Edge Data Filtering for Memory Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large institutions face strain on computing resources due to vast data processing, leading to overloading of edge and platform-layer data channels, necessitating improved data management and utilization without excessive resource expenditure.
Innovation Solution
Implementing a method using a front-end filter to analyze datasets, identify and subtract deprioritized data points, thereby generating a trimmed dataset that optimizes memory and storage capacity by intelligently utilizing network resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is retained in edge layer to maintain meticulous record keeping, then data completeness is improved, but memory capacity and data channel utilization deteriorate
Solution Approach 1:
The patent segments data into different priority levels (prioritized data points vs. deprioritized data points) based on analysis by a front-end filter. This segmentation allows the system to retain only the most important data in the edge layer while discarding less critical data, thus maintaining data completeness for essential records while freeing up memory capacity.
Solution Approach 2:
The patent applies local quality by treating different data points differently based on their priority. Instead of uniformly retaining all data, the system selectively retains only prioritized data points in the edge layer while allowing deprioritized data to be discarded. This localized differentiation optimizes memory usage while maintaining necessary data completeness.
2Productivity
If data is transferred to platform layer for processing, then data processing capability is improved, but data channel bandwidth utilization deteriorates
Solution Approach 1:
The patent extracts only the essential prioritized data points from the complete dataset before transferring to the platform layer. The front-end filter analyzes and separates prioritized data from deprioritized data, transferring only the necessary portion. This extraction approach maintains data processing capability while significantly reducing data channel bandwidth consumption.
3Reliability
If excess memory capacity is maintained in edge layer to prevent overload, then system reliability is improved, but resource utilization deteriorates
Solution Approach 1:
The patent implements a dynamic data retention strategy where the edge layer adapts its memory usage based on data priority analysis. Instead of statically allocating excess memory capacity, the system dynamically determines which data points to retain (prioritized) and which to discard (deprioritized). This dynamic approach maintains system reliability by ensuring essential data is always available while optimizing resource utilization by freeing memory for non-essential data.
Data Source
AI summary
There is provided a method for increasing available memory in an edge layer of a network, where the network stores data and has a default retention period for datasets. The method may include the steps of: (a) receiving the dataset by the edge layer of the network; (b) analyzing the dataset by the front-end filter to identify disposable data points in the dataset, (c) instructing a computer processor to remove the disposable data points from the dataset, upon passage of a specified time interval.