Cloud Resource Prediction via Model Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current cloud computing services lack the ability to predict the allocation of processing resources needed for a given data set and processing task, leading to uncertainty and inefficiency in resource utilization.

Innovation Solution

A method and system that predict the allocation of processing resources by selecting a model from a database based on input parameters, using historical data to generate models that relate data sets and processing tasks to resource requirements, and adjusting predictions based on available resource configurations and user inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If cloud computing services provide flexible resource allocation, then adaptability is improved, but the ability to predict resource allocation deteriorates

Engineering Contradiction:

ImproveflexibilityVSAvoidprediction accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system performs preliminary actions by collecting historical resource allocation data and training prediction models before actual resource allocation occurs. The model database is pre-populated with trained models that can predict resource needs, allowing the system to maintain both flexibility and predictability simultaneously.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where actual resource allocation outcomes are fed back into the model training process. This continuous feedback loop improves prediction accuracy over time while maintaining system flexibility, as the models adapt to new patterns in resource usage.

Inventive Principle:

Principle #23Feedback

2Ease of operation

If cloud computing services use fixed pricing models, then ease of operation is improved, but productivity deteriorates due to inefficient resource utilization

Engineering Contradiction:

Improveease of understandingVSAvoidresource utilization efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system replaces manual resource estimation and allocation mechanisms with automated machine learning models. These models automatically analyze historical data and predict optimal resource allocation, substituting complex manual calculations with automated intelligent systems that improve both efficiency and ease of use.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system dynamically changes resource allocation parameters based on predicted workload characteristics. Instead of fixed allocations, the system adjusts CPU, memory, and storage parameters according to actual needs, improving resource utilization efficiency while maintaining operational simplicity through automated management.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If cloud computing services allocate more processing resources, then productivity is improved, but loss of energy increases

Engineering Contradiction:

Improveprocessing throughputVSAvoidenergy consumption

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system applies partial action by allocating only the necessary amount of resources predicted by the models, avoiding excessive resource allocation. The prediction models determine the precise resource levels needed to achieve required productivity, preventing both under-provisioning and over-provisioning of energy-consuming resources.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11146497B2Resource prediction for cloud computing

Publication Date: 2021.10.12 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

AI summary

The invention relates to a method for predicting an allocation of processing resources provided by a cloud computing module (230) to process a data set based on a predefined processing task. Input parameters are detected, the input parameters containing information about at least the data set to be processed by the cloud computing module and the processing task to be carried out on the data set. A model is selected from a plurality of different models provided in a model database (130), each model providing a relationship between the data set processing task and a predicted allocation of the processing resources. The allocation of the processing resources is predicted based on the selected model and based on the input parameters.