Redundant Processing Node Reconfiguration for Fault Tolerance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In complex systems like aerospace and self-driving cars, redundant processing nodes can lead to functional failures if one node outputs an incorrect computation result, posing safety risks due to the lack of effective fault-tolerant designs.
Innovation Solution
A processor architecture with multiple processing nodes and comparators that perform computations in pairs, comparing results to identify errors and output correct results, allowing for dynamic changes in redundant processing nodes to ensure fault tolerance and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a large number of processing nodes are used to implement distributed parallel operations, then productivity is improved, but reliability deteriorates due to increased risk of functional failure
Solution Approach 1:
The system segments processing nodes into working nodes and redundant nodes, with each node performing specific computations. Comparators are introduced to segment the verification function, allowing individual node failures to be detected and isolated without affecting the entire system.
Solution Approach 2:
Redundant processing nodes are pre-configured to perform the same computations as working nodes. Comparators are beforehand prepared to compare results and detect errors before they propagate through the system, providing a cushion against potential failures.
2Reliability
If hardware redundant processing nodes are implemented, then reliability is improved through fault tolerance, but device complexity increases
Solution Approach 1:
Processing nodes are designed with universal functionality to perform both working computations and redundant verification computations. This multi-functionality reduces the need for entirely separate redundant hardware, thereby reducing overall device complexity while maintaining fault tolerance.
Solution Approach 2:
Instead of creating fully independent redundant hardware systems, the patent uses computational copying where redundant nodes execute the same algorithms and operations as working nodes. This software-based copying approach reduces hardware complexity compared to full hardware redundancy.
3Reliability
If static redundant processing nodes are used, then reliability is improved through error detection, but adaptability deteriorates due to inability to handle dynamic failures
Solution Approach 1:
The system dynamically assigns roles between working nodes and redundant nodes based on real-time performance and health status. When a node fails, the system can dynamically reconfigure which nodes perform working computations and which perform redundant verification, allowing the redundancy configuration to adapt to changing system conditions.
Data Source
AI summary
A processor capable of changing redundant processing node comprises a plurality of processing nodes and a plurality of comparators. The plurality of processing nodes comprises a first processing node, a second processing node, and a third processing node, wherein the first processing node performs a first computation, the second processing node selectively performs the first computation or a second computation, and the third processing node performs the second computation. The plurality of comparators comprises a first comparator and a second comparator, wherein the first comparator connects to the first and second processing nodes to compare whether the results of the first computation performed by the first and second processing nodes are identical, and the second comparator connects to the second and third processing nodes to compare whether results of the second computation performed by the second and third processing nodes are identical.