Adaptive Switch Routing With Neighbor Load Information

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing network architectures face challenges in scalability, versatility, and efficiency due to increasing network load and diverse traffic types from applications like high-performance computing and Internet of Things, with conventional congestion control mechanisms leading to slow responses and inefficient network utilization.

Innovation Solution

Implementing a switch fabric with flow channels that use detailed load information from neighboring switches for adaptive routing, allowing dynamic flow setup and teardown based on traffic demand, and incorporating congestion control mechanisms to manage bandwidth and prioritize traffic classes, reducing reliance on centralized control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional congestion control mechanisms are used, then network architecture simplicity is maintained, but network utilization and response speed deteriorate

Engineering Contradiction:
Improvenetwork utilizationVSAvoidcongestion control mechanism complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements self-service congestion control by enabling each switch to autonomously make routing decisions based on locally maintained load information and received flow requests. Switches independently monitor their own output port loads, maintain flow request queues, and select next-hop switches without requiring centralized control or complex coordination mechanisms, thereby achieving high network utilization through distributed autonomy

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent employs feedback mechanisms where each switch receives flow requests from neighboring switches, processes these requests locally, and generates responses that feed back into the routing decision-making process. The load information is continuously updated based on actual flow processing, creating a closed-loop system that adapts to changing network conditions and optimizes utilization dynamically

Inventive Principle:
Principle #23Feedback

2Speed

If centralized control is used for routing decisions, then control simplicity is maintained, but response speed and network adaptability deteriorate

Engineering Contradiction:
Improveresponse speedVSAvoidcontrol mechanism complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent eliminates centralized control by enabling each switch to autonomously process flow requests, maintain its own routing tables, and make independent routing decisions based on real-time load information. This self-service approach removes the bottleneck of centralized processing, allowing immediate local responses to flow requests and significantly improving response speed

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent segments the routing control function by distributing routing table maintenance and decision-making across individual switches rather than centralizing it. Each switch maintains its own routing information and processes flow requests independently, eliminating the single point of control and enabling parallel processing of multiple flow requests simultaneously

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If detailed load information from neighboring nodes is collected, then routing accuracy is improved, but information overhead and processing complexity increase

Engineering Contradiction:
Improveload measurement accuracyVSAvoidinformation overhead
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent applies local quality by having each switch collect and process only the load information relevant to its own output ports and neighboring switches. Instead of gathering comprehensive global network state, each switch maintains localized routing tables and load metrics, processing only the information needed for local routing decisions. This selective information collection achieves sufficient routing accuracy while minimizing information overhead

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent implements partial action by collecting and processing only the essential load information from neighboring nodes rather than all possible network state data. Each switch maintains routing tables with selective load metrics from neighboring switches, processing just enough information to make accurate routing decisions without the excessive overhead of complete network state awareness

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12386759B2Algorithms for use of load information from neighboring nodes in adaptive routing
Publication Date: 2025.08.12 HEWLETT PACKARD ENTERPRISE DEV LP
  • US12386759B2 patent drawing
  • US12386759B2 patent drawing
  • US12386759B2 patent drawing

AI summary

Systems and methods are provided for passing data amongst a plurality of switches having a plurality of links attached between the plurality of switches. At a switch, a plurality of load signals are received from a plurality of neighboring switches. Each of the plurality of load signals are made up of a set of values indicative of a load at each of the plurality of neighboring switches providing the load signal. Each value within the set of values provides an indication for each link of the plurality of links attached thereto as to whether the link is busy or quiet. Based upon the plurality of load signals, an output link for routing a received packet is selected, and the received packet is routed via the selected output link.