Storage System Malfunction Detection Using Machine Learning Bitmap Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage systems lack an automated mechanism to quickly detect malfunctions, requiring extensive manual analysis of large amounts of unstructured data, which is time-consuming and inefficient, and often necessitates a large customer support staff to identify faulty components and resolve issues.
Innovation Solution
A method that creates a bitmap image from data gathered from storage system operations, training a machine learning system to visually represent components and detect malfunctions, allowing for rapid identification of faulty components and their severity within the storage system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of storage system data is used, then comprehensive inspection of system operations is achieved, but time consumption and labor requirements increase significantly
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated machine learning system that processes storage system data. The system uses trained models to automatically detect malfunctions, identify faulty components, and determine their severity without human intervention, thereby eliminating time-consuming manual analysis while maintaining or improving detection accuracy.
Solution Approach 2:
The machine learning system performs self-service by automatically analyzing storage system operations, detecting anomalies, and identifying problems without requiring external human analysis. The system independently processes data, applies trained detection algorithms, and generates diagnostic results, enabling the storage system to monitor and diagnose its own health status autonomously.
2Reliability
If extensive manual analysis is performed to identify faulty components, then comprehensive fault detection is achieved, but customer support staff requirements increase
Solution Approach 1:
The patent replaces the mechanical system of human support staff analysis with an automated machine learning-based diagnostic system. The machine learning models perform comprehensive fault detection, component identification, and severity assessment automatically, eliminating the need for extensive customer support teams while maintaining high reliability in fault detection.
Solution Approach 2:
The storage system performs self-diagnosis through the machine learning system, which automatically monitors operations, detects malfunctions, identifies faulty components, and determines their severity. This self-service capability eliminates the need for external human support staff to perform routine diagnostic tasks, simplifying the support structure while maintaining comprehensive fault detection.
3Productivity
If automated machine learning analysis is implemented, then analysis speed and automation are improved, but system complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models using historical storage system data and known malfunction patterns. These pre-trained models are then deployed to automatically analyze real-time operations, enabling rapid detection and identification without requiring complex real-time decision-making logic. The preliminary training phase captures complex patterns, simplifying the runtime analysis architecture.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between raw storage system data and diagnostic conclusions. The model acts as a mediator that automatically processes operational data, applies learned detection rules, and generates interpreted results about malfunctions and faulty components. This intermediary layer simplifies the overall system architecture by encapsulating complex analysis logic within the trained model rather than requiring complex procedural code.
Data Source
AI summary
A method is used in analyzing a storage system using a machine learning system. Data gathered from information associated with operations performed in a storage system is analyzed. The storage system is comprised of a plurality of components. A bitmap image is created based on the gathered data, where at least one of the plurality of components is represented in the bitmap image. The machine learning system is trained using the bitmap image, where the bitmap image is organized to depict the plurality of components of the storage system.