Dynamic Edge Resource Augmentation for Intermittent Power
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Edge computing devices, powered by intermittent sources like solar cells, face challenges in maintaining consistent performance due to fluctuating power availability, leading to uncertainties in meeting service level agreements for latency and throughput.
Innovation Solution
A system that dynamically augments resources by utilizing a resource augmentation logic unit to identify available resources and orchestrate the use of remote resources, allowing client compute devices to access additional compute, storage, and accelerator resources over a network, effectively tunneling local bus communications to ensure performance meets target metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If compute resources are placed at remote edge locations powered by intermittent sources, then deployment flexibility and proximity to users are improved, but performance consistency and reliability deteriorate due to fluctuating power availability
Solution Approach 1:
The system dynamically adapts compute workloads to available power conditions by monitoring power availability and adjusting resource allocation in real-time. The orchestrator logic unit dynamically migrates workloads between edge devices and central cloud based on current power states, enabling the system to flexibly respond to intermittent power supply while maintaining service level agreements.
Solution Approach 2:
The patent introduces an orchestrator logic unit as an intermediary between edge compute devices and central cloud infrastructure. This intermediary manages workload distribution, monitors power availability, and makes intelligent decisions about where to execute compute tasks, thereby decoupling the direct relationship between intermittent power supply and compute performance consistency.
2Speed
If compute operations are performed at edge locations with limited power, then latency and bandwidth requirements are reduced, but compute capacity and processing power deteriorate
Solution Approach 1:
The patent segments compute workloads into different components that can be executed at different locations. Critical time-sensitive operations are performed at the edge with local power, while less time-critical but compute-intensive operations are migrated to central cloud data centers with reliable power supply, optimizing the balance between response time and compute capacity utilization.
3Reliability
If fixed compute capacity is guaranteed at edge devices, then service level agreements can be met, but device complexity and power consumption increase
Solution Approach 1:
The orchestrator logic unit implements self-service capabilities by automatically monitoring power availability, assessing workload requirements, and making autonomous decisions about workload migration and resource allocation. This eliminates the need for complex manual configuration and intervention while maintaining service level agreement compliance through automated adaptation to changing conditions.
Data Source
AI summary
Systems and methods may be used to determine where to run a service based on workload-based conditions or system-level conditions. An example method may include determining whether power available to a resource of a compute device satisfies a target power, for example to satisfy a target performance for a workload. When the power available is insufficient, an additional resource may be provided, for example on a remote device from the compute device. The additional resource may be used as a replacement for the resource of the compute device or to augment the resource of the compute device.