Latency-Based Georouting for Edge Server Node Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Centralized cloud systems face challenges in managing and processing data from edge devices due to increased latency and bandwidth limitations, as well as the need for constant maintenance in anycast routing systems, which are not aware of physical distances and can result in suboptimal routing.

Innovation Solution

A globally distributed edge computing platform using latency-based georouting to locate server nodes for edge devices, which reduces latency and increases network throughput by deploying serverless functions and recording each request on a blockchain for secure and immutable execution, compatible with cloud infrastructures like Google Cloud, AWS, and Microsoft Azure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a centralized cloud cluster approach is used, then resource aggregation and management are simplified, but latency increases for users far from the centralized location

Engineering Contradiction:

Improveresource management complexityVSAvoidlatency

Core Design Contradiction:

Device complexityVSLoss of time

Solution Approach 1:

The patent segments the centralized cloud cluster into multiple distributed edge nodes deployed at different geographic locations. Each edge node independently handles requests from local users, eliminating the need for all traffic to route through a single centralized location, thus reducing latency while maintaining manageable resource distribution across multiple sites

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements local quality by deploying computing resources closer to end users at edge locations. Each edge node provides localized resource execution tailored to its geographic position, enabling users to access computing power from nearby nodes rather than traveling to a distant centralized cluster, thereby reducing network latency

Inventive Principle:

Principle #3Local quality

2Extent of automation

If anycast routing is used, then routing decisions are automated, but the system becomes suboptimal because it ignores physical distances

Engineering Contradiction:

Improverouting automationVSAvoidrouting optimality

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The patent introduces latency measurement as an intermediary factor between routing automation and physical distance. Edge nodes measure actual network latency to users and use this measured latency data to inform routing decisions, bridging the gap between automated routing and physical proximity considerations

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent implements feedback mechanisms where edge nodes continuously monitor network conditions and latency to users. This feedback information is used to dynamically adjust routing decisions, ensuring that traffic is directed to the optimal edge node based on real-time network performance rather than static anycast configuration alone

Inventive Principle:

Principle #23Feedback

3Device complexity

If computations are routed away from the user through centralized clusters, then resource consolidation is achieved, but response time increases

Engineering Contradiction:

Improveresource consolidationVSAvoidresponse time

Core Design Contradiction:

Device complexityVSSpeed

Solution Approach 1:

The patent segments the centralized resource pool into distributed edge nodes positioned near users. This segmentation allows computations to be executed locally at edge nodes rather than being consistently routed away through distant centralized clusters, maintaining resource consolidation benefits while significantly improving response time through local execution

Inventive Principle:

Principle #1Segmentation

4Power

If more robust applications with additional resources are deployed, then computing capability increases, but latency increases due to more intensive computations

Engineering Contradiction:

Improvecomputing capabilityVSAvoidlatency

Core Design Contradiction:

PowerVSLoss of time

Solution Approach 1:

The patent applies local quality by deploying computing resources locally at edge nodes positioned close to users. This enables intensive computations to be executed nearby rather than requiring data to travel long distances to centralized clusters, maintaining high computing capability for robust applications while reducing the latency penalty associated with distant resource access

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12058204B1Systems and methods for locating server nodes for edge devices using latency-based georouting

Publication Date: 2024.08.06 EDJX INC

AI summary

Systems for locating server nodes for edge devices using latency-based georouting. A cloud platform including at least one cloud platform router and a node database is in network communication with at least one edge device and server nodes, and receives a hypertext transfer protocol (HTTP) request from the at least one edge device. The database is queried using an application programming interface (API) query and data is fetched from the plurality of server nodes. A query result is returned indicating a nearest node from the server nodes. The HTTP request is responded to with a unique hypertext markup language (HTML) web page. The HTTP request is executed using the nearest node. The API query to the database includes API query parameters, including geolocation for the edge device, which is appended to the API query parameters to a Uniform Resource Identifier (URI).