Data Transfer Optimization via Load-Based Candidate Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In distributed data accumulation systems, determining the optimal data items to transfer, transfer destination servers, and data group sizes to maximize throughput is computationally intensive, especially with a large number of servers and data items, leading to increased calculation complexity and potential congestion.
Innovation Solution
A method where an information processing apparatus selects candidate data items and transfer destination servers based on load status and throughput, determining the data to be transferred and data group sizes to satisfy deadlines while optimizing throughput, by narrowing down the number of data items and servers considered for calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the optimal data item to be transferred, the optimal transfer destination server, and the optimal data group size at the time of the transfer are determined based on throughput, then the throughput is maximized, but the amount of calculation increases depending on the number of servers and the number of data items
Solution Approach 1:
The patent segments the data transfer optimization process into distinct phases: first selecting candidate data items based on simple load status criteria, then selecting candidate destination servers based on load statuses, and finally determining optimal transfer parameters only for these narrowed-down candidates using throughput calculations. This segmentation reduces the computational scope from all possible data items and servers to only the most promising candidates.
Solution Approach 2:
The patent performs preliminary filtering of data items and destination servers based on load status before conducting the computationally intensive throughput optimization. By pre-selecting candidate data items that meet load status criteria and candidate destination servers with appropriate load characteristics, the system reduces the search space for the subsequent throughput-based optimization, thereby reducing overall calculation amount while maintaining throughput maximization.
2Productivity
If data transfer optimization considers all servers and data items to maximize throughput, then the throughput is improved, but the system complexity and calculation time increase
Solution Approach 1:
The patent divides the optimization problem into hierarchical segments: (1) candidate data item selection based on load status, (2) candidate destination server selection based on load statuses, and (3) optimal transfer parameter determination based on throughput. This segmentation transforms a single complex optimization problem into multiple simpler sub-problems, reducing system complexity while achieving throughput improvement.
Solution Approach 2:
The patent applies different optimization criteria to different stages of the transfer decision process. Load status criteria are applied locally to filter candidates, while throughput optimization is applied locally to the selected candidates. This local application of different quality criteria reduces overall system complexity by avoiding uniform complex optimization across all possible combinations.
3Device complexity
If the number of candidate data items and candidate destination servers is reduced for calculation, then the amount of calculation is suppressed, but the optimization accuracy may be compromised
Solution Approach 1:
The patent performs preliminary selection of candidate data items and destination servers using load status criteria that identify the most promising candidates for transfer. This preliminary action ensures that the subsequent throughput optimization is applied to the most relevant candidates, maintaining optimization accuracy while reducing the number of calculations needed compared to evaluating all possible combinations.
Solution Approach 2:
The patent uses load status information as feedback to guide the candidate selection process. By continuously monitoring load statuses of servers and using this feedback to identify candidate data items and destination servers, the system ensures that optimization is focused on the most relevant transfers, maintaining accuracy while reducing calculation scope.
Data Source
AI summary
A transfer method is performed by an information processing apparatus. The method includes: selecting, based on a load status of the information processing apparatus, candidate transfer data that is among the received data and to be transferred to one or more other information processing apparatuses; selecting, based on load statuses of multiple other information processing apparatuses, one or more candidate transfer destination apparatuses among the multiple other information processing apparatuses as candidate transfer destinations of the data; determining, based on throughput between the information processing apparatus and the candidate transfer destination apparatuses, data to be transferred among the candidate transfer data, transfer destination apparatuses of the data to be transferred among the candidate transfer destination apparatuses, and the sizes of data groups including the data to be transferred; and transferring, to the transfer destination apparatuses determined for the determined data groups, the determined data to be transferred.