AI-Guided PRS Measurement Scheduling for UE Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face inefficiencies in positioning measurements due to unnecessary resource consumption and battery power drain when UEs perform frequent positioning measurements without considering channel conditions, leading to unsatisfactory results.
Innovation Solution
Implementing an AI/ML model at the UE to determine whether upcoming positioning reference signals meet quality requirements, allowing the UE to skip measurements when conditions are unsuitable, thereby reducing complexity and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the UE performs frequent positioning measurements without considering channel conditions, then positioning availability is improved, but battery power consumption increases and resource utilization deteriorates
Solution Approach 1:
The system changes the parameter of measurement frequency dynamically based on channel conditions. Instead of performing measurements at fixed intervals, the UE adjusts measurement timing according to PRS quality metrics (RSRP, RSRQ, SINR) and AI/ML predictions, performing measurements only when channel conditions are favorable.
Solution Approach 2:
The UE autonomously determines whether to perform positioning measurements by evaluating channel conditions and AI/ML model predictions without continuous network control. The device self-manages measurement decisions based on local assessments of PRS quality and battery status.
2Measurement precision
If the UE performs frequent positioning measurements, then positioning accuracy is improved, but device complexity and processing overhead increase
Solution Approach 1:
The system performs preliminary assessment of channel conditions using reference signals and AI/ML models before committing to full positioning measurements. The UE evaluates PRS quality metrics and predicts measurement success probability in advance, avoiding unnecessary processing when conditions are poor.
Solution Approach 2:
The patent replaces traditional mechanical/threshold-based measurement triggering with AI/ML model-based predictions. The AI/ML model analyzes channel conditions and predicts whether upcoming PRS will meet quality requirements, substituting complex rule-based decision logic with learned patterns.
3Area of stationary object
If the UE performs positioning measurements in unfavorable channel conditions, then measurement coverage is improved, but measurement quality and reliability deteriorate
Solution Approach 1:
The system implements feedback loops where the UE continuously monitors PRS quality metrics (RSRP, RSRQ, SINR) and uses this feedback to adjust measurement decisions. The AI/ML model is trained on historical measurement outcomes and channel conditions, using this feedback to improve future measurement timing decisions.
Solution Approach 2:
The measurement strategy transitions from static (fixed intervals) to dynamic (condition-based). The UE adaptively adjusts measurement frequency and timing based on real-time channel conditions, making the system flexible and responsive to environmental changes rather than following rigid schedules.
Data Source
AI summary
A user device may determine based on a received reference signal from a network node, channel information. The user device may apply as an input to an artificial intelligence and machine learning (AI/ML) model, the channel information. The user device may determine, based on an output of the AI/ML model, whether to measure an upcoming positioning reference signal (PRS) transmitted by the network node. The user device in response to the determination to measure the upcoming PRS, may perform a positioning measurement based on the upcoming PRS. The user device may transmit to the network node the positioning measurement.