Cloud Manager Energy-Aware Node Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing environments face challenges in reducing energy consumption, as existing technologies do not effectively leverage energy consumption data when selecting computing nodes to serve jobs, leading to inefficient resource utilization.
Innovation Solution
A cloud manager determines computing nodes and their peripherals capable of serving a job, computes energy usage at different processing utilizations, and dispatches the job to configurations that minimize energy consumption based on evaluated energy usage data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If computing nodes are selected without considering energy consumption data, then job service capability is maintained, but energy consumption increases
Solution Approach 1:
The system pre-computes energy consumption data for different computing nodes and job configurations before actual job execution. Energy models are built in advance, and the cloud manager prepares scheduling decisions with energy optimization considerations, rather than making decisions reactively when jobs arrive. This allows energy-efficient scheduling without adding complex real-time computation overhead.
Solution Approach 2:
The cloud manager acts as an intermediary layer between job submissions and physical computing nodes. It introduces an energy-aware scheduling mechanism that translates job requirements into energy-optimized node selections, without requiring changes to the underlying hardware or job submission interfaces. This intermediary layer handles the complexity of energy optimization transparently.
2Use of energy by moving object
If computing nodes are selected based on energy consumption data, then energy efficiency is improved, but job performance may be compromised
Solution Approach 1:
The system changes the selection parameters for computing nodes by incorporating energy consumption data as an additional dimension alongside traditional performance metrics. Instead of selecting nodes based solely on processing power or availability, the cloud manager evaluates multiple parameters including energy efficiency, allowing it to identify nodes that provide optimal balance between performance and energy consumption.
Solution Approach 2:
The system evaluates energy consumption across multiple computing nodes and job configurations, computing energy usage for different processing utilizations and node combinations. By analyzing more options than strictly necessary (excessive evaluation), the system ensures that the selected configuration achieves acceptable performance while optimizing for energy efficiency.
3Use of energy by moving object
If multiple computing node configurations are evaluated, then energy optimization is achieved, but computational overhead increases
Solution Approach 1:
The evaluation process is segmented into distinct phases: identifying candidate computing nodes, computing energy consumption for each candidate, evaluating different processing utilizations, and selecting the optimal configuration. This segmentation allows the system to manage computational complexity by breaking down the overall evaluation into smaller, more efficient steps rather than attempting to evaluate all possibilities simultaneously.
Data Source
AI summary
Functionality can be implemented within a cloud manager to leverage energy consumption data of cloud processing and their associated facility resources when selecting computing nodes to complete the job. The cloud manager can determine possible computing nodes to complete the job based on the job attributes. The cloud manager can determine aggregate energy data of the cloud resources from an energy usage database. The cloud manager can analyze the energy usage data to determine a configuration of the computing nodes to perform the job that reduces total energy consumption. For example, a configuration of servers can be based on a number of servers and processor utilization at the servers to perform the job. The cloud manager can assign the job to the servers and set the processor utilization at the servers in accordance with the resource configuration determined to minimize energy consumption.