SSD Unpowered Retention Forecasting via RBER Extrapolation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Solid state drives (SSDs) using NAND flash memory, particularly those with quad-level cell (QLC) technology, face challenges in data retention when unpowered, leading to potential data loss due to increased bit error rates over time, making it difficult for error correction processes to maintain data integrity during extended power-down periods.

Innovation Solution

A method is developed to determine a scaling factor and retention time power law coefficient by curve fitting raw bit error rate values, allowing for the extrapolation of the time at which a SSD would reach a maximum raw bit error rate if left unpowered, enabling the prediction of safe unpowered data retention periods and preventing data loss by powering the SSD before errors become uncorrectable.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If QLC NAND flash memory is used to increase storage capacity, then storage density is improved, but data retention reliability deteriorates when unpowered

Engineering Contradiction:

Improvestorage densityVSAvoiddata retention reliability

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system performs preliminary characterization of raw bit error rate (RBER) at multiple time points before actual data loss occurs. By establishing the RBER progression curve in advance through power cycle testing, the system can predict future data retention behavior and issue warnings before errors become uncorrectable, enabling proactive data protection measures.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements a feedback mechanism where RBER measurements from powered and unpowered states are continuously monitored and fed back to update the retention time prediction. This feedback loop allows the system to adjust predictions based on actual observed error rates and provide real-time status information to users about data integrity risks.

Inventive Principle:

Principle #23Feedback

2Ease of operation

If extended power-down periods are allowed to improve operational flexibility, then ease of operation is improved, but data integrity deteriorates due to increased bit error rates

Engineering Contradiction:

Improveoperational flexibilityVSAvoiddata integrity

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The SSD performs self-characterization by automatically conducting RBER measurements at multiple time points during normal operation. The drive independently builds its own retention profile without requiring external testing equipment, storing this characterization data for future prediction use. This self-service approach enables the drive to autonomously monitor and report its own data retention status.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces physical long-term storage testing with mathematical modeling and extrapolation. Instead of physically leaving the drive unpowered for extended periods to test retention, the system uses RBER progression curves and power law models to calculate predicted retention times, substituting computational analysis for physical experimentation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Device complexity

If traditional fixed retention time specifications are used to simplify product specifications, then device complexity is reduced, but measurement precision deteriorates for individual drive predictions

Engineering Contradiction:

Improveproduct specification complexityVSAvoidretention time prediction accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system transitions from using a single fixed retention time parameter to a dynamic prediction model that incorporates multiple parameters: initial RBER, RBER at different time points, scaling factors, and power law coefficients. By changing from a static specification to a multi-parameter predictive approach, the system achieves higher precision for individual drive predictions while maintaining practical usability through standardized characterization procedures.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11972120B2System and method of forecasting an amount of time a solid state drive can be unpowered

Publication Date: 2024.04.30 DELL PROD LP

AI summary

In one or more embodiments, one or more systems, one or more methods, and/or one or more processes may receive a scaling factor and a retention time power law coefficient associated with a solid state drive (SSD); determine a first raw bit error rate (RBER) value for the SSD at a first time; extrapolate a second time at which a second RBER value for the SSD would reach a maximum RBER value if left unpowered, based at least on the first raw bit error rate value, the scaling factor, and the retention time power law coefficient; and provide the second time at which the second RBER value for the SSD would reach the maximum raw bit error rate value if left unpowered to at least one of an information handling system (IHS), IHS firmware, a baseboard management controller of the IHS, and an application executing on the IHS.