File System Utilization Prediction with Pattern-Based Capacity Reconfiguration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing file system resources in data centers is complex due to varying utilization patterns across directories, leading to inefficient resource allocation and potential application malfunctions, while existing machine learning techniques are computationally expensive and inadequate for precise prediction.
Innovation Solution
Implement a trained classification model to categorize file system usage data into trend and periodicity categories, using anomaly detection to adjust file system resources dynamically based on predicted thresholds and anomalies, with periodic adjustments for improved efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning techniques are used to predict file system utilization, then prediction accuracy is improved, but computational cost increases
Solution Approach 1:
The patent segments the file system into multiple directories and classifies each directory's usage pattern independently into categories (trend, periodicity, or anomaly). This segmentation allows the system to apply different prediction techniques to different parts of the file system, reducing overall computational cost while maintaining prediction accuracy for each segment.
Solution Approach 2:
The patent applies different analysis methods to different directories based on their specific usage patterns. Directories with trend patterns receive time series analysis, periodicity patterns receive periodic analysis, and anomaly patterns trigger alerts. This local quality approach ensures that computational resources are allocated efficiently based on the specific characteristics of each directory rather than applying a uniform expensive machine learning model to all directories.
2Reliability
If manual monitoring and clean-up activities are performed, then file system space is managed, but operational complexity increases
Solution Approach 1:
The patent implements a self-service monitoring system that automatically classifies directory usage patterns, predicts future utilization, and triggers appropriate responses without requiring manual intervention. The system self-manages file system space by identifying trends and anomalies, eliminating the need for complex manual monitoring processes while maintaining reliable space management.
Solution Approach 2:
The patent establishes a feedback loop where directory usage data is continuously collected, classified into patterns, and used to predict future utilization. The system automatically adjusts based on predicted trends, creating a closed-loop feedback mechanism that simplifies operational complexity while ensuring reliable file system space management through automated decision-making.
Data Source
AI summary
A trained classification model is executed, causing a classification of a first set of file system usage data into a set of categories comprising a trend category and a periodicity category. Responsive to the first set of file system usage data being classified into the trend category, a time series of the first set of file system usage data is generated. Responsive to the first set of file system usage data being classified into the periodicity category, using an anomaly detection model, an anomaly within the first set of file system usage data is detected. Responsive to predicting that the time series will exceed a threshold, a first reconfiguring of a file system resource is caused, altering a capacity of the file system. Responsive to detecting the anomaly, a second reconfiguring of the file system resource is caused, altering a capacity of the file system.