Time-Domain Beam Prediction Configuration for Lower DL-RS Overhead

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current wireless communication systems face inefficiencies in beam management due to high signaling overhead and latency, especially in high-frequency ranges, and lack consistent measurement configurations for AI/ML-based time-domain beam predictions, leading to inconsistencies between wireless devices and network nodes.

Innovation Solution

Implementing methods and configurations for wireless devices to perform time-domain predictions of beam measurements, allowing devices to transmit prediction information instead of measurement results, reducing the need for unnecessary DL-RS transmissions and lowering energy consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional beam management procedures are used with periodic DL-RS transmissions, then beam measurement accuracy is maintained, but signaling overhead and latency increase

Engineering Contradiction:

Improvebeam measurement accuracyVSAvoidsignaling overhead

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The system performs beam measurements and AI/ML-based predictions in advance before they are actually needed for transmission. The WD performs measurements on DL-RS resources and generates prediction results that are stored and used later, eliminating the need for repeated periodic transmissions and reducing signaling overhead while maintaining measurement accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of transmitting actual beam measurement results periodically, the system uses AI/ML models to generate prediction copies of future beam quality values based on historical measurement data. This allows the network to obtain accurate beam information without requiring repeated physical transmissions of reference signals

Inventive Principle:

Principle #26Copying

2Reliability

If frequent DL-RS transmissions are performed for beam measurements, then beam management accuracy is improved, but energy consumption increases

Engineering Contradiction:

Improvebeam management accuracyVSAvoidenergy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

Beam measurements are performed in advance when conditions are favorable, and the results are cached and reused through AI/ML predictions. This eliminates the need for continuous frequent transmissions, significantly reducing energy consumption while maintaining beam management accuracy through predictive modeling

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of continuous periodic transmissions, the system uses event-triggered measurements combined with AI/ML predictions. Measurements are performed periodically or event-driven, and AI/ML models generate intermediate prediction results, reducing the frequency of actual transmissions and energy consumption while maintaining reliability

Inventive Principle:

Principle #19Periodic action

3Quantity of substance

If AI/ML-based time-domain predictions are implemented, then DL-RS overhead is reduced, but measurement configuration consistency issues arise

Engineering Contradiction:

ImproveDL-RS overheadVSAvoidmeasurement configuration consistency

Core Design Contradiction:

Quantity of substanceVSStability of the object's composition

Solution Approach 1:

The patent establishes universal measurement configuration rules that work for both traditional periodic beam management and AI/ML-based predictive beam management. The configuration includes standardized parameters such as measurement bandwidth, time averaging, and reporting formats that ensure consistency across different operation modes, allowing the system to reduce DL-RS overhead while maintaining configuration stability

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system dynamically adjusts measurement configuration parameters based on the operational mode. When AI/ML predictions are enabled, parameters such as measurement frequency, averaging window size, and prediction horizon are optimized to ensure consistency between predicted and actual measurements, reducing overhead while maintaining stability

Inventive Principle:

Principle #35Parameter changes

4Productivity

If beam predictions are performed for future time instances, then beam management efficiency is improved, but prediction accuracy requirements increase

Engineering Contradiction:

Improvebeam management efficiencyVSAvoidprediction accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system performs predictions for multiple future time instances beyond what is immediately needed. By generating predictions for a horizon longer than required, the system can select the most accurate predictions and use them for current beam management decisions, improving efficiency while managing accuracy requirements through selective usage of prediction results

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20260025180A1Measurement configurations for wireless device (WD)-sided time domain beam predictions

Publication Date: 2026.01.22 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

AI summary

A method, network node and wireless device (WD) for providing measurement configurations for WD-sided time domain beam predictions are disclosed. According to one aspect, a method in a WD includes receiving from the network node a CSI report configuration configuring the WD to report at least one prediction of CSI based at least in pant on a downlink reference signal configuration. The method also includes transmitting to the network node abeam information report including at least one prediction of CSI for at least one future time instance of a first set of at least one future time instance in accordance with the CSI report configuration.