Cellular Beam Pattern Analysis for Aerial UE Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing techniques for distinguishing aerial UEs from terrestrial UEs in cellular networks face challenges, particularly in handover regions where Reference Signal Received Power (RSRP) gaps are close to zero, leading to inadequate detection accuracy and interference issues.

Innovation Solution

A method using beam detection patterns and an aerial UE detection model, trained on historical data or environmental information, to classify UEs based on unique beam identifiers and patterns characteristic of aerial UEs in flight, employing machine learning models and beamforming techniques.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If RSRP gap measurement is used to distinguish aerial UEs from terrestrial UEs, then detection can be performed with simple metrics, but detection accuracy deteriorates in handover regions where RSRP gap is close to zero for both types of UEs

Engineering Contradiction:

Improvedetection mechanism complexityVSAvoidaerial UE detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the detection process into multiple independent measurement components: RSRP gap measurement, beam detection pattern analysis, and machine learning-based classification. By dividing the detection task into separate measurable parameters, the system achieves better discrimination accuracy without requiring a single complex measurement mechanism.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent changes from relying on a single parameter (RSRP gap) to using multiple parameters including beam detection patterns, number of detected beams, and machine learning model outputs. This multi-parameter approach allows the system to distinguish aerial UEs from terrestrial UEs even in handover regions where RSRP gap alone is insufficient.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If aerial UEs are not properly identified and classified, then standard service policies apply to all UEs, but interference to ground UEs increases and service optimization for aerial UEs cannot be provided

Engineering Contradiction:

Improvenetwork service efficiencyVSAvoidinterference to ground UEs

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent implements a feedback mechanism where the network receives beam detection patterns from UEs, processes them through a machine learning model, and uses the classification result to apply appropriate service policies. This closed-loop system enables the network to adjust resource allocation and interference management based on real-time UE classification, thereby optimizing service for aerial UEs while protecting ground UEs from interference.

Inventive Principle:

Principle #23Feedback

3Ease of operation

If direct indication mechanisms are used for aerial UEs to inform the network of flying mode, then identification is straightforward for registered aerial UEs, but legacy UEs and rogue aerial UEs cannot be identified

Engineering Contradiction:

Improveaerial UE identification simplicityVSAvoidcompatibility with legacy and unregistered UEs

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent enables aerial UEs to automatically reveal their status through their beam detection patterns without requiring explicit indication mechanisms. The machine learning model analyzes these passive measurements and automatically classifies the UE type. This self-service approach works for all UEs including legacy devices and rogue aerial UEs that cannot or do not provide direct indication.

Inventive Principle:

Principle #25Self-service

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enhances detection accuracy by identifying distinct beam patterns of aerial UEs, reducing interference, and enabling efficient service optimization for both aerial and terrestrial UEs.

Implementation Method 1

employing machine learning models and beamforming techniques

Methodology Applied

Scientific EffectBeamforming:

Implementation Method 2

signals from the aerial UE become more visible to multiple cells due to line-of-sight propagation conditions

Methodology Applied

Scientific EffectLine-of-sight propagation:

Implementation Method 3

As base station antennas are typically tilted downwards to the ground, or at least down below the base station antenna height

Methodology Applied

Scientific EffectAntenna tilt:

Implementation Method 4

classify the UE as an aerial UE when the one or more beams identified by the one or more beam identifiers detected by the UE reflect a beam detection pattern that is predetermined to be representative for aerial UEs in flight

Methodology Applied

Scientific EffectMachine learning pattern recognition:

Data Source

PatentEP3949163B1Technique for classifying a UE as an aerial ue

Publication Date: 2025.08.27 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

Figure 1
Figure 2
Figure 3

AI summary

A technique for classifying a User Equipment, UE, connected to a cellular network as an aerial UE is disclosed. A method implementation of the technique is performed by a network node of the cellular network and comprises receiving (S302) one or more beam identifiers detected by the UE and identifying one or more beams transmitted by at least one base station of the cellular network, and classifying (S304) the UE using an aerial UE detection model configured to classify the UE as an aerial UE when the one or more beams identified by the one or more beam identifiers detected by the UE reflect a beam detection pattern that is predetermined to be representative for aerial UEs in flight.