Resource Saturation Rate Sorting for Real-Time Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer system resource allocation methods have high computational complexity (O(n^2)) and cannot satisfy real-time calculation requirements, especially for large systems with many resource users, and fail to support minimum resource quota allocation efficiently.
Innovation Solution
A method that calculates resource saturation rates for each user, sorts users based on these rates, and classifies them into B-class and C-class users, allocating resources efficiently by determining a boundary user and reallocating resources based on maximum and minimum quotas, reducing time complexity to O(log n) and enabling real-time calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If existing resource allocation algorithms are used to allocate resources among multiple resource users, then resource allocation can be performed, but the computational complexity becomes O(n^2) which cannot satisfy real-time calculation requirements for large systems
Solution Approach 1:
The patent segments the resource allocation process into two distinct phases: (1) calculating each resource user's resource saturation rate independently, and (2) sorting users by saturation rate and allocating resources in order. This segmentation transforms the O(n^2) complexity into O(n log n) by avoiding the need to recalculate all users' allocations when a single user's request changes, thus enabling real-time calculation for large systems.
Solution Approach 2:
The patent introduces a new parameter - resource saturation rate - to characterize each user's resource demand state. By changing the allocation criterion from direct resource amount to saturation rate, the system can efficiently identify which users need resources most urgently and allocate accordingly, reducing computational complexity while maintaining allocation effectiveness.
2Loss of time
If existing resource allocation algorithms calculate resource allocation quota for all resource users, then complete allocation information is obtained, but the calculation time increases significantly when only one user's allocation is needed
Solution Approach 1:
The patent extracts and pre-calculates only the critical information needed for allocation decisions - specifically, each user's resource saturation rate - and stores it. When a resource allocation request arrives, the system only needs to retrieve pre-computed saturation rates and perform sorting, rather than recalculating allocations for all users. This extraction approach dramatically reduces calculation time for single-user queries.
3Adaptability or versatility
If resource users have different weights and request different amounts of resources, then differentiated allocation is achieved, but the allocation algorithm complexity increases to O(n^2)
Solution Approach 1:
The patent applies local quality by treating each resource user individually with their own weight and saturation rate characteristics. Instead of using a uniform allocation approach, the system calculates and sorts users based on their specific saturation rates, allowing differentiated allocation that adapts to each user's local needs without requiring complex O(n^2) interactions between all users.
Data Source
AI summary
A computer system resource allocation method is disclosed. The method may be implemented by a process and may comprise acquiring a total system resource and resource allocation data of each resource user submitting a resource application request, the resource allocation data including a maximum resource quota and a requested amount of resource by the each resource user, determining a corresponding resource saturation rate as a ratio between the amount of requested resource and the maximum resource quota, sorting the resource users according to the calculated resource saturation rates of the respective resource users, determining a boundary resource user using a set condition, according to the sorted resource users, and identifying resource users with a resource saturation rate smaller than or equal to that of the boundary resource user to be B-class resource users, and identifying resource users with a resource saturation rate larger than that of the boundary resource user to be C-class resource users.