Network Status Mapping via Dynamic Packet Rerouting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Congestion in computer networks occurs due to multiple stations sending packets along the same nodes or hops, and speed mismatches between network input and output ports or links, leading to slowed transmission and packet loss.

Innovation Solution

A network map tag is inserted into packets to monitor congestion status, allowing a network controller to reroute packets based on a congestion map formed from compiled information, ensuring optimal path selection and load balancing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple stations send packets along the same nodes or hops, then network throughput increases, but congestion occurs at these nodes or hops

Engineering Contradiction:
Improvenetwork throughputVSAvoidcongestion
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements dynamic path selection by continuously monitoring queue depth at network nodes and adjusting packet routing in real-time. The controller dynamically switches packets between different paths based on current congestion conditions, transforming static routing into adaptive routing that responds to changing network states.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent employs feedback mechanisms where network nodes report their queue depth status back to the controller, which then uses this information to make informed routing decisions. This closed-loop feedback system enables the network to respond to congestion conditions and adjust traffic distribution accordingly.

Inventive Principle:
Principle #23Feedback

2Productivity

If packets are routed through congested nodes, then path utilization increases, but transmission speed decreases

Engineering Contradiction:
Improvepath utilizationVSAvoidtransmission speed
Core Design Contradiction:
ProductivityVSSpeed

Solution Approach 1:

The system dynamically adjusts routing decisions based on real-time congestion detection. When a node is detected to be congested (high queue depth), the controller dynamically redirects packets to alternative less-congested paths, optimizing transmission speed while maintaining acceptable path utilization.

Inventive Principle:
Principle #15Dynamics

3Reliability

If congestion control mechanisms are implemented, then packet loss decreases, but network complexity increases

Engineering Contradiction:
Improvepacket lossVSAvoidnetwork complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces a dedicated controller as an intermediary component that centralizes congestion management functions. This controller collects queue depth information from network nodes, processes routing decisions, and manages packet forwarding, thereby simplifying the overall network architecture while effectively reducing packet loss.

Inventive Principle:
Principle #24Intermediary (Mediator)

4Measurement precision

If real-time monitoring of network status is implemented, then routing accuracy improves, but overhead increases

Engineering Contradiction:
Improverouting accuracyVSAvoidmonitoring overhead
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent implements partial monitoring by focusing measurement and reporting only on critical parameters such as queue depth at network nodes, rather than monitoring all possible network states. This selective monitoring approach provides sufficient routing accuracy while minimizing the overhead associated with comprehensive real-time monitoring.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS8976697B2Network status mapping
Publication Date: 2015.03.10 AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE LTD
  • US8976697B2 patent drawing
  • US8976697B2 patent drawing
  • US8976697B2 patent drawing

AI summary

Embodiments of the present disclosure provide systems and methods for network status mapping. Such an exemplary system and method involves inserting a network map tag in a flow set of packets in a computer network and receiving a response to the network map tag from a network element that includes populated fields of the network map tag comprising a field to identify a network element, a field to identify the outgoing port of the network element, a field to identify queue of the outgoing port; and a status field for the queue of the outgoing port.