Digital Twin PCI Resource Allocation for Pool Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems of computing devices within resource pools face inefficiencies due to underutilization of resources, where some devices do not use their resources at all times while others are overburdened, leading to suboptimal resource allocation and potential latency in accessing necessary resources.
Innovation Solution
A method and system that utilize a digital twin service, ledger service, and virtual switches to manage resource allocation across pool devices, enabling direct access to peripheral component interconnect (PCI) bus devices of other pool devices, and employing machine learning for resource prediction and allocation optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If resources are allocated statically to each computing device, then device complexity is reduced and ease of operation is improved, but resource utilization efficiency deteriorates and productivity decreases
Solution Approach 1:
The patent creates digital twins (virtual copies) of physical computing devices and their resources. These digital twins replicate the hardware architecture, resource capabilities, and operational states, enabling virtual resource allocation and management without directly manipulating physical devices. This copying approach allows multiple virtual instances to access and allocate physical resources dynamically while maintaining simplified operational interfaces.
Solution Approach 2:
The patent introduces digital twins as intermediary entities between the resource management system and physical computing devices. The digital twin service acts as a mediator that handles complex resource allocation, performance calculations, and access coordination, thereby simplifying the interface for end users while enabling sophisticated resource optimization behind the scenes.
2Productivity
If resources are shared across multiple pool devices, then resource utilization efficiency is improved and productivity increases, but access latency may worsen and reliability deteriorates
Solution Approach 1:
The patent performs performance calculations and resource allocation decisions in advance by utilizing digital twins to simulate and evaluate potential resource allocations. The system pre-calculates performance metrics and determines optimal resource assignments before actual resource access is needed, thereby reducing access latency and ensuring reliable resource availability when required.
Solution Approach 2:
The patent implements a feedback mechanism where performance calculations based on digital twin data are continuously monitored and used to adjust resource allocations. The system evaluates actual resource performance against predicted performance from digital twins, and uses this feedback to optimize future allocations, thereby maintaining high reliability and efficiency in shared resource environments.
3Productivity
If digital twins are generated for all pool devices, then resource prediction accuracy is improved and productivity increases, but device complexity and computational overhead worsen
Solution Approach 1:
The patent applies local quality by creating digital twins with differentiated levels of detail and complexity based on the specific needs and characteristics of each pool device. Rather than generating identical comprehensive digital twins for all devices, the system tailors the digital twin complexity to match the actual resource allocation requirements and performance prediction needs of each device, thereby reducing overall computational overhead while maintaining necessary prediction accuracy.
Data Source
AI summary
A method for managing pool device resources, the method comprising: obtaining, by a digital twin service, a digital twin generation request, wherein the digital twin generation request specifies a pool device, identifying a plurality of PCI bus device being used by the pool device associated with the digital twin generation request, obtaining configuration information associated with the plurality of PCI bus devices, initiating a resource allocation using a virtual switch to access a peripheral component interconnect (PCI) bus device on a second pool device based on the configuration information and the plurality of PCI bus devices, performing performance calculations on the PCI bus device based on the resource allocation, and storing a result of the performance calculations.