Host-Storage Power Shutdown Prediction via Statistical Event Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data storage systems lack an effective method to predict and prepare for imminent power shutdowns, leading to potential data loss and increased recovery times due to the lack of early notification and preparatory actions.

Innovation Solution

A method and system where a host detects statistically indicative events of an imminent power shutdown and sends a notification to the storage device to initiate preparatory actions, such as committing data to non-volatile memory and completing unfinished operations, allowing for a longer preparation period and improved storage performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the storage device waits for deterministic power shutdown signals, then power management is simple, but data loss occurs and recovery time increases

Engineering Contradiction:

Improvedata integrityVSAvoidrecovery time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The host system performs preliminary actions by detecting statistical indicators of imminent power shutdown (such as user inactivity, system state patterns) and sends advance notifications to the storage device before actual power failure occurs. This allows the storage device to complete pending operations and commit data to non-volatile memory in advance, reducing both data loss and recovery time.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If the host sends early notification of power shutdown, then preparatory actions can be taken, but false alarms may occur

Engineering Contradiction:

Improvepower shutdown prediction accuracyVSAvoidevent detection system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The host system implements feedback mechanisms by continuously monitoring system state indicators and adjusting its prediction behavior based on actual power shutdown patterns. The storage device also provides feedback about its operational state and data commitment status, allowing the host to refine its prediction algorithms and reduce false alarms over time.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system changes parameters by using multiple statistical indicators (user activity levels, system state patterns, time-based thresholds) rather than relying on a single deterministic signal. This multi-parameter approach improves prediction accuracy while managing the complexity of the detection system through standardized threshold-based decision making.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If the storage device performs complex preparatory actions, then data safety is improved, but power consumption increases

Engineering Contradiction:

Improvedata safetyVSAvoidpower consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The storage device performs partial preparatory actions by committing only the most critical data to non-volatile memory based on the predicted shutdown timeline and data priority levels. Not all data requires the same level of protection, so the system performs selective data commitment rather than exhaustive data protection, reducing power consumption while maintaining adequate data safety.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS9547574B2Power shutdown prediction for non-volatile storage devices

Publication Date: 2017.01.17 APPLE INC

AI summary

A method includes, in a host that stores data in a storage device, detecting an event that is indicative, statistically and not deterministically, of an imminent power shutdown in the host. A notification is sent to the storage device responsively to the detected event, so as to cause the storage device to initiate preparatory action for the imminent power shutdown.