Provider Substrate Extensions for Edge Computing Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing platforms face challenges in providing low latency computing resources to end users due to physical constraints such as network distance and number of hops between end user devices and centralized data centers, limiting the achievement of very low latencies required for applications like game streaming, video conferencing, and real-time communications.
Innovation Solution
Deploying provider substrate extensions within communications service provider networks, which are closer to end users, allowing for the provisioning of computing resources with dramatically lower access latency by installing servers in locations such as mobile or cellular networks, wired internet service providers, and WiFi providers, thereby creating edge locations that offer single-digit millisecond latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computing resources are provisioned from centralized data centers, then resource pooling and management efficiency are improved, but network distance and access latency increase
Solution Approach 1:
The patent segments the centralized cloud computing system into multiple distributed edge locations. Instead of having all computing resources in one centralized data center, the system divides resources across geographically distributed edge locations that are closer to end users. This segmentation allows users to access computing resources from the nearest edge location, reducing network distance and access latency while maintaining the resource pooling benefits of cloud computing.
Solution Approach 2:
The patent introduces a spatial dimension to cloud resource deployment by establishing edge locations at multiple geographic positions between the centralized data center and end users. This creates a multi-dimensional resource access model where users can connect to edge locations in their local area rather than relying solely on distant centralized data centers, thereby reducing latency without sacrificing resource consolidation.
2Loss of time
If edge locations are deployed within communications service provider networks, then access latency is reduced, but network infrastructure complexity increases
Solution Approach 1:
The patent makes existing communications service provider network infrastructure serve multiple functions. The same network infrastructure that provides connectivity services also hosts computing resources at edge locations. This multi-functionality allows the network to simultaneously provide communication services and computing services, reducing the need for separate dedicated infrastructure and thereby limiting the increase in complexity.
Solution Approach 2:
The patent enables communications service provider networks to self-extend their capabilities by hosting cloud computing resources within their own infrastructure. The network infrastructure leverages its existing distributed presence and connectivity capabilities to provide edge computing services, rather than requiring completely new dedicated infrastructure. This self-service approach minimizes additional complexity while achieving low-latency access.
3Ease of operation
If provider substrate extensions are deployed closer to end users, then computing resource accessibility is improved, but deployment and management difficulty increases
Solution Approach 1:
The patent introduces cloud provider network control planes as intermediaries that manage the deployment and operation of provider substrate extensions at edge locations. These control planes serve as mediators between the centralized cloud management system and the distributed edge locations, automating provisioning, configuration, and resource management. This intermediary layer simplifies deployment by providing standardized management interfaces and automated processes, reducing the difficulty of managing geographically distributed edge locations.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Techniques for dynamic resource movement in heterogeneous computing environments including provider substrate extensions are described. A dynamic resource movement service of a provider network monitor conditions of heterogeneous computing environments, including provider substrate extensions of the cloud provider network, to evaluate customer-provided movement policy conditions governing when to move customer application resources from these environments, where to move the resource to, and/or how to move the customer application resources. The customer-provided movement policy conditions may be based on a variety of factors, such as a latency between end-users of the customer application and the application itself.