Cloud Resource Prediction for Instantiation Delays

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems fail to predict and allocate cloud resources in real-time, leading to delays and increased operational costs, especially when users are actively interacting with applications.

Innovation Solution

A system that uses machine learning to predict user actions and resource needs within applications, allowing for the pre-allocation and dynamic provisioning of cloud resources from multiple providers to minimize delays and costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If cloud resources are provisioned dynamically based on real-time demands, then operational costs are reduced, but user experience delays increase due to provisioning time

Engineering Contradiction:

Improveoperational costVSAvoiduser experience delay

Core Design Contradiction:

Loss of energyVSLoss of time

Solution Approach 1:

The system performs preliminary actions by predicting user actions before they occur and pre-provisioning cloud resources in advance. The machine learning model analyzes user behavior patterns, application state, and historical data to forecast upcoming resource needs, triggering resource provisioning before the user actually needs them, thus eliminating provisioning delays while maintaining cost efficiency through on-demand activation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring user actions, resource usage patterns, and application performance. The machine learning model uses this feedback to refine predictions and adjust resource provisioning strategies in real-time, optimizing the balance between cost savings and user experience by learning from actual usage patterns rather than relying solely on static predictions

Inventive Principle:

Principle #23Feedback

2Productivity

If machine learning prediction is used to anticipate resource needs, then resource allocation efficiency is improved, but system complexity increases

Engineering Contradiction:

Improveresource allocation efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system applies universality by using a multi-functional machine learning model that handles multiple prediction tasks simultaneously - predicting user actions, estimating resource requirements, determining timing, and selecting appropriate cloud providers. This single integrated model reduces overall system complexity compared to having separate specialized models for each function, while maintaining high resource allocation efficiency through comprehensive predictive capabilities

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250181470A1Cloud Instantiation Based on Machine Learned Prediction

Publication Date: 2025.06.05 TANGOE US INC

AI summary

A system is provided for instantiating cloud services for an application in real time to allow the application to run in a small footprint and only request additional services on demand. By using predictive algorithms to forecast which services a user may want to access and having the resources available for them when the service is required the system is able to also improve response time for these on-demand services. The software can use and request/reserve resources from different IaaS providers based on computing needs and costs and an appropriate balance between the two.