Machine Learning Model for Cloud Resource Usage Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing environments face challenges in managing computing resources efficiently due to difficulties in monitoring and analyzing vast amounts of historical usage data, leading to poor resource allocation, overuse, and waste.
Innovation Solution
A cloud resource prediction platform that utilizes a machine learning model to predict resource usage by training on historical cloud and customer data, determining usage growth profiles and deviation data, and processing new resource requests to generate projected usage data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual monitoring and analysis of historical usage data is used, then resource allocation decisions can be made, but the process is time-consuming and prone to errors
Solution Approach 1:
The patent replaces manual mechanical analysis of historical usage data with an automated machine learning model. The ML model processes historical cloud data and customer data to generate usage growth profiles and predictions, eliminating the need for manual monitoring and analysis while improving accuracy and speed of resource allocation decisions.
2Measurement precision
If more historical data is collected for analysis, then prediction accuracy improves, but data processing complexity increases
Solution Approach 1:
The patent introduces usage growth profiles as an intermediary representation that simplifies complex historical data. The ML model first processes vast historical data to create condensed usage growth profiles, which then serve as input for predictions. This two-stage approach maintains prediction accuracy while reducing the complexity of direct data processing.
3Productivity
If resource allocation is based on current usage only, then quick decisions can be made, but future resource needs may not be met
Solution Approach 1:
The patent implements preliminary action by having the ML model continuously analyze historical data and generate usage growth profiles in advance. When resource allocation decisions are needed, the model can quickly query these pre-computed profiles to predict future usage patterns, enabling both rapid decision-making and reliable forward-looking resource allocation.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A device may receive historical cloud data associated with resources of a cloud computing environment, and may receive historical customer data associated with requested resource usage by customers of the cloud computing environment. The device may determine a usage growth profile based on the historical cloud data and the historical customer data, and may determine, based on the historical cloud data and the historical customer data, usage deviation data indicating deviations between actual and planned resource usage. The device may train a model, with the usage growth profile and the usage deviation data, to generate a trained model, and may receive a request for new resource usage by a customer associated with the cloud computing environment. The device may process the request for the new resource usage, with the trained model, to generate projected resource usage data, and may perform actions based on the projected resource usage data.