SON Facilitator API for Wireless Network Configuration Automation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current 4G wireless networks are inadequate for handling the increased data bandwidth and latency demands of emerging applications like ultra-high definition video streaming, autonomous vehicles, and IoT devices, and the challenges of higher frequency EM signals, such as mmW, include rapid attenuation and complexity in managing thousands of configurable network parameters.

Innovation Solution

A self-organizing network (SON) enhancement mechanism using artificial intelligence (AI) and multiple wireless connections to automate network configuration adjustments, ensuring quality of service (QoS) by maintaining one stable connection while testing alternative configurations on another.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Power

If higher frequency EM signals (mmW) are used to attain higher data bandwidth, then data bandwidth is improved, but signal attenuation increases rapidly

Engineering Contradiction:
Improvedata bandwidthVSAvoidsignal attenuation
Core Design Contradiction:
PowerVSLoss of energy

Solution Approach 1:

The patent divides the network into multiple small cells rather than using a single large cell. This segmentation allows the use of higher frequency mmW signals over shorter distances, reducing attenuation while maintaining high bandwidth. Multiple base stations are deployed to cover different geographic areas, each handling traffic locally before backhauling to the core network.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements local processing and caching at edge base stations rather than requiring all data to traverse the entire network. This local quality enhancement reduces the burden on high-frequency links by handling traffic locally when possible, reserving mmW connections for essential high-bandwidth operations.

Inventive Principle:
Principle #3Local quality

2Reliability

If manual adjustment of network parameters is performed to optimize performance, then network performance can be improved, but the complexity and time required increases significantly

Engineering Contradiction:
Improvenetwork performanceVSAvoidparameter management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements self-organizing network (SON) capabilities that enable base stations to automatically configure and optimize their own parameters. The system autonomously performs neighbor relationship configuration, parameter optimization, and performance monitoring without manual intervention, reducing operational complexity while maintaining high network performance.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent employs closed-loop feedback mechanisms where network performance is continuously monitored and automatically adjusted. The system collects performance data, analyzes it using machine learning algorithms, and dynamically optimizes parameters such as handover thresholds, power levels, and resource allocation based on real-time conditions.

Inventive Principle:
Principle #23Feedback

3Productivity

If comprehensive network parameter optimization is attempted, then network performance improves, but the time required for configuration and testing increases

Engineering Contradiction:
Improvenetwork performanceVSAvoidconfiguration time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent pre-configures base stations with essential parameters and templates during deployment. Neighbor relationships, basic power settings, and operational parameters are established in advance, allowing rapid network deployment and reducing the time required for initial configuration and commissioning.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system performs automatic parameter optimization and performance tuning after deployment, eliminating the need for lengthy manual configuration phases. Machine learning algorithms continuously learn from network behavior and automatically adjust parameters to optimize performance, reducing both configuration time and ongoing operational overhead.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3884697B1Facilitating self-organizing network (SON) enhancement
Publication Date: 2025.07.02 GOOGLE LLC
  • EP3884697B1 patent drawingFigure 1
  • EP3884697B1 patent drawingFigure 2
  • EP3884697B1 patent drawingFigure 3

AI summary

Wireless networks may have thousands of configurable parameters, so manual tuning is infeasible. A self-organizing network (SON) can provide automation. However, automated algorithms are not designed to interact with a wireless network, and network experimentation can jeopardize reliability. To address the former, a SON facilitator (332) of a wireless network management node (122) exposes an API (506) that can translate network configuration information (512) for consumption by a SON enhancer (504), which may implement an AI algorithm for network tuning. The SON facilitator can also transform output from the SON enhancer into directions for controlling a test scenario (502), including generating a DL SON message (524) describing the test to a UE (102). To further increase reliability during the test scenario, the UE can be provisioned with two wireless connections (310). A first connection is unchanged by the test scenario for stability, and a second connection is used for testing.