Dedicated Optical Distribution for Virtualized Computing Resources

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In virtualized datacenter environments, traditional systems cause bottlenecks and waste resources due to inefficient allocation of physical processing and memory resources, leading to reduced performance and increased latency in data processing.

Innovation Solution

A dedicated optical distribution system that utilizes a dedicated physical resource manager to identify and aggregate unassigned processing units and memory devices across physical host servers, establishing direct communication paths to create a candidate resource set that satisfies virtual machine requirements through simulation testing and reconfiguration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If physical processing resources and memory resources are assigned to handle particular processes in virtualized environments, then resource allocation is established, but resources are not actually utilized, thereby reducing performance and wasting datacenter resources

Engineering Contradiction:

Improvedatacenter performanceVSAvoidresource utilization efficiency

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system dynamically allocates and deallocates physical processing resources and memory resources based on actual utilization needs. The virtualization platform continuously monitors resource usage and reconfigures allocations to match demand, transforming static resource assignment into dynamic adaptive allocation that optimizes both productivity and resource efficiency

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes resource allocation parameters by adjusting the mapping between virtual machines and physical resources. When utilization drops below thresholds, the system modifies allocation parameters to consolidate or release resources, thereby improving overall datacenter performance while reducing wasted resource capacity

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If traditional systems are used for distributed computing environments, then resource allocation is simplified, but bottlenecks and single points of failure occur for processing data

Engineering Contradiction:

Improvesystem architecture complexityVSAvoiddata processing reliability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system segments the distributed computing environment into multiple independent resource pools and failure domains. By dividing the architecture into modular units with independent resource allocation, the system eliminates single points of failure while maintaining manageable complexity through standardized segmentation patterns

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The virtualization platform acts as an intermediary layer between physical resources and computing workloads. This intermediary abstracts the complexity of distributed resource management while providing enhanced reliability through features like live migration, failover capabilities, and centralized resource orchestration that prevent bottlenecks

Inventive Principle:

Principle #24Intermediary (Mediator)

3Quantity of substance

If processing is shifted to a datacenter to handle petabyte scale incoming data, then data processing capacity is increased, but computing systems become burdened and operate inefficiently

Engineering Contradiction:

Improvedata processing capacityVSAvoidcomputing system efficiency

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The virtualization platform provides universal resource allocation that allows the same physical infrastructure to efficiently handle diverse workloads at petabyte scale. By creating multi-functional resource pools that can be dynamically assigned to different computing tasks, the system maintains high efficiency while processing large volumes of data across multiple applications and services

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11526374B2Dedicated distribution of computing resources in virtualized environments

Publication Date: 2022.12.13 AT&T INTELLECTUAL PROPERTY I L P

AI summary

Concepts and technologies directed to dedicated optical distribution of computing resources in virtualized environments are disclosed herein. In various aspects, a system can include a processor and memory storing instructions that, upon execution, cause performance of operations. The operations can include receiving a virtual machine creation request that includes a virtual processing requirement and a virtual memory requirement for a virtual machine. The operations can include accessing a physical host infrastructure map that identifies remainder resources from physical host servers within a datacenter. The operations can include creating a simulation test routine and assembling a candidate resource set from the remainder resources. The operations can include establishing a dedicated processing path and a dedicated memory path for the candidate resource set. The operations can include initiating the simulation test routine on the candidate resource set via the dedicated processing path and the dedicated memory path.