Distributed VM Allocation and Container Placement for Bottleneck Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cognitive operating systems face inefficiencies and bottlenecks in virtual machine allocation and container placement due to centralized decision-making, which are exacerbated by increased data processing demands.
Innovation Solution
A composite objective function is used to determine virtual machine allocation and container placement strategies, with each computing node individually solving the function and determining a fitness value based on task completion time and energy consumption to identify the optimal solution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If centralized algorithm is used for virtual machine allocation and container placement, then decision-making process is simplified, but system throughput is reduced and bottlenecks are created
Solution Approach 1:
The patent divides the centralized decision-making process into distributed computing nodes, each independently solving the allocation problem locally. This segmentation eliminates the bottleneck of centralized processing while maintaining manageable complexity at each node level, thereby improving overall system throughput.
2Extent of automation
If centralized algorithm is used for virtual machine allocation and container placement, then control is centralized, but energy efficiency is reduced
Solution Approach 1:
Each computing node independently solves the allocation problem using local information and the composite objective function, making autonomous decisions without requiring centralized control. This self-service approach reduces the energy consumption associated with centralized communication and coordination while maintaining energy-efficient allocation decisions.
3Measurement precision
If more data is processed to improve allocation accuracy, then solution quality improves, but processing time and energy consumption increase
Solution Approach 1:
The patent employs a composite objective function that incorporates local metrics (energy consumption, response time, resource utilization) specific to each computing node. This allows each node to make accurate allocation decisions based on its local conditions without requiring processing of the entire dataset, thereby maintaining accuracy while reducing processing time and energy consumption.
Data Source
AI summary
A first computing node receives information pertaining to a predefined objective, and determines a first result including a first VM allocation and a first container placement strategy to achieve the predefined objective. A second computing node receives the information pertaining to the predefined objective, and determines a second result that includes a second VM allocation and a second container placement strategy. A third processor receives the first result and determines a first fitness value based upon time taken by the first computing node to complete a task and an energy consumed by the first computing node. The third processor receives the second result and determines a second fitness value based upon taken by the second computing node to complete a task and an energy consumed by the second computing node. The highest fitness value is output with the VM allocation and the container placement strategy.