Container Workload Migration for Edge Energy Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current distributed computing systems face challenges in efficiently deploying and executing containers in energy-constrained edge devices, leading to potential device power-off, strained computing resources, and poor container performance.
Innovation Solution
A migration mechanism that estimates energy consumption of containers based on CPU usage, memory, client volume, and network traffic, and uses a multi-objective optimization algorithm to schedule container operations and transfer workloads to optimize energy efficiency and performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If containers are deployed on energy-constrained edge devices, then computing services can be executed close to data sources reducing latency, but energy consumption increases causing device power-off and reduced battery life
Solution Approach 1:
The system dynamically migrates containers between edge devices based on real-time energy level monitoring. The migration decision is made by comparing energy levels of source and destination devices, and the container is relocated to a device with sufficient energy capacity. This dynamic adaptation allows the system to maintain low latency by keeping containers on energy-sufficient devices while preventing energy depletion on any single device.
2Productivity
If containers are deployed on edge devices with limited computing resources, then edge computing services can be provided, but computing resources become strained leading to poor container performance
Solution Approach 1:
The system performs dynamic container migration based on real-time monitoring of computing resource utilization. When a container experiences resource strain or when a destination device has available capacity, the system automatically migrates the container to balance the workload distribution. This ensures that containers always run on devices with sufficient resources, maintaining reliable performance while enabling continuous service provision across the edge network.
3Ease of manufacture
If container operations are scheduled without optimization, then deployment is simple, but energy consumption increases and battery life is reduced
Solution Approach 1:
The system changes the scheduling parameters by introducing energy level as a critical factor in container deployment decisions. Instead of deploying containers arbitrarily, the system evaluates energy levels of candidate devices and selects destinations that optimize energy consumption. The migration policy uses energy level thresholds and comparisons to determine optimal container placement, thereby reducing overall energy consumption and extending battery life while maintaining automated deployment simplicity.
Data Source
AI summary
Container workloads can be transferred (e.g., migrated) between nodes of a distributed computing environment based on energy consumption. For example, a system may generate an energy consumption estimate for a container executing on a first node. The system can further determine that the energy consumption estimate of the container exceeds an energy consumption threshold. In response, the system may implement a multi-objective optimization algorithm to identify a second node usable to execute the container. The multi-objective optimization algorithm may identify the second node based on current workloads of a group of nodes that includes the second node and the energy consumption estimate of the container. The system may then deploy the container at the second node.