NWDAF AI/ML Positioning for Dynamic Network Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for user positioning in wireless networks rely on traditional techniques that may not fully leverage the potential of AI and ML technologies, leading to limitations in accuracy, efficiency, and adaptability to dynamic network conditions.
Innovation Solution
The implementation of AI/ML-based positioning methods within next-generation wireless communication systems, utilizing a Network Data Analytics Function (NWDAF) that includes a Model Training Logical Function (MTLF) and an Analytics Logical Function (AnLF) to train and apply ML models for accurate UE positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional positioning techniques are used, then device complexity is reduced, but positioning accuracy and adaptability to dynamic network conditions deteriorate
Solution Approach 1:
The patent introduces a Network Data Analytics Function (NWDAF) as an intermediary component that mediates between network elements and positioning applications. The NWDAF collects data from multiple network elements, performs complex analytics using AI/ML models, and delivers positioning results, thereby enabling high accuracy without increasing client-side device complexity
Solution Approach 2:
The patent replaces traditional mechanical/mathematical positioning calculations with AI/ML-based analytics. Instead of using conventional signal processing algorithms, the system employs trained machine learning models that automatically learn optimal positioning features from network data, achieving superior accuracy while simplifying the overall system architecture
2Adaptability or versatility
If traditional positioning methods are used, then implementation simplicity is maintained, but adaptability to dynamic network conditions deteriorates
Solution Approach 1:
The patent implements dynamic adaptability through AI/ML models that continuously learn from changing network conditions. The models can adapt to new deployment scenarios, interference patterns, and network configurations automatically, allowing the positioning system to maintain high performance across diverse and dynamic environments without requiring manual reconfiguration
Solution Approach 2:
The system dynamically adjusts positioning parameters and model characteristics based on real-time network conditions. The AI/ML framework can modify its internal parameters and feature weights in response to changing environmental factors, enabling the system to adapt to various network scenarios while maintaining implementation simplicity through automated parameter optimization
3Productivity
If AI/ML-based positioning is implemented, then positioning accuracy and efficiency are improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent segments the computational workload by separating AI/ML-based analytics from the positioning execution. The NWDAF performs complex model training and data processing in a centralized function, while network elements and client devices only perform simpler data collection and result retrieval operations, thereby improving efficiency without proportionally increasing complexity at every layer
Solution Approach 2:
The NWDAF serves as a universal platform that handles multiple positioning tasks using the same AI/ML infrastructure. The system can serve multiple clients, support various positioning methods, and adapt to different network configurations through a single multi-functional analytics function, reducing overall system complexity compared to implementing dedicated positioning solutions for each scenario
Data Source
AI summary
Systems and methods are disclosed for supporting artificial intelligence/machine learning (AI/ML)-based positioning. A Network Data Analytics Function (NWDAF) containing a Model Training Logical Function (MTLF) for model training and containing Analytics Logic Function (AnLF) for inference and analytics derivation are provided. A Location Management Function (LMF) provides input data through positioning protocols, collecting measurements from a user equipment (UE) and next generation radio access network (NG-RAN) nodes. The LMF may provide inference capabilities rather than the AnLF, which performs analytics derivation using trained models provided by NWDAF MTLF.