MDAS Traffic Analytics for 5G Slice GST Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in 5G networks is the need to divide GST attributes among multiple instances of network functions (NFs) based on traffic analytics, particularly for parameters like downlink throughput per slice, which is critical for efficient resource allocation.
Innovation Solution
A method and system using Management Data Analytics Service (MDAS) to generate a Slice Traffic Analytics Report (STAR) through AI-based modeling, collecting performance measurements from network functions, and configuring attributes based on projected traffic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If GST attributes are divided among multiple NF instances based on traffic analytics, then resource allocation efficiency is improved, but system complexity increases due to the need for traffic collection, analysis, and dynamic configuration
Solution Approach 1:
The patent introduces an intermediary component (MDAS/Analytics function) that collects traffic measurements from multiple NF instances, performs analytics processing, and generates configuration recommendations. This intermediary handles the complex tasks of data aggregation, analysis, and configuration generation, thereby improving resource allocation efficiency while isolating the complexity from the core NF instances themselves.
Solution Approach 2:
The system divides the GST configuration management into separate functional modules: traffic measurement collection, analytics processing, configuration generation, and NF instance configuration. This segmentation allows each module to specialize in specific tasks, improving overall resource allocation efficiency while organizing system complexity into manageable, independent components.
2Measurement precision
If AI-based models are used to generate traffic analytics reports, then measurement precision is improved, but device complexity increases due to the deployment and maintenance of AI models
Solution Approach 1:
The patent introduces an Analytics function as an intermediary that houses and executes AI-based models for traffic pattern recognition and forecasting. This intermediary concentrates the AI model complexity in a dedicated component, allowing precise traffic analytics generation while isolating the computational complexity from the core NF management functions.
Solution Approach 2:
The system performs preliminary traffic pattern analysis and forecasting using AI models before generating configuration recommendations. By pre-analyzing traffic patterns and predicting future behavior, the system achieves high measurement precision for resource allocation while preparing configuration data in advance, reducing real-time computational complexity.
Data Source
AI summary
A method for generating a Slice Traffic Analytics Report (STAR) is provided. The method includes receiving a first request for subscribing to Slice Traffic Analytics Report (STAR) from a Network Slice Subnet Management Function (NSSMF), collecting one or more performance measurements from each of the one or more network functions after completion of a pre-defined time period, and generating the STAR based on the one or more performance measurements collected from the one or more network functions using an Artificial Intelligence (AI) based model.