Cloud Resource Access Bands for Stockout-Aware Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing platforms face inefficiencies in managing finite computing resources, leading to stockouts during high demand periods and underutilization when increasing capacity or enforcing quotas.
Innovation Solution
Implementing a method to determine access control bands based on historical computing usage, including first, second, and third access control bands to optimize resource allocation, ensuring availability and reducing stockouts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If quotas are applied to limit computing resource consumption, then resource capacity is preserved, but resource utilization efficiency deteriorates
Solution Approach 1:
The patent implements dynamic access control bands that automatically adjust based on real-time system conditions, historical usage patterns, and workload characteristics. Instead of static quotas, the system continuously modifies access control parameters to optimize both resource preservation and utilization efficiency, allowing the system to adapt to changing demands while maintaining resource capacity
Solution Approach 2:
The system changes multiple parameters simultaneously including access control band levels, historical usage thresholds, workload priority weights, and resource allocation factors. By adjusting these parameters dynamically based on system state, the patent resolves the contradiction between preserving resource capacity and maintaining high utilization efficiency
2Reliability
If total system capacity is increased to prevent stockouts, then resource availability is improved, but resource utilization efficiency deteriorates
Solution Approach 1:
The system performs preliminary analysis of historical computing usage patterns to predict future resource demands and proactively adjusts access control bands before stockouts occur. By anticipating demand based on historical data, the system ensures resource availability without needing to continuously increase total capacity, thereby maintaining utilization efficiency
Solution Approach 2:
The patent implements a feedback mechanism that continuously monitors actual resource usage, access control band effectiveness, and system performance. This feedback loop allows the system to learn from past allocations and optimize future resource distribution, ensuring availability while preventing capacity waste through data-driven adjustments
3Device complexity
If static access control is implemented, then system complexity is reduced, but adaptability to varying demand deteriorates
Solution Approach 1:
The access control system performs self-adjustment by automatically analyzing historical usage data and modifying access control bands without requiring manual intervention or complex external control mechanisms. This self-service capability enables the system to adapt to varying demands while keeping the control architecture relatively simple, as the system manages its own optimization
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A method includes determining a first access control band based on a first historical computing usage of a distributed computing system by one or more workloads. The method also includes determining a second access control band based on a second historical computing usage of the distributed computing system. The method also includes determining a third access control band based on an amount of computing resources of the distributed computing system not defined by the first access control band or the second access control band. The method also includes receiving a request for a particular amount of computing resources and determining one or more access control bands from the first access control band, the second access control band, and the third access control band. The method also includes allocating to the one or more workloads at least a portion of the requested particular amount of computing resources.