ML-Based Power State Control for Processing Devices

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional power management approaches fail to accurately determine device-specific usage patterns, leading to premature power conservation actions or avoidable power failures in devices that are only used during discrete periods.

Innovation Solution

The implementation of machine learning techniques to analyze usage-related data from processing devices, predict usage patterns, and automatically generate instructions for controlling power states, thereby optimizing power management without hardware changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional power management approaches are used to determine device usage patterns, then power management actions can be taken, but accuracy problems occur leading to premature power conservation actions or avoidable device power failures

Engineering Contradiction:

Improvedevice usage determination accuracyVSAvoidpower management reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent replaces conventional rule-based power management mechanisms with machine learning models that analyze usage patterns. The ML model processes historical usage data to predict future device usage states, substituting simple threshold-based decisions with intelligent predictive analytics that adapt to actual device usage patterns, thereby improving both accuracy and reliability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements feedback loops where actual device usage data is continuously collected and fed back into the machine learning model. This feedback mechanism allows the model to learn from past predictions and actual outcomes, continuously improving its accuracy in determining device usage patterns and adjusting power management decisions accordingly

Inventive Principle:

Principle #23Feedback

2Ease of operation

If devices are kept in powered-on states during periods when not in use, then device availability is maintained, but energy is wasted

Engineering Contradiction:

Improvedevice availabilityVSAvoidenergy consumption

Core Design Contradiction:

Ease of operationVSUse of energy by moving object

Solution Approach 1:

The patent implements dynamic power management where device power states are adjusted based on predicted usage patterns. Instead of static power management policies, the system dynamically transitions devices between powered-on and powered-off states based on ML-predicted likelihood of upcoming usage, optimizing the balance between availability and energy consumption

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs preliminary actions by predicting future device usage before it occurs. The machine learning model analyzes historical patterns to anticipate when a device will be needed, allowing the system to pre-keep devices powered on when necessary and pre-power them off when usage is unlikely, preventing both premature shutdowns and unnecessary energy consumption

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11256316B2Automated device power conservation using machine learning techniques

Publication Date: 2022.02.22 DELL PROD LP

AI summary

Methods, apparatus, and processor-readable storage media for automated device power conservation using machine learning techniques are provided herein. An example computer-implemented method includes obtaining usage-related data from one or more processing devices; determining at least one usage pattern for the one or more processing devices by processing the obtained usage-related data using one or more machine learning techniques; automatically generating, based at least in part on the at least one determined usage pattern, instructions pertaining to controlling one or more power states of the one or more processing devices; and performing at least one automated action based at least in part on the generated instructions.