Parallel Distributed Processing Control System for Production Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing production distribution planning techniques face inefficiencies due to order dependency relationships between divided models, reducing the expected improved efficiency from model division.
Innovation Solution
A parallel distributed processing control system that includes a storage unit, divided model generation, CPU allocation, engine execution, constraint monitoring, and output information generation units, ensuring equalized processing loads across CPUs to enhance production distribution planning efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the plan creation period is divided into multiple models for parallel calculation, then calculation speed should improve, but order dependency relationships between divided models reduce the expected efficiency improvement
Solution Approach 1:
The production distribution plan is divided into multiple divided models, each handling specific steps or time periods. This segmentation enables parallel calculation across multiple CPUs while maintaining manageable model sizes. The system groups steps into different divided models that can be processed independently or with minimized dependencies.
Solution Approach 2:
A constraint management mechanism acts as an intermediary between divided models to coordinate calculations and manage dependencies. The system identifies and manages constraint relationships between divided models, allowing parallel processing while ensuring consistency across model boundaries through centralized constraint handling.
2Productivity
If multiple CPUs are used for parallel calculation, then calculation efficiency improves, but unequal processing loads across CPUs reduce overall efficiency
Solution Approach 1:
The CPU allocation is dynamically adjusted based on processing load measurements. The system monitors the execution time and load of each CPU, then reallocates divided models to balance the workload. This dynamic adjustment ensures that faster CPUs handle more complex models while slower CPUs handle simpler ones, optimizing overall parallel processing efficiency.
Solution Approach 2:
The system implements feedback mechanisms where calculation results and processing times from each CPU are monitored and used to adjust subsequent task allocation. This feedback loop enables continuous optimization of load distribution across CPUs, ensuring that processing capacity is efficiently utilized without creating bottlenecks.
3Loss of time
If divided models are calculated in parallel, then planning time is reduced, but constraint satisfaction becomes more difficult to ensure
Solution Approach 1:
A centralized constraint management mechanism serves as an intermediary that coordinates between parallel divided model calculations. This mechanism identifies constraint relationships between divided models and ensures that constraint satisfaction is maintained across model boundaries, allowing parallel processing while guaranteeing reliability.
Solution Approach 2:
Constraints are extracted and managed separately from the main calculation process. The system identifies constraint relationships and handles them through dedicated mechanisms that operate independently from the parallel calculation flow, ensuring that constraint satisfaction is not compromised by parallel processing.
Data Source
AI summary
A parallel distributed processing control system used in production distribution planning includes: a storage unit storing step information of steps constituting a production distribution process of a product, CPU information of CPUs that calculate a value of a simulation result for the step, and a constraint value in the production distribution process; a divided model generation unit generating a divided model by grouping the steps; a CPU allocation unit allocating the divided model to the plurality of CPUs; an engine execution unit enabling the CPU to calculate the value for the step constituting the divided model; and a constraint monitoring unit determining whether the value satisfies a condition specified by the constraint value. An output information generation unit generates result information using the value satisfying the condition; and the CPU allocation unit allocates the divided model so that processing loads of the plurality of CPUs are equalized.