Automated Radio Cell Optimization via ML Root Cause Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Telecommunication carriers face challenges in optimizing radio cell quality and reducing operating expenses due to manual 'best guess' methods in troubleshooting and small cell planning, leading to revenue loss from over-the-top services, necessitating advanced automatic network monitoring and optimization beyond neighbor cell management.

Innovation Solution

A method and system utilizing an automated classification model for root cause analysis of radio access network issues, correlating network monitoring parameters to generate recommendations for optimizing radio access network performance, which includes a processor, memory device, and instructions for receiving user input, identifying parameters, performing analysis, and generating recommendations for improving cell coverage and quality of service.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual 'best guess' methods are used for troubleshooting and small cell planning, then device complexity is reduced, but productivity and network optimization effectiveness deteriorate

Engineering Contradiction:

Improvenetwork optimization effectivenessVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system enables automatic network monitoring and optimization through self-organizing network functions that autonomously analyze performance data, identify issues, and implement corrections without manual intervention, allowing the network to service itself

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual troubleshooting and optimization processes are replaced with automated electronic systems that use machine learning models and algorithms to perform root cause analysis and generate optimization recommendations

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If advanced automatic network monitoring and optimization systems are implemented, then productivity and network performance improve, but device complexity and operating expenses increase

Engineering Contradiction:

Improvetroubleshooting efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The automatic optimization system is divided into hierarchical levels with a high-level SON function (Network Manager) optimizing the overall network and lower-level SON functions at each Network Element locally optimizing individual elements, distributing complexity across multiple manageable components

Inventive Principle:

Principle #1Segmentation

3Measurement precision

If more network monitoring parameters are analyzed, then measurement precision and root cause accuracy improve, but device complexity and processing requirements increase

Engineering Contradiction:

Improveroot cause analysis accuracyVSAvoidprocessing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system extracts and focuses on specific key performance indicators and critical parameters from the vast amount of available network data that are most relevant to particular issues, rather than analyzing all possible parameters equally

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS10966108B2Optimizing radio cell quality for capacity and quality of service using machine learning techniques

Publication Date: 2021.03.30 NETSCOUT SYSTEMS INC

AI summary

A method for optimizing a radio access network includes receiving at least one area of the radio access network to be analyzed from a user and receiving a desired outcome from a user. A plurality of network monitoring parameters related to a user requested analysis is identified. The identified plurality of network monitoring parameters is correlated. A root cause analysis is performed using an automated classification model based on the correlated plurality of network monitoring parameters. A recommendation related to the desired outcome is generated based on the performed root cause analysis.