ML-Based Storage Version Analysis for Automated Issue Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage system management approaches are labor-intensive and inaccurate in identifying and addressing software version-related issues, particularly in accessing and managing data from storage systems running on outdated software versions.
Innovation Solution
The implementation of machine learning techniques for proactive storage system-based software version analysis, which involves obtaining data from multiple storage systems, applying machine learning algorithms to determine performance issues, grouping data by issue type and software version, and generating outputs for necessary actions, thereby automating the software version update process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional storage system management approaches are used to identify software version-related issues, then manual analysis can be performed, but the process becomes labor-intensive and inaccurate
Solution Approach 1:
The patent replaces manual mechanical analysis with automated machine learning algorithms. The system uses ML models to automatically analyze storage system data, identify software version-related issues, and determine performance problems without human intervention, thereby eliminating labor-intensive processes while maintaining or improving accuracy.
Solution Approach 2:
The system enables self-service by automatically performing issue identification and analysis without requiring manual intervention. The machine learning model autonomously processes storage system data, detects performance issues, and generates insights, allowing the system to serve itself in the analysis process.
2Reliability
If conventional management approaches are used, then existing processes can be maintained, but issue detection becomes inconsistent and inaccurate
Solution Approach 1:
The patent implements a universal machine learning-based analysis system that can detect multiple types of software version-related issues across different storage systems. The same ML model serves multiple detection functions, providing consistent and reliable issue identification across diverse scenarios, thereby improving reliability without proportionally increasing complexity.
3Productivity
If manual analysis methods are used to access storage system data, then data can be retrieved, but the process is inefficient and prone to errors
Solution Approach 1:
The patent replaces manual data access and analysis methods with automated machine learning processes. The system automatically retrieves storage system data, applies ML algorithms for analysis, and generates insights, thereby simultaneously improving both the efficiency of data access and the accuracy of data analysis compared to manual methods.
Data Source
AI summary
Methods, apparatus, and processor-readable storage media for proactive storage system-based software version analysis using machine learning techniques are provided herein. An example computer-implemented method includes obtaining storage system data from multiple storage systems; determining performance issues among the storage systems by applying a machine learning algorithm to the storage system data; automatically grouping the storage system data into a set of groups based on issue type among the determined performance issues; automatically grouping, within the set, the storage system data into subsets based on a software version attributed to the corresponding storage system data; generating an output pertaining to actions to be performed with respect to at least one software version update; and transmitting the output to users of the storage systems which correspond to the storage system data in at least one of the subsets.