Data Storage Thermal Management via Neural Network Scheduling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Data storage devices in autonomous vehicles face challenges in managing power usage and temperature, leading to potential performance degradation and safety issues due to increased energy consumption and thermal management limitations, especially in hot environments.

Innovation Solution

Implementing an artificial neural network (ANN) to predict power consumption and temperature trends, allowing the data storage device to throttle operations and adjust performance parameters such as caching, buffering, and background maintenance schedules to maintain optimal performance while keeping the temperature within safe limits.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the data storage device operates at high performance, then productivity is improved, but temperature increases and power consumption increases

Engineering Contradiction:

Improvedata storage performanceVSAvoiddevice temperature

Core Design Contradiction:

ProductivityVSTemperature

Solution Approach 1:

The patent implements dynamic thermal management by continuously monitoring temperature and adjusting operational parameters in real-time. The system transitions between different performance states (high performance, reduced performance, power-saving mode) based on thermal conditions, allowing the device to adapt its productivity-temperature tradeoff dynamically rather than operating at a fixed performance level

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system employs periodic background maintenance operations (garbage collection, wear leveling) that are scheduled to occur during periods when thermal constraints allow. These maintenance tasks are interrupted or delayed when temperature thresholds are exceeded, creating a periodic pattern of maintenance activity that respects thermal limits while still ensuring long-term device health

Inventive Principle:

Principle #19Periodic action

2Productivity

If the data storage device operates at high performance, then productivity is improved, but power consumption increases

Engineering Contradiction:

Improvedata storage performanceVSAvoidpower consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The controller dynamically adjusts power consumption by monitoring both temperature and power usage simultaneously. When either threshold is approached, the system transitions to lower power states, creating a dynamic balance between productivity and energy consumption rather than operating at maximum power continuously

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements feedback control by continuously measuring temperature and power consumption, comparing these measurements against thresholds, and adjusting operational parameters accordingly. This closed-loop control ensures that productivity is maximized within the constraints of thermal and power limits

Inventive Principle:

Principle #23Feedback

3Reliability

If background maintenance operations are performed frequently, then reliability is improved, but temperature increases and productivity decreases

Engineering Contradiction:

Improvestorage reliabilityVSAvoiddevice temperature

Core Design Contradiction:

ReliabilityVSTemperature

Solution Approach 1:

Background maintenance operations such as garbage collection and wear leveling are scheduled to execute periodically during windows of opportunity when thermal conditions permit. The system interrupts these periodic maintenance tasks when temperature thresholds are exceeded, ensuring reliability through regular maintenance while preventing thermal runaway

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

The system performs preliminary thermal assessment before scheduling maintenance operations. By predicting future temperature based on current conditions and planned maintenance tasks, the system can proactively schedule maintenance during periods when thermal headroom exists, preventing temperature excursions before they occur

Inventive Principle:

Principle #10Preliminary action

4Temperature

If the device uses aggressive thermal management, then temperature is controlled, but productivity decreases

Engineering Contradiction:

Improvedevice temperatureVSAvoiddata storage performance

Core Design Contradiction:

TemperatureVSProductivity

Solution Approach 1:

The thermal management system operates dynamically, allowing high performance modes when thermal conditions permit and reducing performance only when necessary. Rather than maintaining a conservative fixed performance level, the system adapts its thermal management aggressiveness based on real-time thermal headroom, maximizing productivity while staying within thermal limits

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11709625B2Optimization of power usage of data storage devices

Publication Date: 2023.07.25 MICRON TECHNOLOGY INC

AI summary

Systems, methods and apparatuses to control power usage of a data storage device. For example, the data storage device has a temperature sensor configured to measure the temperature of the data storage device are provided. A controller of the data storage device determines a set of operating parameters that identify an operating condition of the data storage device. An inference engine of the data storage device determines, using an artificial neural network in the data storage device and based on the set of operating parameters, an operation schedule for a period of time of processing input and output of the data storage device. The operation schedule is configured to optimize a performance of the data storage device in the period of time without the temperature of the data storage device going above a threshold.