Centralized Recovery Manager for Reconfigurable Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Reconfigurable devices in harsh environments, such as space, are prone to upsets like single event upsets (SEU), single event functional interrupts (SEFI), and multiple bit upsets (MBU) due to radiation effects, which can corrupt their functional performance and require effective mitigation strategies to ensure continuous operation with minimal external intervention.
Innovation Solution
A centralized program/recovery manager (CPRM) is coupled with reconfigurable devices to monitor for upsets, reset, scrub, or reprogram them as needed, using a memory module to store configuration information and communicate with reconfigurable devices through a shared upset status bus and data transfer interface, enabling proactive mitigation of device upsets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If reconfigurable devices are used in harsh environments, then adaptability and functionality are improved, but reliability deteriorates due to radiation-induced upsets
Solution Approach 1:
The system performs preliminary actions by periodically monitoring reconfigurable devices for upsets before they cause functional failure. The CPRM detects configuration upsets in advance and initiates recovery procedures (reset, reconfiguration, or reprogramming) to maintain operational reliability while preserving the adaptability of reconfigurable devices in harsh environments.
2Reliability
If traditional mitigation methods are used to protect against upsets, then reliability is improved, but device complexity and cost increase
Solution Approach 1:
The CPRM acts as an intermediary between reconfigurable devices and the external environment. It centralizes the monitoring and recovery functions, simplifying the overall system architecture by consolidating upset detection and mitigation logic in a single management unit rather than requiring complex redundant hardware or software in each device.
Solution Approach 2:
The system enables self-service by allowing the CPRM to automatically detect upsets and perform recovery operations (reset, reconfiguration, or reprogramming) without external intervention. This autonomous operation reduces the need for complex external control systems and minimizes operational overhead.
3Duration of action of stationary object
If reconfigurable devices are monitored and recovered automatically, then operational continuity is improved, but use of energy increases
Solution Approach 1:
The system implements periodic monitoring instead of continuous monitoring, where the CPRM checks reconfigurable devices at regular intervals for configuration upsets. This periodic approach maintains operational continuity by detecting and recovering from upsets while reducing energy consumption compared to constant monitoring and verification processes.
Data Source
AI summary
Methods, systems, and devices for configuration and upset recovery of reconfigurable devices are provided. A central program/recovery manager (CPRM) is coupled with each of a number of reconfigurable devices. The reconfigurable devices are programmed/configured by the CPRM, which then periodically monitors each of the reconfigurable devices to detect if one or more of the devices has experienced an upset. In the event of an upset, the CPRM may attempt to reset the reconfigurable device, scrub a memory of the reconfigurable device, or reprogram the reconfigurable device. A memory module is coupled with the CPRM and each of the reconfigurable devices that stores bit or programming files that may be used to program and/or reprogram the reconfigurable devices.