Bare Metal As-Is Session for Edge Cloud Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Edge computing systems face resource constraints and power management challenges due to their resource-constrained and power-limited environments, which can lead to inefficiencies and limitations in providing low-latency services, especially in multi-tenant and dynamic network usage scenarios.
Innovation Solution
Implementing a 'bare metal as-is' service model that allows edge devices to temporarily control and manage unused cloud resources, providing full access to hardware resources like power and networking, similar to on-premises management, to enhance resource utilization and flexibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If edge computing systems use centralized cloud computing environments, then resource availability and processing power are improved, but latency and network dependency increase
Solution Approach 1:
The patent segments cloud computing resources into edge-located server platforms that can be physically deployed near users. This segmentation allows edge devices to access local resources immediately (reducing latency) while maintaining the ability to leverage cloud-scale processing power through the shared resource pool.
Solution Approach 2:
The patent introduces a spatial dimension to resource allocation by allowing server platforms to be physically relocated between edge locations and centralized data centers. This dimensional flexibility enables the system to optimize between local low-latency access and centralized high-processing-power scenarios based on real-time demands.
2Productivity
If edge devices have full control of hardware resources, then resource utilization efficiency and flexibility are improved, but system complexity and management overhead increase
Solution Approach 1:
The patent introduces an orchestrator as an intermediary layer that manages hardware assignments between edge devices and server platforms. The orchestrator handles the complex coordination of resource allocation, session management, and hardware handover, allowing edge devices to have full control during active sessions while centralizing management complexity in the orchestrator.
Solution Approach 2:
The bare-metal-as-is session model enables edge devices to self-configure and directly control hardware resources once assigned, without requiring continuous orchestration intervention. This self-service approach maximizes resource utilization efficiency during active sessions while minimizing ongoing management overhead.
3Loss of energy
If cloud resources are shared among multiple tenants, then infrastructure reuse and cost efficiency are improved, but resource isolation and security boundaries are compromised
Solution Approach 1:
The patent implements dynamic resource allocation where server platforms can be temporarily dedicated to single-edge devices during bare-metal-as-is sessions, then reassigned to other tenants when not in use. This dynamic switching provides strong isolation and security during active usage while enabling infrastructure sharing and cost efficiency across multiple tenants over time.
4Adaptability or versatility
If edge computing systems use virtualized resource access, then system flexibility and scalability are improved, but hardware transparency and direct control are reduced
Solution Approach 1:
The patent creates a universal server platform design that can function in multiple modes: as a virtualized cloud resource, as a dedicated edge platform, or as a bare-metal resource with full hardware access. This multi-functionality allows the same infrastructure to serve diverse use cases, providing hardware transparency when needed while maintaining overall system flexibility through the unified architecture.
Data Source
AI summary
A server platform in a cloud computing system is determined to be in an unused state and a request from a remote computing system outside the data center system is received to control hardware of at least one of the server platforms of the cloud computing systems. A bare-metal-as-is (BMAI) session is initiated for the remote computing system to use the server platform based on the unused state, wherein exclusive control of at least a portion of hardware of the server platform is temporarily handed over to the remote computing system in the BMAI session. Control of the portion of the hardware of the server platform is reclaimed based on an end of the BMAI session.