Cloud Storage Usage Prediction via Linear Regression

Solution Overview

Problem

Cloud storage service providers face inefficiencies due to unpredictable storage resource usage, leading to user inconvenience and increased computing costs, as they struggle to balance resource allocation with the need to avoid idle or excessive storage.

Innovation Solution

A method and system using a linear regression model to predict future storage resource usage by monitoring time series datasets, selecting suitable training sets, and updating models to accurately forecast storage needs, thereby optimizing resource allocation and reducing computing costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If storage resources are expanded in advance to prevent user inconvenience, then user service reliability is improved, but resource operation efficiency deteriorates due to excessive idle storage resources

Engineering Contradiction:

Improveuser service reliabilityVSAvoidresource operation efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary action by predicting future storage resource usage trends using linear regression models and time series data analysis. This allows the system to anticipate future storage needs and make proactive capacity adjustments, preventing service failures before they occur while avoiding unnecessary early expansion that would create idle resources.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring actual storage usage against predicted values and adjusting the linear regression models accordingly. This iterative feedback loop enables the system to refine its predictions over time, improving accuracy in forecasting storage needs and optimizing capacity allocation to match actual demand patterns.

Inventive Principle:

Principle #23Feedback

2Productivity

If storage resources are not expanded in advance, then resource operation efficiency is maintained, but user convenience deteriorates when usage suddenly exceeds the limit

Engineering Contradiction:

Improveresource operation efficiencyVSAvoiduser convenience

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system performs preliminary action by predicting future storage resource usage trends using linear regression models and time series data analysis. This allows the system to anticipate future storage needs and make proactive capacity adjustments, preventing service failures before they occur while avoiding unnecessary early expansion that would create idle resources.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring actual storage usage against predicted values and adjusting the linear regression models accordingly. This iterative feedback loop enables the system to refine its predictions over time, improving accuracy in forecasting storage needs and optimizing capacity allocation to match actual demand patterns.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If complex prediction models are used to improve prediction accuracy, then prediction precision is improved, but computing costs increase

Engineering Contradiction:

Improveprediction accuracyVSAvoidcomputing costs

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system employs simple linear regression models rather than complex machine learning algorithms. These lightweight models are computationally inexpensive to train and execute, making them cost-effective for continuous prediction operations. The models are updated periodically with new data but do not require the heavy computational resources needed by sophisticated neural networks or ensemble methods.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The system optimizes prediction accuracy by carefully selecting and transforming input parameters from time series data. Techniques such as data normalization, feature engineering, and parameter optimization are applied to enhance model performance without increasing computational complexity. The linear regression models leverage mathematical optimizations to achieve good predictive performance with minimal processing power.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20240220833A1Method for predicting usage for cloud storage service and system therefor

Publication Date: 2024.07.04 SAMSUNG SDS CO LTD

AI summary

Provided are a method for predicting usage for cloud storage service and system therefor. The method according to some embodiments may include obtaining a time series dataset through monitoring usage of storage resource, extracting a plurality of candidate training sets from the time series dataset, evaluating suitability of the plurality of candidate training sets to a linear regression model, wherein an independent variable of the linear regression model comprises a time variable and a dependent variable represents usage of the storage resource; selecting a training set from the plurality of candidate training sets based on the evaluation result, and predicting future usage of the storage resource through the linear regression model trained with the training set.