Server Allocation Module for Multi-Tier Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for allocating servers in multi-tiered architectures are inefficient due to exponential processing times and lack of flexibility, as they typically require a single algorithm for server allocation, which becomes impractical with increasing tiers and varying workloads.
Innovation Solution
A server management system with a server allocation module that dynamically allocates servers across tiers based on workload, using multiple algorithms (two-approximation, pseudo-polynomial-time exact, and fully-polynomial-time approximation) to minimize cost while meeting response time constraints, allowing for flexible selection based on accuracy and computation time requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional server allocation algorithms are used, then server allocation can be performed, but processing time increases exponentially with the number of tiers
Solution Approach 1:
The patent transforms the server allocation problem into a knapsack problem by changing the parameter representation from direct server allocation to item selection from predefined sets. Each tier has a set of possible server configurations (items), and the algorithm selects one configuration per tier that optimizes the overall objective function (response time constraint satisfaction with minimum cost). This parameter transformation reduces the problem from exponential to polynomial time complexity.
Solution Approach 2:
The patent segments the server allocation problem by dividing each tier into discrete configurable items (server configurations) that can be independently selected. Instead of considering all possible server allocation combinations across all tiers simultaneously (exponential complexity), the algorithm processes each tier's configurable items separately and combines results, achieving polynomial time complexity through dynamic programming.
2Adaptability or versatility
If a single server allocation algorithm is used, then the system is simple to implement, but flexibility to handle varying workloads and accuracy requirements is limited
Solution Approach 1:
The patent implements a universal server allocation framework that can handle multiple allocation scenarios through a single unified approach. The knapsack-based algorithm can accommodate different objective functions (minimizing cost, minimizing response time, balancing both), different numbers of tiers, and varying constraint requirements by simply changing the input parameters and item sets, without requiring fundamentally different algorithms for different scenarios.
Solution Approach 2:
The patent introduces dynamic adaptability by allowing the selection of different knapsack problem formulations (exact solution vs. approximation algorithms) based on the specific workload characteristics and accuracy requirements. The system can dynamically adjust the level of computational effort and the specific algorithm used, providing flexibility to handle varying operational conditions while maintaining a consistent overall framework.
Data Source
AI summary
Plural sets of items corresponding to plural tiers of a multi-tiered system are defined, where the items represent amounts of resources to allocate to the tiers. Items from respective sets are selected based on a response time constraint and a target cost. Information is provided pertaining to allocation of amounts of resources to the respective tiers based on the selected items.