Storage Reliability Prediction Using Deterioration-Phase ML Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the reliability of nonvolatile storage devices do not adequately consider the degree of deterioration, leading to reduced accuracy in reliability information prediction.
Innovation Solution
A method that involves selecting an optimal machine learning model based on deterioration characteristic and phase information to generate reliability information, using a model request signal to adaptively retrieve parameters from volatile memories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single machine learning model is used for reliability prediction without considering deterioration phase, then the prediction process is simple, but the reliability of result data is lowered
Solution Approach 1:
The patent segments the reliability prediction process by dividing it into multiple deterioration phases (early, middle, late) and selecting different machine learning models for each phase. This segmentation allows the system to use phase-appropriate models, improving prediction reliability while managing complexity through structured organization.
Solution Approach 2:
The patent implements a dynamic model selection mechanism that adapts the machine learning model based on the current deterioration phase of the storage device. The system dynamically determines which phase the device is in and selects the corresponding optimal model, making the prediction process adaptive rather than static.
2Reliability
If multiple machine learning models are selected based on deterioration phase, then the reliability of result data is improved, but the device complexity increases
Solution Approach 1:
The patent performs preliminary determination of the deterioration phase before selecting the machine learning model. By first assessing which phase the storage device is in (early, middle, or late deterioration), the system prepares the appropriate model in advance, streamlining the selection process and reducing operational complexity.
Solution Approach 2:
The patent changes the parameter of model selection based on the deterioration phase parameter. Different machine learning models are designated for different phases (e.g., first model for early phase, second model for middle phase, third model for late phase), allowing the system to optimize prediction accuracy for each phase while maintaining a manageable complexity through parameter-based selection.
Data Source
AI summary
In a method of operating a storage device including a plurality of nonvolatile memories, reliability information of the storage device is predicted. A read operation on the storage device is performed based on a result of predicting the reliability information. In the predicting the reliability information of the storage device, a model request signal is outputted by selecting one of a plurality of machine learning models as an optimal machine learning model based on deterioration characteristic information and deterioration phase information. The model request signal corresponds to the optimal machine learning model. The plurality of machine learning models are used to generate first reliability information related to the plurality of nonvolatile memories. First parameters of the optimal machine learning model may be received based on the model request signal. The first reliability information is generated based on the deterioration characteristic information and the first parameters.