ML-Based Computing Resource Allocation Platform
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Organizations face challenges in accurately allocating computing resources for jobs due to the difficulty in estimating the types and amounts needed, leading to inefficiencies and waste, especially when handling thousands or millions of requests across various geographic locations.
Innovation Solution
A computing resource allocation platform that utilizes machine learning models, such as factorization machines, random forests, and gradient boosting, to process requests in real-time, dynamically re-allocate resources based on performance, and improve resource utilization by analyzing historical data and performance metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual methods are used to allocate computing resources, then simplicity and ease of operation are maintained, but resource utilization efficiency deteriorates due to inaccurate estimation and waste
Solution Approach 1:
The system enables self-service by allowing the computing resource allocation platform to automatically determine and allocate resources without manual intervention. The machine learning models process requests autonomously, analyzing historical data and performance metrics to make allocation decisions, thereby improving efficiency while eliminating the need for complex manual allocation processes
Solution Approach 2:
The patent replaces manual mechanical allocation processes with automated machine learning-based systems. Instead of human operators manually estimating and allocating resources, the system uses trained machine learning models that process requests and determine allocations automatically, substituting human decision-making with algorithmic processes that improve accuracy and efficiency
2Measurement precision
If machine learning models are implemented for automatic allocation, then resource allocation accuracy improves, but system complexity and processing requirements increase
Solution Approach 1:
The system applies preliminary action by pre-training machine learning models using historical computing resource usage data before actual allocation occurs. This pre-processing phase prepares the models to make accurate allocation decisions in real-time, improving measurement precision while managing complexity through advance preparation rather than complex real-time processing
Solution Approach 2:
The patent introduces machine learning models as intermediaries between resource requests and resource allocation. These models act as mediators that process requests and translate them into optimized allocation decisions, improving accuracy by introducing intelligent processing layers without requiring direct complex interactions between all system components
3Adaptability or versatility
If dynamic re-allocation is performed during job execution, then adaptability to changing demands improves, but processing time and system overhead increase
Solution Approach 1:
The system implements dynamics by enabling dynamic re-allocation of computing resources during job execution. The machine learning models continuously monitor performance metrics and adjust resource allocations in response to changing demands, allowing the system to adapt flexibly while managing time overhead through efficient monitoring and adjustment mechanisms
Solution Approach 2:
The patent incorporates feedback mechanisms where performance metrics from ongoing jobs are fed back to the machine learning models. This feedback loop enables the system to learn from actual resource usage patterns and adjust allocations dynamically, improving adaptability while optimizing the timing and frequency of adjustments to minimize processing time overhead
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A device may receive a computing resource request. The computing resource request may be related to allocating computing resources for a job. The device may process the computing resource request to identify a set of parameters related to the computing resource request or to the job. The set of parameters may be used to determine an allocation of the computing resources for the job. The device may utilize multiple machine learning models to process data related to the set of parameters identified in the computing resource request. The device may determine the allocation of the computing resources for the job based on utilizing the multiple machine learning models to process the data. The device may generate a set of scripts related to causing the computing resources to be allocated for the job according to the allocation. The device may perform a set of actions based on the set of scripts.