Shortest Path Routing in Multi-Access Cloud Nodes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Cloud service networks face inefficiencies and high latency due to administrators' inability to control the location of geographically dispersed access nodes, leading to suboptimal routing and increased network hops.

Innovation Solution

Implementing a shortest path algorithm that uses utilities like traceroute to identify local nodes with fewer hops, grouping them for service provision, and managing them in a round-robin scheme to reduce latency and improve efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If administrators configure access nodes in multi-tenant cloud systems, then resource sharing and multi-tenancy are enabled, but network latency increases due to inability to control physical location of access nodes

Engineering Contradiction:

Improvemulti-tenancy capabilityVSAvoidnetwork latency

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system implements feedback by continuously monitoring network hop counts from hosts to access nodes using traceroute utilities. This feedback mechanism enables the cloud service to identify which access nodes are physically closer to which hosts, and dynamically route requests through optimal nodes, thereby reducing latency while maintaining multi-tenancy architecture

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The invention changes the routing parameter from static administrator-configured paths to dynamic shortest-path routing based on actual network hop counts. By calculating and utilizing hop count metrics, the system adapts route selection to minimize physical distance traversed, reducing latency without compromising multi-tenancy resource sharing

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If access nodes are geographically dispersed to serve global customers, then service coverage is improved, but network efficiency deteriorates due to increased number of hops

Engineering Contradiction:

Improveglobal service coverageVSAvoidnetwork efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system applies local quality by identifying and prioritizing access nodes that are locally closer to specific hosts. Rather than treating all access nodes uniformly, the system determines hop counts to each node and selects locally optimal nodes for routing, thereby improving network efficiency while maintaining global service coverage through distributed node deployment

Inventive Principle:

Principle #3Local quality

3Productivity

If shortest path routing is implemented to reduce latency, then network efficiency improves, but system complexity increases due to need for path calculation and node management

Engineering Contradiction:

Improvenetwork efficiencyVSAvoidrouting management complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system implements self-service by automatically performing traceroute operations to discover hop counts between hosts and access nodes. The cloud service itself conducts the path discovery and maintains routing information without requiring external manual configuration, thereby reducing the complexity burden on administrators while achieving efficient shortest-path routing

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS9537748B1Finding shortest path in multi-access nodes in cloud service

Publication Date: 2017.01.03 EMC IP HLDG CO LLC

AI summary

This disclosure relates to a method, article of manufacture, and apparatus for finding a shortest path in a cloud. In some embodiments, this includes obtaining one or more nodes associated with a tenant, obtaining hop counts for each of the one or more nodes, determining a threshold hop count based on the hop counts, identifying one or more local nodes based on the threshold hop count, and associating the one or more local nodes with the tenant.