Dynamic Server Allocation Across Tiers Using Algorithm Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for allocating servers in multi-tiered server systems are inefficient due to exponential processing times and lack of flexibility, making it difficult to meet response time constraints while minimizing system cost.
Innovation Solution
A server management system with a server allocation module that dynamically allocates servers across tiers based on workload, using a selection of algorithms such as two-approximation, pseudo-polynomial-time exact, and fully-polynomial-time approximation algorithms to optimize server resource allocation and reduce processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional algorithms are used to allocate servers in each tier, then the allocation can meet response time constraints, but the processing time increases exponentially as the number of tiers increases
Solution Approach 1:
The patent divides the server allocation problem into separate subproblems for each tier, where each tier's server allocation is determined independently based on its specific response time requirement and workload. This segmentation transforms the exponential-time global optimization problem into multiple linear-time local optimization problems, significantly reducing overall processing time while maintaining constraint satisfaction.
Solution Approach 2:
The patent implements a dynamic allocation approach where the number of servers in each tier is adjusted based on real-time workload conditions and response time requirements. The system can dynamically add or remove servers from each tier as needed, allowing flexible adaptation to changing system demands without requiring complete re-allocation of all tiers, thus reducing computation time.
2Productivity
If conventional algorithms are used for server allocation, then allocations can be computed, but the system lacks flexibility in selecting different allocation strategies
Solution Approach 1:
The patent creates a universal server allocation framework that can accommodate multiple different allocation algorithms and strategies within a single system. The framework allows administrators to select from various algorithms (e.g., round-robin, weighted fairness, priority-based) and switch between them based on different operational requirements, making the system highly adaptable to varying scenarios while maintaining efficient computation.
Data Source
AI summary
To perform resource allocation in a system having plural tiers, one of plural resource allocation algorithms is selected in response to determining, based on one or more conditions, which of the plural resource allocation algorithms to select. The selected resource allocation algorithm is used to allocate resources for the plural tiers of the system.