ML Model for Network Device Configuration Consistency Validation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing network device configuration and state validation methods rely on separate utilities for each type of network element, requiring extensive manual effort and user-defined rules, which are inefficient and prone to errors.

Innovation Solution

A machine learning-based method that converts platform-dependent and platform-independent data into key-value pairs, training a software model to learn relationships and validate configurations and states across network devices, enabling automated consistency checking without manual rule definition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If separate consistency checker utilities are implemented for each type of network element, then validation coverage is achieved, but device complexity and manual effort increase significantly

Engineering Contradiction:

Improvevalidation coverageVSAvoidnumber of separate utilities

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple separate consistency checker utilities into a single unified machine learning model. The model accepts various network element data types (IP addresses, MAC addresses, interfaces, port aggregations) as input features and performs consistency validation across all network element types simultaneously, eliminating the need for multiple discrete utilities while maintaining comprehensive validation coverage

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The machine learning model is designed as a universal validation system that can handle multiple network element types and consistency check scenarios through a single model instance. The model uses platform-dependent and platform-independent features to perform diverse consistency validations, making it adaptable to different network element types without requiring separate specialized utilities for each

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If manual rule definition is used for consistency checking, then validation accuracy can be controlled, but productivity and ease of operation deteriorate due to extensive manual effort

Engineering Contradiction:

Improvevalidation accuracyVSAvoidvalidation speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system employs a machine learning model that automatically learns consistency rules and patterns from training data without requiring manual rule definition. The model self-adapts to validate network element configurations by processing platform-dependent and platform-independent features, eliminating the need for extensive manual rule creation while maintaining high validation accuracy through learned patterns

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The machine learning model is pre-trained on comprehensive dataset containing platform-dependent and platform-independent features before deployment. This preliminary training action enables the model to automatically apply learned consistency patterns during validation operations, achieving both high accuracy and productivity without requiring manual rule definition during actual validation operations

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If user-defined rules are used for validation, then adaptability to specific cases is improved, but ease of operation and reliability worsen due to errors in manual rule creation

Engineering Contradiction:

Improvecase-specific validationVSAvoiderror rate in manual rules

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The machine learning model automatically discovers and learns consistency patterns from training data specific to different network element types and configurations. Instead of relying on users to manually define case-specific rules, the model self-adapts to various validation scenarios by processing platform-dependent and platform-independent features, eliminating manual rule creation errors while maintaining case-specific adaptability through learned patterns

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS10530662B2Machine learning method to validate run-time rules and detect software/hardware consistency errors for network elements

Publication Date: 2020.01.07 CISCO TECHNOLOGY INC

AI summary

A computer-implemented method includes: obtaining platform dependent data and platform independent data from each of a plurality of first network devices for a computer network environment. The received platform dependent data and platform independent data are converted to key-value pairs. Sequences of the key-value pairs representing the configurations and states of the respective first network device are created. Vectors for the sequences of the key-value pairs are generated in a vector space. The vectors are supplied to a model to train the model to learn relationships of the platform dependent data and platform independent data of each of the plurality of first network devices. Platform dependent data and platform independent data from one or more second network devices are supplied to the trained software model to determine consistency of configurations and states of the one or more second network devices.