Cloud Workload Deployment via Energy Efficiency Grouping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud computing systems lack energy efficiency considerations when deploying workloads, as they primarily focus on resource availability and utilization without accounting for power consumption efficiency.
Innovation Solution
A method is introduced to classify compute nodes into energy efficiency groups based on energy efficiency metrics, deploy workload replicas across these groups, and monitor energy consumption and performance during a probing period to identify the most efficient nodes for workload deployment, optimizing energy usage while ensuring resource availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If workload deployment is based solely on resource availability and utilization, then resource allocation is optimized, but energy efficiency is not considered leading to higher power consumption
Solution Approach 1:
The system performs preliminary classification of compute nodes into energy efficiency groups before workload deployment. Energy efficiency metrics are pre-calculated and stored for each node, allowing the deployment process to quickly reference and select from pre-evaluated nodes rather than calculating energy metrics in real-time during deployment decisions
Solution Approach 2:
The system segments compute nodes into distinct energy efficiency groups (e.g., high efficiency, medium efficiency, low efficiency groups) based on their energy efficiency metrics. This segmentation allows the workload deployment system to selectively choose from specific groups rather than evaluating all nodes individually, simplifying the deployment process while improving energy efficiency
2Use of energy by moving object
If compute nodes are classified into multiple energy efficiency groups, then energy efficiency optimization is improved, but system complexity increases
Solution Approach 1:
The system changes the parameter of node selection from purely resource-based to energy efficiency-based by introducing energy efficiency metrics as a primary classification parameter. Nodes are re-evaluated and re-grouped based on their energy efficiency characteristics, allowing the system to optimize power consumption by selecting nodes from appropriate energy efficiency groups rather than using traditional resource-only metrics
3Measurement precision
If workload replicas are deployed across multiple energy efficiency groups for probing, then energy efficiency accuracy is improved, but deployment time increases
Solution Approach 1:
The system deploys workload replicas to a selective subset of compute nodes representing different energy efficiency groups during the probing period, rather than deploying to all available nodes. This partial action approach provides sufficient data to identify the optimal energy efficiency group without the time cost of probing every node in the system
Data Source
AI summary
Computer-implemented methods for deploying workloads in a cloud computing system based on energy efficiency are provided. Aspects include obtaining an energy efficiency metric for a plurality of compute nodes in the cloud computing environment and classifying the plurality of compute nodes into energy efficiency groups based on the energy efficiency metrics. Aspects also include creating a partition of nodes including one compute node selected from each of the energy efficiency groups, deploying a replica of a workload to each compute node in the partition, and monitoring an energy consumption and a computing performance of each of compute node in the partition during a probing period. Aspects further include identifying, based on the energy consumption and performance, a selected energy efficiency group from the plurality of energy efficiency groups and deploying the workload to one or more of the plurality of compute nodes in the selected energy efficiency group.