing, thus balancing responsiveness with computational efficiency.

Inventive Principle:

Principle #19Periodic action

Data Source

PatentUS11327869B2Distributed architecture for determining performance parameters

Publication Date: 2022.05.10 DELL PROD LP

AI summary

System performance of a first information handling system may be adjusted based on system usage. Performance parameters may be determined by a second information handling system based on the system usage and may be used, by the first information handling system, to adjust system performance. Configuration of the first information handling system may thus be distributed to two or more tiers. The second information handling system can be more efficient with determining operating parameters for the first information handling system when the second system is not power limited, as when the first information handling system is a mobile device.