Dynamic Network Performance Assessment and Selective Remediation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Managing and maintaining large-scale Wi-Fi networks is challenging due to difficulties in determining the relationship between configuration changes and communication performance, leading to false positives, reduced performance, and increased costs, with existing detection techniques often resulting in inaccurate diagnostics and remedial actions.

Innovation Solution

A computer system that dynamically assesses communication performance, detects network problems, and recommends configuration changes using machine-learning models to improve network performance, while allowing for selective undoing of changes based on performance metrics and user input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If configuration changes are made to improve network performance, then communication performance may be improved, but false positives and inaccurate detection increase

Engineering Contradiction:

Improvecommunication performanceVSAvoiddetection accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The system implements closed-loop feedback by continuously monitoring network performance metrics after configuration changes are applied. The machine learning model receives feedback about the actual impact of changes and uses this information to refine future recommendations, reducing false positives while maintaining performance improvements.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs self-diagnosis and self-optimization by automatically detecting network problems, generating configuration changes, applying them, and evaluating their impact without human intervention. This automated closed-loop process reduces detection errors by continuously learning from actual network behavior.

Inventive Principle:

Principle #25Self-service

2Loss of time

If automated remedial actions are implemented, then response time is reduced, but network stability may be compromised

Engineering Contradiction:

Improveresponse timeVSAvoidnetwork stability

Core Design Contradiction:

Loss of timeVSStability of the object's composition

Solution Approach 1:

The system performs preliminary testing and validation of configuration changes in a simulated or controlled environment before applying them to the production network. This advance preparation reduces response time by having ready-to-deploy solutions while maintaining stability through careful pre-validation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements rollback mechanisms and safety buffers that allow automated remediation while protecting network stability. If an automated change causes instability, the system can automatically revert to the previous stable configuration, cushioning the impact on network stability.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

3Measurement precision

If manual analysis and root-cause investigation are performed, then detection accuracy improves, but operational complexity and cost increase

Engineering Contradiction:

Improvedetection accuracyVSAvoidoperational complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The machine learning model acts as an intermediary between raw network data and human operators. It automatically performs complex analysis, pattern recognition, and root-cause identification, presenting simplified findings and recommendations to operators. This maintains high detection accuracy while reducing operational complexity by offloading the analytical burden to the AI system.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Measurement precision

If extensive network monitoring is implemented, then problem detection accuracy improves, but system resource consumption increases

Engineering Contradiction:

Improveproblem detection accuracyVSAvoidsystem resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system implements selective monitoring that focuses computational resources on the most critical network metrics and anomalies rather than uniformly monitoring all parameters. The machine learning model identifies and prioritizes the subset of metrics that provide the highest detection value, maintaining accuracy while reducing overall resource consumption by avoiding excessive monitoring of less important parameters.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20240195687A1Dynamic assessment of network performance and selective remediation recommendations

Publication Date: 2024.06.13 RUCKUS IP HOLDINGS LLC

AI summary

A computer system is described. During operation, the computer system may receive information specifying communication in a network. Then, the computer system may detect a network problem based at least in part on the information. Moreover, the computer system may automatically determine a remedial action based at least in part on the detected network problem and may automatically perform the determined remedial action. Alternatively, when the remedial action cannot be determined, the computer system may selectively collect additional information for a predefined time interval, e.g., using one or more edge electronic devices or one or more controllers in the network. Next, the computer system may diagnose the network problem and may compute a second remedial action based at least in part on the diagnosis of the network problem. After receiving approval the computer system may automatically perform the second remedial action when a subsequent instance of the network problem is detected.