Dynamic Resource Scaling for Computing Workloads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In applications with varying computing tasks, a preset resource quantity is often twice the peak requirement, leading to resource redundancy and waste, which affects utilization rates.
Innovation Solution
A method for optimizing computing resources by determining a target resource quantity based on current load data and scaling resources accordingly, linking the scaling of a first resource with a second resource to match their quantities, thereby reducing redundancy and waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a preset resource quantity is set to twice the peak requirement to ensure stability, then system stability is improved, but resource utilization rate deteriorates due to resource redundancy and waste
Solution Approach 1:
The patent implements dynamic resource scaling where the resource quantity is automatically adjusted based on real-time load data. The system transitions from a static preset resource quantity to a dynamic configuration that can expand or contract according to actual computing task requirements, resolving the contradiction between stability and utilization by making the system adaptable rather than fixed
Solution Approach 2:
The patent introduces a feedback mechanism where current load data is continuously monitored and used to determine the target resource quantity. The system compares the current resource quantity with the target quantity and adjusts accordingly, creating a closed-loop control system that optimizes resource allocation while maintaining stability through data-driven decision-making
2Productivity
If resource quantity is increased to handle peak computing tasks, then task completion capability is improved, but resource consumption increases leading to waste during trough periods
Solution Approach 1:
The system dynamically adjusts resource quantity based on whether the system is in a peak or trough period. During peak periods, the resource quantity increases to maintain task completion capability, while during trough periods, the resource quantity is reduced to minimize consumption, eliminating the need to maintain high resource levels continuously
Solution Approach 2:
The patent changes the resource quantity parameter based on load conditions. The system determines the target resource quantity by comparing current load data with historical patterns to identify peak or trough periods, and adjusts the resource quantity parameter accordingly to optimize both capability and consumption
Data Source
AI summary
A method for optimizing computing resource is performed by an electronic device. The method includes: determining a current resource quantity of a first resource based on current load data of the first resource and a target resource quantity of the first resource in connection with performing a computing task; scaling the first resource based on a comparison of the target resource quantity and the current resource quantity of the first resource; and scaling a second resource based on a scheduling state of the scaled first resource, wherein the scheduling state of the first resource refers to a scheduling condition of the first resource on the second resource, including that scheduling has been completed on the second resource and scheduling has not been completed on the second resource.