ML Cross-Layer Connectivity Discovery for Network Inventory Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional networking systems lack automated solutions for discovering cross-layer connectivity links between different layers in networks, leading to potential mistakes and omissions in inventory databases, which can result in discrepancies between stored and actual network topologies.

Innovation Solution

The implementation of Machine Learning (ML) processes within a Network Management System to automatically discover cross-layer port-to-port connectivity links between Network Elements operating in multiple layers by analyzing performance metrics and traffic patterns, reducing the need for constant human interaction and improving inventory accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual methods are used to create and update inventory database, then flexibility and adaptability are maintained, but mistakes and omissions occur leading to discrepancies between stored and actual topology

Engineering Contradiction:

Improveaccuracy of inventory dataVSAvoidautomation of topology discovery

Core Design Contradiction:

ReliabilityVSExtent of automation

Solution Approach 1:

The system performs self-service by automatically discovering cross-layer topology and updating inventory database without human intervention. The ML model autonomously analyzes network data, identifies connectivity patterns, and maintains inventory accuracy, eliminating manual errors while achieving high reliability

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical processes of inventory updating are replaced with automated ML-based discovery system. The system substitutes human operators with intelligent algorithms that continuously monitor network state and automatically update topology information, improving both accuracy and automation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual updating of inventory database is performed, then control and verification are possible, but time consumption and productivity are reduced

Engineering Contradiction:

Improvespeed of topology discoveryVSAvoidtime for manual inventory maintenance

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary action by continuously monitoring network data and proactively discovering topology changes before they need to be manually updated. The ML model is trained in advance and automatically detects connectivity patterns, eliminating the need for time-consuming manual inventory maintenance

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The topology discovery process operates continuously without interruption. The ML model constantly analyzes network traffic and performance data, maintaining up-to-date inventory information in real-time, thereby maximizing productivity while minimizing time loss through uninterrupted automated operation

Inventive Principle:

Principle #20Continuity of useful action

3Ease of operation

If inventory database is manually maintained, then detailed control is achievable, but complexity of operation increases and errors are introduced

Engineering Contradiction:

Improvesimplicity of inventory managementVSAvoidcomplexity of cross-layer topology

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The ML model acts as an intermediary between complex network data and simple inventory management. It processes complex cross-layer connectivity information and transforms it into manageable inventory records, simplifying operation while handling underlying complexity automatically

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates accurate copies of actual network topology in the inventory database through automated discovery. Instead of manual transcription which introduces errors and complexity, the ML model generates precise digital representations of physical connections, simplifying inventory management while accurately reflecting network complexity

Inventive Principle:

Principle #26Copying

Data Source

PatentUS11057278B1Discovery of port-to-port connectivity across network layers using machine learning

Publication Date: 2021.07.06 CIENA CORP

AI summary

Systems and methods for discovering the connectivity topology of cross-layer links in a multi-layer network are provided. In one implementation, a method includes a step of obtaining input data related to a plurality of Network Elements (NEs) operating in a plurality of layers within a multi-layer network having one or more cross-layer port-to-port connectivity links therebetween. The method also includes the step of utilizing Machine Learning (ML) processes and the input data to discover the one or more cross-layer port-to-port connectivity links between pairs of NEs operating in different layers of the plurality of layers within the network.