AI/ML Positioning Models for Low-Power Terminal Location
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication technologies face challenges in accurately positioning terminal devices, particularly in scenarios where line of sight is obstructed or synchronization errors occur, leading to inefficiencies and increased power consumption.
Innovation Solution
Implementing an artificial intelligence/machine learning (AI/ML) based positioning model at terminal or network devices to determine location-related measurement information, allowing for more accurate positioning and reducing the need for continuous monitoring of reference signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If terminal devices continuously monitor reference signals for positioning, then positioning accuracy is maintained, but power consumption increases
Solution Approach 1:
The network device configures the terminal device to monitor positioning reference signals only at periodic intervals rather than continuously. The terminal device receives configuration information including monitoring periodicity parameters, enabling it to wake up at specific intervals to measure reference signals and then enter sleep mode, thus maintaining positioning accuracy while significantly reducing power consumption during movement or idle periods
Solution Approach 2:
The network device performs preliminary positioning calculations using its own stored terminal device information and historical positioning data. This preliminary action allows the network device to pre-compute positioning results before the terminal device needs to report its position, reducing the need for the terminal device to continuously monitor and process reference signals, thereby lowering its power consumption while maintaining positioning accuracy
2Adaptability or versatility
If terminal devices perform measurements in obstructed environments, then positioning coverage is improved, but measurement precision deteriorates
Solution Approach 1:
The network device acts as an intermediary that collects positioning reference signal measurements from multiple transmission points and combines them with historical positioning information and terminal device movement data. This intermediary processing allows the system to maintain positioning accuracy in obstructed environments by compensating for signal blockages through multi-point measurements and predictive algorithms, thereby improving coverage without sacrificing precision
Solution Approach 2:
The system dynamically adjusts positioning parameters such as measurement thresholds, reference signal frequency, and prediction algorithm weights based on terminal device movement status and environment conditions. When the terminal device is moving or in obstructed areas, the system changes parameters to rely more on historical data and predictive modeling, maintaining positioning accuracy across diverse environments and expanding effective coverage
3Measurement precision
If AI/ML based positioning model is implemented, then positioning accuracy is enhanced, but device complexity increases
Solution Approach 1:
The network device serves as an intermediary that hosts and executes the complex AI/ML positioning models, receiving only simple measurement data from terminal devices. This architecture allows the system to benefit from advanced AI/ML-based positioning accuracy while keeping terminal device complexity low, as the heavy computational burden of the positioning model is offloaded to the network infrastructure rather than requiring complex models to be deployed on resource-constrained terminal devices
Data Source
AI summary
Embodiments of the present disclosure relate to methods, devices, and computer readable medium for communication. According to embodiments of the present disclosure, an artificial intelligence/machine learning (AI/ML) based positioning model is deployed at a terminal device or a network device. If the AI/ML based positioning model is triggered, location related measurement information of the terminal device is determined based on the AI/ML based positioning model. A core network device estimates a position of the terminal device based on the reported location related measurement information. In this way, the terminal device can be positioned more accurately.