Access Point Clustering for Wireless Network Configuration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Wireless telecommunications networks face challenges in accurately forecasting traffic growth at individual access points, leading to potential service degradation due to underestimation or wasteful resource allocation due to overestimation.

Innovation Solution

A computer-implemented method using machine learning to determine the configuration of each access point by clustering time-series performance data from multiple access points, allowing for more accurate traffic growth rate estimation and network reconfiguration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If individual access point performance data is analyzed to determine growth rates, then forecasting accuracy is improved, but storage and processing resources are significantly consumed

Engineering Contradiction:
Improvegrowth rate forecasting accuracyVSAvoidstorage and processing resources
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple access points into clusters based on similarity of performance characteristics. Instead of analyzing each access point individually, the system aggregates data at the cluster level, reducing the overall computational burden while maintaining forecasting accuracy through representative cluster profiles.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent segments the network into multiple clusters of access points with similar characteristics. This segmentation allows the system to handle large numbers of access points by processing a smaller number of cluster representatives, thereby reducing storage and processing requirements while preserving individual access point forecasting capability through cluster-based inference.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If a universal growth rate is applied to all access points, then resource consumption is reduced, but forecasting accuracy deteriorates

Engineering Contradiction:
Improveprocessing resourcesVSAvoidgrowth rate forecasting accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies local quality by assigning different growth rates to different clusters of access points based on their specific performance characteristics. Instead of using a single universal growth rate, the system tailors forecasting parameters to local cluster conditions, improving accuracy while maintaining computational efficiency through the cluster-based approach.

Inventive Principle:
Principle #3Local quality

3Reliability

If individual configuration is determined for each access point, then service quality is improved, but operational complexity increases

Engineering Contradiction:
Improveservice qualityVSAvoidconfiguration management
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent merges access points into clusters for configuration purposes. By determining configurations at the cluster level rather than individually, the system reduces operational complexity and ease of management while maintaining service quality through cluster-based configuration strategies that can be applied uniformly to multiple access points with similar characteristics.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP4437750B1Clustering of access points in a wireless telecommunications network and configuration of an access point in a cluster
Publication Date: 2025.05.07 BRITISH TELECOM PLC
  • EP4437750B1 patent drawingFigure 1
  • EP4437750B1 patent drawingFigure 2
  • EP4437750B1 patent drawingFigure 3

AI summary

This invention provides a method of configuring a first access point in a wireless telecommunications network, the first access point being one of a first plurality of access points, the method comprising the steps of: obtaining time-series performance data for each access point of the first plurality of access points; determining a similarity value between the time-series performance data of each access point of the first plurality of access points and the time-series performance data of each other access point of the first plurality of access points using a dynamic time warping technique; based on the similarity values, identifying a first plurality of clusters of the first plurality of access points, the first access point being a member of a first cluster of the first plurality of clusters; identifying a configuration for the first access point based on its association with the first cluster; and causing the identified configuration of the first access point.