Adaptive Memory Refresh for Non-Volatile Storage in Embedded Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory units in embedded systems, especially in vehicles, face data loss due to high temperatures, leading to potential system failures, as conventional refresh methods are inadequate and often performed at insufficient intervals.
Innovation Solution
A method that checks for refresh-triggering criteria at specifiable intervals, independently of the system's operating mode, to determine the necessity and optimal timing for memory refresh, considering factors like temperature, memory type, and error correction, ensuring frequent refreshes in high-risk conditions to prevent data loss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If refresh is performed at fixed time intervals regardless of operating mode, then memory content is maintained, but system energy consumption increases and refresh may be performed unnecessarily frequently
Solution Approach 1:
The refresh interval is made dynamic by adjusting it based on the operating mode. The system transitions from fixed-time refreshing to adaptive refreshing where the interval varies according to operational conditions, allowing longer intervals during low-risk modes and shorter intervals during high-risk modes
Solution Approach 2:
The refresh interval parameter is changed based on operating mode. The system monitors operating conditions and adjusts the time interval between refreshes accordingly, extending the interval when risk is low and reducing it when risk increases, thereby optimizing energy consumption while maintaining reliability
2Use of energy by moving object
If refresh interval is extended to save energy, then energy consumption decreases, but memory content may be lost at high temperatures
Solution Approach 1:
The system implements feedback by monitoring operating conditions (particularly temperature) and using this information to adjust the refresh interval. When temperature exceeds a threshold or other risk conditions are detected, the system shortens the refresh interval to prevent data loss, otherwise it extends the interval to save energy
Solution Approach 2:
The system performs self-assessment of its operating conditions and automatically adjusts its refresh strategy without external intervention. It monitors its own temperature and operational state, then autonomously modifies the refresh interval to balance energy consumption and data retention needs
3Reliability
If refresh is performed frequently to prevent data loss, then memory content is maintained, but system productivity decreases due to more frequent interruptions
Solution Approach 1:
The refresh frequency is made dynamic rather than fixed. The system adjusts the interval between refreshes based on real-time operating conditions, performing refreshes more frequently only when necessary (high temperature, critical operations) and less frequently during normal conditions, thereby maintaining reliability while minimizing productivity impact
4Reliability
If refresh-triggering criterion check is performed continuously, then data loss is prevented, but system complexity and energy consumption increase
Solution Approach 1:
Instead of continuous monitoring, the system performs periodic checks of the refresh-triggering criterion at specified time intervals. This approach maintains adequate monitoring for data loss prevention while significantly reducing system complexity and energy consumption compared to continuous assessment
Solution Approach 2:
The system performs partial monitoring by checking only the essential refresh-triggering criteria at periodic intervals rather than continuously monitoring all possible parameters. This provides sufficient protection against data loss while keeping the system simple and energy-efficient
Data Source
AI summary
A method for carrying out a refresh of a memory area of a non-volatile memory unit of an embedded system includes refreshing the memory area when a refresh-triggering criterion is satisfied, a check being performed at predefined time intervals to determine whether the refresh-triggering criterion is satisfied, the embedded system being automatically activated and the check being performed if the embedded system is deactivated following the expiration of any of the predefined time intervals.