Remote Resource Allocation Analysis for Distributed Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional resource allocation techniques for distributed computer systems are computationally intensive and require frequent updates, especially as the number of components increases, affecting management server performance and necessitating updates across different systems.
Innovation Solution
A system and method for performing customized remote resource allocation analyses using a snapshot of a distributed computer system, where a resource allocation algorithm is selected based on user-provided parameters, allowing for remote analysis and optimization of resource allocation without overwhelming the management server.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional resource allocation analysis is performed locally on each distributed computer system, then resource allocation can be performed using current utilization and requirement data, but the computational intensity increases significantly as the number of components increases, affecting management server performance
Solution Approach 1:
The patent extracts the computationally intensive resource allocation analysis function from the local management server and relocates it to a remote server. The local management server only needs to collect current utilization and requirement data, then send it to the remote server for analysis. This separation removes the computational burden from the management server while maintaining analysis accuracy.
Solution Approach 2:
The patent introduces a remote server as an intermediary between the local management server and the resource allocation analysis process. The remote server receives snapshots from multiple distributed computer systems, performs the computationally intensive analysis using stored algorithms, and returns results. This intermediary handles the computational intensity away from the original management servers.
2Adaptability or versatility
If resource allocation analysis algorithms are updated or patched at different distributed computer systems, then the analysis can adapt to new requirements, but updates must be applied across all systems which increases complexity and time consumption
Solution Approach 1:
The patent merges the resource allocation analysis algorithms into a centralized location on the remote server, where a single copy of the algorithm is maintained. When an update or patch is needed, it is applied once to the centralized algorithm rather than being propagated to multiple distributed systems. This eliminates update propagation time and ensures all systems benefit from the same updated algorithm simultaneously.
3Adaptability or versatility
If multiple resource allocation algorithms are maintained for different distributed computer systems, then each system can have customized analysis, but the complexity of managing and updating algorithms across systems increases
Solution Approach 1:
The patent makes the remote server universal by enabling it to perform resource allocation analysis for multiple different distributed computer systems using a single set of algorithms. The remote server receives snapshots from various systems and applies the same algorithmic framework to each, customized only by the specific input data. This eliminates the need to maintain separate algorithm copies for each system, reducing management complexity while preserving customized analysis capability.
Data Source
AI summary
A system and method for performing customized remote resource allocation analyzes on distributed computer systems utilizes a snapshot of a distributed computer system, which is received at a remote resource allocation module, to perform a resource allocation analysis using a resource allocation algorithm. The resource allocation algorithm is selected from a plurality of resource allocation algorithms based on at least one user-provided parameter associated with the distributed computer system.