Storage Expansion Disk Provisioning Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the context of 'storage as a service' (STaaS) models, providers face challenges in determining the optimal number of extra disks to include with storage devices to minimize expansion logistics costs, as these disks may remain unutilized if customers do not expand their storage capacity, leading to inefficiencies and increased costs.
Innovation Solution
A data-driven approach utilizing customer historical storage usage and purchase history, combined with machine learning models to predict storage expansion requests, determines the optimal number of extra disks to include, considering costs such as the monthly cost of orphan disks and fulfillment costs, thereby minimizing disk shipment costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If extra disks are included with the storage device to enable future expansion, then the probability of meeting customer storage needs is improved, but the cost of including unused disks increases
Solution Approach 1:
The system performs preliminary analysis of customer historical storage usage and purchase history before production to predict future storage expansion needs. This allows extra disks to be pre-selected and pre-configured based on predicted demand, ensuring expansion capability is ready when needed while avoiding inclusion of disks that won't be used.
Solution Approach 2:
The system dynamically adjusts the number of extra disks based on multiple parameters including historical usage patterns, purchase history, predicted expansion probability, and cost considerations. By changing these parameters in the prediction model, the system optimizes the balance between having sufficient extra disks for expansion and minimizing costs of unused disks.
2Measurement precision
If machine learning models are used to predict storage expansion requests, then the precision of extra disk provisioning is improved, but the complexity of the system increases
Solution Approach 1:
The system implements feedback mechanisms where actual customer storage usage and expansion behavior are continuously monitored and fed back into the machine learning models. This feedback loop allows the models to learn from real outcomes and improve prediction accuracy over time, justifying the initial complexity increase through continuous refinement and validation.
Solution Approach 2:
The prediction system is segmented into multiple independent machine learning models that analyze different aspects of customer behavior (storage usage patterns, purchase history, expansion timing). Each model focuses on specific prediction tasks, making the overall complex system manageable through modular design and enabling targeted optimization of each component.
Data Source
AI summary
A system can determine to produce a storage device for a user identity indicative of a user. The system can determine a number of extra disks to include with the storage device as part of the production, the extra disks enabling further storage capacity for the storage device beyond a specified storage capacity, the determining of the number of extra disks being based on data from a group of data, the group of data comprising first cost data representative of a first cost associated with including the second number of extra disks, probability data representative of a probability that the further storage capacity beyond the specified storage capacity will be requested during a defined time period after the production, and second cost data representative of a second cost associated with installing the second number of extra disks after the storage device has been delivered to the user site.