Pipeline Node Time Allocation for Reception Queue Overflow Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The data collection and analysis system in factory automation (FA) requires high performance to handle enormous data and needs to be configured to allow users to freely determine data collection targets and processing methods, while preventing overflow of reception queues.
Innovation Solution
A pipeline computing apparatus with a computing unit composed of nodes connected via reception queues and a control unit that includes a node monitoring unit, a queue monitoring unit, a priority variable calculating unit, and a time allocating unit. This apparatus calculates a priority variable based on node processing time and accumulated message amounts to dynamically allocate operating time to each node.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If pipeline processing is used to handle enormous data in factory automation, then data processing capability is improved, but reception queue overflow occurs
Solution Approach 1:
The patent implements dynamic priority adjustment where the priority of each node is not fixed but changes based on real-time queue lengths. The control unit continuously monitors the length of reception queues and adjusts node priorities dynamically, allowing the system to adapt to varying data loads and prevent queue overflow while maintaining high processing capability.
Solution Approach 2:
The patent employs feedback control by having the control unit continuously monitor the length of reception queues and use this information to adjust node priorities. This closed-loop feedback mechanism ensures that when queues become long, priorities are adjusted to prevent overflow, while when queues are short, processing efficiency is maintained.
2Productivity
If node processing speed is increased to handle more data, then productivity is improved, but queue overflow risk increases
Solution Approach 1:
The patent makes node processing speed dynamic by adjusting the priority of each node based on real-time queue conditions. When a reception queue becomes long, the control unit increases the priority of nodes that process data from that queue, thereby increasing their processing speed. This dynamic adjustment allows the system to handle high data volumes without overflowing queues.
3Ease of operation
If fixed priority is assigned to nodes for simple control, then ease of operation is improved, but processing efficiency deteriorates
Solution Approach 1:
The patent implements a self-adjusting system where nodes automatically have their priorities adjusted by the control unit based on queue conditions. This eliminates the need for manual priority configuration while maintaining operational simplicity, as the system self-optimizes its processing efficiency based on real-time data without requiring complex user intervention.
4Productivity
If dynamic priority adjustment is implemented to improve processing efficiency, then productivity is improved, but system complexity increases
Solution Approach 1:
The patent uses feedback control to manage system complexity. The control unit monitors queue lengths and automatically adjusts node priorities based on this feedback. This feedback mechanism provides a systematic and automated approach to dynamic priority adjustment, improving processing efficiency without requiring complex manual configuration or intervention.
Solution Approach 2:
The system performs self-adjustment of priorities through the control unit that automatically monitors queue conditions and modifies node priorities accordingly. This self-service capability eliminates the need for external complex control mechanisms, allowing the system to optimize its own performance while maintaining relatively simple architecture.
Data Source
Figure 1
Figure 2(a)~2(b)
Figure 3
AI summary
A pipeline computing apparatus (110) comprises: a computing unit (120) configured as a pipeline; a node monitoring unit (161) that obtains a node processing time; a queue monitoring unit (162) that obtains an accumulated message amount; a priority variable calculating unit (163) that, on the basis of the node processing time and the accumulated message amount in a reception queue in a stage previous to the node, calculates a priority variable of the node; and a time allocating unit (164) that allocates operating time to each of nodes in accordance with the priority variable.