Top-of-Rack Switch Tuning With Replicated Wavelength Bands

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing IP fabrics based on Clos switching topologies face challenges with increasing complexity, cost, and latency as spine dedicated devices proliferate, necessitating a more efficient and cost-effective solution for data center networking.

Innovation Solution

Implementing an optical data center fabric (ODCF) with passive optical power splitters to replicate and distribute wavelengths, reducing the need for traditional switches and providing an express path between data center edges and leaf nodes, thus minimizing latency and operational complexity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional IP Clos switching topologies are used to provide multistage circuit switching networks, then host connectivity and routing flexibility are improved, but device complexity and operational costs increase rapidly as spine dedicated devices proliferate

Engineering Contradiction:
Improverouting flexibilityVSAvoidspine device proliferation
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent extracts the active switching function from the spine layer and relocates it to the leaf nodes. The spine layer is reduced to passive optical components (power splitters), eliminating the need for complex spine switches. This extraction resolves the contradiction by maintaining routing flexibility through leaf node intelligence while removing device complexity from the spine layer.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the mechanical/electronic switching system in the spine layer with a passive optical system using power splitters and wavelength multiplexing. This substitution eliminates the need for active spine switches, reducing device complexity while maintaining connectivity through optical wavelength routing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If 5 stage or greater CLOS switching topologies are implemented to deliver required host connectivity, then network coverage is improved, but capital costs and operational complexity explode

Engineering Contradiction:
Improvehost connectivityVSAvoidswitching fabric complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent inverts the traditional Clos architecture by placing active switching intelligence at the leaf nodes rather than in the spine switches. This inversion allows the system to achieve the same host connectivity with fewer stages, as leaf nodes perform the switching functions that would otherwise require multiple spine stages.

Inventive Principle:
Principle #13The other way round (Inversion)

Solution Approach 2:

The patent introduces wavelength multiplexing as an additional dimension for routing. By using multiple wavelengths on the same physical path, the system achieves the connectivity of multiple switching stages without requiring multiple physical stages, effectively compressing the network topology.

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

3Power

If spine dedicated devices are added to increase network capacity, then bandwidth is improved, but latency and failure points increase

Engineering Contradiction:
Improvenetwork bandwidthVSAvoidlatency
Core Design Contradiction:
PowerVSLoss of time

Solution Approach 1:

The patent uses passive optical power splitters that continuously transmit optical signals without conversion or processing delays. The optical signal flows continuously from leaf nodes through the passive spine layer to destination leaf nodes, eliminating the latency introduced by active switching at each spine stage while maintaining high bandwidth through wavelength multiplexing.

Inventive Principle:
Principle #20Continuity of useful action

4Productivity

If more spine switches are deployed to handle increased traffic, then network capacity is improved, but operational complexity and failure points increase

Engineering Contradiction:
Improvenetwork capacityVSAvoidfailure points
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent extracts the active switching function from the spine layer, leaving only passive optical components. This eliminates failure points associated with spine switch hardware, power supplies, and control planes, while maintaining network capacity through wavelength-multiplexed optical paths.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces expensive, complex spine switches with inexpensive passive optical power splitters. These passive components have no moving parts, no power requirements, and极高的 reliability, effectively serving as disposable, maintenance-free infrastructure that can be deployed in large numbers without increasing operational complexity.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The ODCF reduces capital and operational costs while significantly decreasing latency and simplifying network topology, enabling easier scaling and troubleshooting, suitable for high-bandwidth applications like cloud gaming and financial services.

Implementation Method 1

a power splitter coupled to the hub optical transceiver. The power splitter operates as a passive device that is configured to replicate the spectrum of wavelengths and output a plurality of replicated spectrum of wavelengths. Each replicated spectrum of wavelengths of the plurality of replicated spectrum of wavelengths has a corresponding power that is a fraction of a total power received from the hub optical transceiver.

Methodology Applied
Scientific EffectOptical power splitting:

Implementation Method 2

a hub optical transceiver configured for receiving a spectrum of wavelengths

Methodology Applied
Scientific EffectOptical transmission: Optical Fibre

Implementation Method 3

Each spoke transceiver is configured to receive a corresponding one of the plurality of replicated spectrum of wavelengths. Each spoke transceiver is tunable to select a band of wavelengths that set a bandwidth for the each spoke transceiver.

Methodology Applied
Scientific EffectOptical wavelength detection:

Data Source

PatentUS12413313B2Top-of-rack switch of a rack assembly tuned to receive a band of wavelengths from a replicated spectrum of wavelengths provided by a power splitter
Publication Date: 2025.09.09 SONY INTERACTIVE ENTERTAINMENT LLC
  • US12413313B2 patent drawing
  • US12413313B2 patent drawing
  • US12413313B2 patent drawing

AI summary

An optical communication system including a hub optical transceiver, a power splitter, and a plurality of spoke transceivers. The hub optical transceiver is configured for receiving a spectrum of wavelengths. The power splitter is coupled to the hub optical transceiver, and operates as a passive device that is configured to replicate the spectrum of wavelengths and output a plurality of replicated spectrum of wavelengths, and each replicated spectrum of wavelengths has a corresponding power that is a fraction of a total power received from the hub optical transceiver. The plurality of spoke transceivers is coupled to the power splitter and each of the plurality of spoke transceivers is configured to receive a corresponding one of the plurality of replicated spectrum of wavelengths, wherein each spoke transceiver is tunable to select a band of wavelengths that set a bandwidth for the each spoke transceiver.