Orthogonal Switching Network for Cloud Scalability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current telecommunications networks face challenges in scaling to high capacity while maintaining simplicity and performance, particularly due to the rapid growth of the Internet, which leads to increased complexity and deterioration in performance as the number of switching stages increases.

Innovation Solution

A large-scale network architecture that utilizes access nodes, primary switches, and secondary switches with orthogonal connectivity, allowing for routing of data through a distributed single-stage connector, reducing the number of switching stages and enhancing performance by using fast optical primary switches and bufferless optical connections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If the number of switching stages is increased to achieve high capacity and wide coverage, then the network dimension and capacity increase, but the complexity and performance deterioration

Engineering Contradiction:
Improvenetwork capacityVSAvoidnetwork complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The network is segmented into access nodes, primary switches, and secondary switches with distinct functions. Access nodes handle local connectivity, primary switches provide fast optical switching for most traffic, and secondary switches handle remaining traffic, dividing the complex switching function into manageable segments that scale independently

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces orthogonal connectivity dimensions where access nodes connect to primary switches through orthogonal port sets. This dimensional organization allows the network to scale capacity by adding switches in orthogonal dimensions rather than increasing the number of switching stages linearly, reducing complexity while maintaining growth

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Quantity of substance

If the number of switching stages is increased to achieve large-scale network dimension, then the network can support more access nodes, but the performance deteriorates

Engineering Contradiction:
Improvenumber of access nodesVSAvoidnetwork performance
Core Design Contradiction:
Quantity of substanceVSProductivity

Solution Approach 1:

Traffic is segmented into two categories: most traffic (significant proportion) routes through primary switches with fast optical switching for high performance, while remaining traffic routes through secondary switches. This segmentation ensures that performance is maintained for the majority of traffic even as the network scales to support tens of thousands of access nodes

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Primary switches act as intermediaries between access nodes and the core network, providing fast optical switching that maintains performance. The orthogonal connectivity structure allows primary switches to mediate traffic efficiently without requiring multiple sequential switching stages, preserving performance while enabling large-scale deployment

Inventive Principle:
Principle #24Intermediary (Mediator)

3Quantity of substance

If traditional multi-stage networks are used to achieve high capacity, then the network dimension increases, but the control complexity increases

Engineering Contradiction:
Improvenetwork capacityVSAvoidcontrol complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

Control functions are segmented and distributed to access controllers, primary controllers, and secondary controllers rather than centralized. Each controller manages its local switches and routing, simplifying control complexity while enabling the network to scale to high capacity through distributed autonomous decision-making

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS10129050B2Contiguous network for cloud communications
Publication Date: 2018.11.13 BESHAI MAGED E
  • US10129050B2 patent drawing
  • US10129050B2 patent drawing
  • US10129050B2 patent drawing

AI summary

A network comprises ingress nodes, egress nodes, primary switches, and secondary switches where any pair of an ingress node and an egress node connects to orthogonal sets of primary switches and each secondary switch connects a respective set of primary switches to an orthogonal set of primary switches. Thus, each ingress node has a primary path and numerous compound paths to each egress node. The primary path traverses a respective primary switch, and each compound path traverses a first primary switch, a secondary switch, and a second primary switch. The disclosed connectivity pattern enables network scalability to accommodate hundreds of thousands of ingress-egress node pairs while permitting a significant proportion of incoming data to be routed through the primary switches avoiding the secondary switches.