Time-Series Analysis Using Section-Specific Approximation Degrees
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In time-series analysis, existing methods fail to consistently achieve sufficient speed-up of calculations while maintaining acceptable error levels, as the appropriateness of approximation calculation intensity varies across different periods.
Innovation Solution
A method that selects sections of time steps and applies varying degrees of approximation calculation, calculating errors and speed-up indices to identify optimal combinations that balance error and speed-up, storing these for subsequent data sets to ensure both efficient analysis and controlled error levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If approximation calculation is applied to speed up time-series analysis, then calculation speed is improved, but error increases
Solution Approach 1:
The time-series analysis is divided into multiple sections, and different approximation calculation application degrees are applied to different sections. This segmentation allows the system to optimize for speed in some sections while maintaining higher accuracy in others, resolving the contradiction between calculation speed and error level.
Solution Approach 2:
The approximation calculation application degree is dynamically adjusted based on the section being processed. By varying the application degree across different sections rather than using a fixed degree throughout, the system can adaptively balance speed and accuracy requirements.
2Device complexity
If a single approximation calculation application degree is used throughout the analysis, then device complexity is reduced, but the ability to optimize for different sections is lost
Solution Approach 1:
The analysis period is segmented into multiple sections, each capable of having different approximation calculation application degrees. This segmentation enables section-specific optimization while keeping the overall control mechanism relatively simple through automated selection.
Solution Approach 2:
The system automatically selects appropriate approximation calculation application degrees for each section based on predetermined criteria, eliminating the need for complex manual configuration. The system serves itself by making optimal decisions without requiring complex external control.
3Ease of operation
If approximation calculation is applied uniformly across all sections, then ease of operation is improved, but overall speed-up performance is insufficient
Solution Approach 1:
The system dynamically adjusts the approximation calculation application degree for different sections automatically. This dynamic adjustment provides both simplicity of operation (automatic selection) and improved overall speed-up (optimized per-section settings).
Solution Approach 2:
The approximation calculation application degree parameter is changed across different sections to optimize performance. By varying this parameter section-by-section, the system achieves better overall speed-up while maintaining ease of operation through automated parameter selection.
Data Source
AI summary
A non-transitory computer-readable storage medium storing a program that causes a processor to execute a process. The process includes selecting a section from among a plurality of sections, performing on an input data group the time-series analysis from a top section to the section when each of a plurality of approximation application degrees is set in the section, based on a result of the performing, for each of the plurality of approximation application degrees is set, calculating an error and an index value for a result of the time-series analysis when an approximation calculation is not applied, the index value indicating a degree of speed-up, storing an approximation application degree in which the error falls within a range, and the index value obtained when the error falls within the range, and executing the time-series analysis on an another input data group by applying a combination of the approximation application degrees.