ASIC Interface Controller for Low Latency Mesh Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing mesh networks face performance degradation due to increased network traffic, particularly in real-time services like VoIP, as they incur significant packet forwarding delays, limiting the network to about 8 hops due to computing overhead, which is inadequate for scalable and efficient communication.

Innovation Solution

An interface controller implemented as an Application Specific Integrated Circuit (ASIC) with programmable building blocks, comprising MAC and Network Processor cores, optimized for low power consumption and fast packet forwarding, capable of handling up to 10,000 nodes with reduced latency, enabling efficient routing and minimizing host processor involvement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If mesh networks use standard packet forwarding with host processor involvement, then routing flexibility is maintained, but packet forwarding latency increases significantly

Engineering Contradiction:
Improvepacket forwarding latencyVSAvoidhost processor involvement
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The patent extracts packet forwarding functionality from the host processor into a dedicated network processor core. This separate core handles packet routing independently, removing the latency burden from the host processor while maintaining routing flexibility through programmable logic.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The network processor core acts as an intermediary between the host processor and network interfaces. It handles time-critical packet forwarding operations, allowing the host processor to focus on higher-level tasks while ensuring low-latency packet handling through specialized processing.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Quantity of substance

If mesh networks support more hops to increase node capacity, then network scalability improves, but packet forwarding delays accumulate

Engineering Contradiction:
Improvenumber of supported nodesVSAvoidend-to-end forwarding delay
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The patent segments the network processing function into distributed network processor cores at each node. Each core independently handles packet forwarding with minimal delay, allowing packets to traverse many hops (100+) without cumulative latency degradation that would occur with centralized host processor handling at each node.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The network processor core performs packet forwarding in advance of host processor intervention. By handling routing decisions and packet transmission before higher-level processing is needed, the system minimizes per-hop latency and enables support for extensive multi-hop networks.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If full-featured network processors are used to handle complex routing, then routing capability is enhanced, but power consumption increases

Engineering Contradiction:
Improverouting capabilityVSAvoidpower consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The patent segments network processing into two parts: a lightweight network processor core for time-critical packet forwarding operations, and a full-featured host processor for higher-level networking tasks. This segmentation allows the system to use minimal power for routine packet handling while retaining full routing capability when needed.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The network processor core provides localized, optimized processing for packet forwarding at each network node. Instead of using full-power processors at every node, the system applies processing power locally only where and when needed, reducing overall network power consumption while maintaining routing versatility.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS7693167B2Mobile nodal based communication system, method and apparatus
Publication Date: 2010.04.06 ROCKWELL COLLINS INC
  • US7693167B2 patent drawing
  • US7693167B2 patent drawing
  • US7693167B2 patent drawing

AI summary

An improved micro architectural approach for a network microprocessor has low power consumption, and employs two specialized processing cores, a MAC processing core and a network processor core. Each of these processing cores has facilities designed for a specific set of functions, to handle ISO layer 2 and layer 3 functionality in a packet switched Software Defined Radio mobile network.