UE Measurement Reporting for AI-Driven 5G Cell Energy Saving

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing 3GPP networks face challenges in efficiently implementing network energy saving (NES) techniques, particularly in 5G systems, as switching off cells can lead to increased power consumption in neighboring cells and overhead signaling, and there is a lack of specific AI/ML implementations to address these issues.

Innovation Solution

A method involving UE measurement reports, model training, and inference functions using AI/ML to predict and optimize energy-saving strategies by analyzing expected data communication parameters, such as uplink/downlink data arrival times and packet sizes, to determine optimal cell activation/deactivation patterns and handover decisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If a cell is switched off to save energy, then energy consumption of that cell is reduced, but power consumption of neighboring cells increases and signaling overhead increases

Engineering Contradiction:

Improveenergy consumptionVSAvoidsignaling overhead

Core Design Contradiction:

Loss of energyVSObject-generated harmful factors

Solution Approach 1:

The system performs preliminary actions by collecting measurement data from UEs about expected data communication patterns before making cell switching decisions. This advance data gathering enables more informed decisions that can predict when cells will be needed, reducing unnecessary handover signaling and energy waste from premature cell shutdowns.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where UE measurement reports about expected data communication are continuously fed back to the network. This feedback loop allows the network to adjust cell activation decisions based on actual traffic patterns, reducing both energy consumption and signaling overhead by making more accurate predictions about when cells will be needed.

Inventive Principle:

Principle #23Feedback

2Loss of energy

If a cell is switched off to save energy, then energy consumption of that cell is reduced, but power consumption of neighboring cells increases

Engineering Contradiction:

Improveenergy consumptionVSAvoidpower consumption of neighboring cells

Core Design Contradiction:

Loss of energyVSUse of energy by stationary object

Solution Approach 1:

The system collects measurement data from UEs in advance about their expected data communication patterns with the network. This preliminary information gathering allows the network to predict future traffic demands and make more accurate decisions about cell activation, avoiding the scenario where neighboring cells must suddenly increase power consumption to handle unexpected traffic loads.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts cell activation decisions based on real-time measurement data from UEs about expected data communication. This dynamic approach allows the network to optimize energy consumption by activating cells only when predicted traffic patterns indicate they will be needed, rather than using static thresholds that may cause neighboring cells to over-compensate with increased power consumption.

Inventive Principle:

Principle #15Dynamics

3Measurement precision

If AI/ML is implemented for energy saving decisions, then energy optimization accuracy is improved, but system complexity increases

Engineering Contradiction:

Improveenergy optimization accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system introduces an intermediary measurement data collection mechanism where UEs provide information about their expected data communication patterns. This intermediary layer simplifies the AI/ML implementation by providing pre-processed, relevant input data, reducing the complexity of the machine learning models needed while maintaining high energy optimization accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20260006547A1Method, model training function and model inference function

Publication Date: 2026.01.01 NEC CORP

AI summary

The method performed by a User Equipment, UE. Is disclosed, in which the method comprises the step of receiving, from an access network node, a measurement configuration for requesting information relating to expected data communication with the access network node; and transmitting, to the access network node, a measurement report including the information, wherein the information is used for outputting at least one parameter using a model for energy saving.