Machine Learning Storage Sizing Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional sizing approaches for storage components require manual human involvement and often result in inaccurate determinations, leading to increased support costs and decreased user satisfaction.
Innovation Solution
The implementation of machine learning techniques, including deep learning and k-nearest neighbors algorithms, to automatically determine storage component sizing configurations based on dynamically obtained storage system data, eliminating the need for manual input and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual human involvement is used for sizing storage components, then expertise and tradeoff analysis are applied, but accuracy of sizing determination deteriorates and support costs increase
Solution Approach 1:
The system performs self-service by automatically determining storage component sizing configurations using machine learning models without requiring manual human involvement. The ML models process workload characteristics and storage system parameters to generate sizing recommendations autonomously, eliminating the need for expert human analysts while improving accuracy through consistent algorithmic application.
Solution Approach 2:
The patent replaces the mechanical system of manual human analysis with an automated computational system based on machine learning. The ML models substitute human expertise by learning patterns from historical data and applying them to new sizing problems, transforming a human-dependent process into an automated algorithmic system that scales without additional human resources.
2Productivity
If manual sizing approaches are used, then human expertise is utilized, but productivity and automation level deteriorate
Solution Approach 1:
The system performs preliminary action by pre-training machine learning models on historical storage workload data and configuration outcomes before actual sizing is needed. This pre-computed knowledge enables rapid automated sizing decisions without requiring manual intervention during the actual sizing process, thereby increasing productivity while maintaining ease of operation through simple model inference.
3Reliability
If inaccurate sizing determinations occur, then manual errors are introduced, but support costs increase and user satisfaction decreases
Solution Approach 1:
The system implements feedback by using historical data on actual storage performance and configuration outcomes to continuously improve the machine learning models. The models learn from past sizing decisions and their real-world performance, adjusting their parameters to reduce errors and improve accuracy over time, thereby increasing reliability and user satisfaction through progressively better sizing recommendations.
Data Source
AI summary
Methods, apparatus, and processor-readable storage media for automatically determining sizing configurations for storage components using machine learning techniques are provided herein. An example computer-implemented method includes obtaining multiple items of input related to at least one storage component; determining a set of storage component sizing configurations by processing at least a portion of the multiple items of input using a first set of one or more machine learning techniques comprising at least one deep learning technique; identifying a subset of the storage component sizing configurations by processing at least a portion of the determined set of storage component sizing configurations using a second set of one or more machine learning techniques; and performing one or more automated actions based at least in part on the identified subset of storage component sizing configurations.