Provider Substrate Extension for Low-Latency Cloud Connectivity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

As data centers grow in scale and complexity, managing physical computing resources becomes increasingly complicated, and existing cloud services may not be optimal for applications requiring low latency and high data processing at customer premises due to geographical distance and security concerns.

Innovation Solution

A provider substrate extension (PSE) is deployed on-premises, providing a local extension of cloud network capabilities with pre-configured hardware, software, and firmware to support computing resources, ensuring secure and reliable communication with the provider network, and managed through the same interfaces as cloud services.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If cloud services are used for data processing, then scalability and resource sharing are improved, but latency increases due to geographical distance

Engineering Contradiction:
ImprovescalabilityVSAvoidlatency
Core Design Contradiction:
Adaptability or versatilityVSSpeed

Solution Approach 1:

The system segments the cloud network into a provider network and customer-deployed substrate extensions. By dividing the network architecture, critical data processing functions are placed locally at customer premises while maintaining connection to the provider network for broader cloud services, thus reducing latency for local operations while preserving scalability through the hybrid architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The substrate extension acts as an intermediary between the customer's local network and the provider network. It includes a gateway and virtualization layer that mediates traffic flow, enabling local data processing close to data sources while maintaining secure connectivity to the provider network for resource sharing and scalability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If more physical computing resources are deployed at customer premises, then latency is reduced, but device complexity increases

Engineering Contradiction:
ImprovelatencyVSAvoidcomplexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

Instead of deploying complex physical infrastructure at customer premises, the system uses virtualization to create virtual copies of cloud services and resources. The substrate extension provides a simplified interface that presents virtualized computing, storage, and networking resources locally, reducing complexity compared to managing physical hardware while enabling low-latency access.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system changes the fundamental parameter of resource deployment from physical to virtual. By using virtualization technologies, the substrate extension provides scalable computing resources without requiring physical hardware deployment at customer sites, thus reducing complexity while maintaining performance.

Inventive Principle:
Principle #35Parameter changes

3Ease of operation

If virtualization technologies are used to share hardware resources, then ease of operation is improved, but loss of information may occur in complex network configurations

Engineering Contradiction:
Improveease of operationVSAvoidinformation loss
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The substrate extension incorporates feedback mechanisms that continuously monitor network traffic, connectivity status, and resource allocation. This feedback enables the system to detect and correct information loss or data corruption in complex network configurations, ensuring reliable operation while maintaining ease of use through automated management.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11659058B2Provider network connectivity management for provider network substrate extensions
Publication Date: 2023.05.23 AMAZON TECH INC
  • US11659058B2 patent drawing
  • US11659058B2 patent drawing
  • US11659058B2 patent drawing

AI summary

A first service of a provider network obtains an identification of one or more substrate addressable devices included in an extension of the provider network. Based on the identification, a launch of one or more compute instances within the provider network is initiated. The one or more compute instances are to connect the provider network to the extension of the provider network across at least a third-party network by receiving a first control plane message directed to a first substrate addressable device of the one or more substrate addressable devices, by updating a message state data store based at least in part on the first control plane message, and by sending a second control plane message to the first substrate addressable device via a secure tunnel.