NWDAF Machine Learning for 5G ATSSS Traffic Steering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for multipath communication within a 5G core network fail to efficiently integrate traffic management across heterogeneous access networks, leading to resource consumption and network congestion due to inadequate data sharing and predictive analytics among network functions like NWDAF, ePDG, and NSWOF, resulting in suboptimal traffic steering, switching, and splitting.
Innovation Solution
Utilizing machine learning to enhance the network data analytics function (NWDAF) for predictive load condition analytics, integrating ePDG and NSWOF within its analytical scope, enabling data-driven and real-time policy decision-making for traffic steering, switching, and splitting (ATSSS) across multiple access types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning is integrated into NWDAF for predictive analytics, then traffic steering efficiency is improved, but device complexity increases
Solution Approach 1:
The patent introduces machine learning models as intermediary components between network data collection and traffic steering decisions. The NWDAF incorporates ML modules that process raw network data and generate predictive analytics, which then guide traffic steering actions. This intermediary layer enables intelligent decision-making while maintaining a clear separation between data processing and control functions, resolving the contradiction by adding capability without proportionally increasing overall system complexity.
Solution Approach 2:
The patent segments the NWDAF functionality into distinct modules: data collection, machine learning processing, analytics generation, and traffic steering control. By dividing the system into specialized components, each handling specific tasks, the patent improves traffic steering efficiency through targeted ML applications while managing device complexity through modular architecture. Each segment can be independently optimized and maintained.
2Productivity
If ePDG and NSWOF are integrated into NWDAF analytical scope, then traffic management is improved, but device complexity increases
Solution Approach 1:
The patent merges ePDG and NSWOF analytical functions into the NWDAF framework, creating a unified traffic management system. Instead of operating as separate silos, these network functions are integrated under the common NWDAF architecture, enabling shared data analytics and coordinated traffic steering decisions. This merging improves overall traffic management efficiency by eliminating redundant processing while the unified architecture actually reduces device complexity compared to separate implementations.
Solution Approach 2:
The NWDAF is designed as a universal platform that serves multiple network functions including ePDG and NSWOF. The analytics engine provides multi-functional support for different access types (3GPP and non-3GPP) and traffic scenarios through a single integrated system. This multi-functionality approach improves traffic management across diverse networks while avoiding the complexity of maintaining separate analytical systems for each function.
3Productivity
If real-time predictive analytics are implemented, then network resource utilization is improved, but use of energy increases
Solution Approach 1:
The patent implements periodic analytics generation where the NWDAF produces predictive analytics at optimized intervals rather than continuously. The system determines appropriate update frequencies based on network conditions, traffic patterns, and service requirements. This periodic approach maintains effective network resource utilization through timely updates while significantly reducing energy consumption compared to continuous real-time processing, resolving the contradiction between productivity and energy use.
Data Source
AI summary
A device may receive secure connection data and load data associated with a secure connection established between a user equipment (UE) and a core network via an untrusted access network. The device may process the secure connection data and the load data, with a machine learning model, to generate analytics associated with the secure connection, and may provide the analytics to one or more analytics consumers to cause the one or more analytics consumers to perform one or more actions based on the analytics. The one or more actions may include providing access traffic steering, switching, and splitting for the secure connection, providing mobility management for the UE, generating a policy for the secure connection, selecting a user plane function of the core network to communicate with the secure connection, or modifying the secure connection.