Context-Aware Network Analysis Model Selection in 5G Core
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network analysis methods in 5G core networks lack precision and relevance due to insufficient consideration of the formulation context in which statistical and predictive analyses are requested, leading to inefficient responses to diverse use cases.
Innovation Solution
A method and system that incorporate a formulation context into the analysis process by selecting appropriate analysis models based on information provided in the request, using dedicated parameters or learning algorithms to enhance the relevance and precision of statistical and predictive analyses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single analysis model is used for all statistical and predictive analysis requests, then the system complexity is reduced, but the accuracy and relevance of analysis results deteriorate due to insufficient consideration of formulation context
Solution Approach 1:
The system dynamically selects analysis models based on the formulation context of each request. The NWDAF function determines the appropriate analysis model by evaluating context information such as the type of analysis requested, target object, time period, and area, rather than using a static single model for all requests. This dynamic adaptation resolves the contradiction by allowing model complexity to vary according to specific needs.
Solution Approach 2:
The system changes the parameter of analysis model selection based on formulation context parameters. Different context parameters (analysis type, target, time, area) trigger selection of different analysis models from a plurality of available models. This parameter-driven approach enables the system to maintain appropriate complexity levels while achieving high accuracy for each specific analysis scenario.
2Measurement precision
If multiple analysis models are maintained for different formulation contexts, then the accuracy and relevance of analysis results is improved, but the device complexity increases due to model selection and management requirements
Solution Approach 1:
The NWDAF function performs self-service by automatically determining the appropriate analysis model based on the formulation context provided in each request. The system autonomously evaluates context parameters and selects the most suitable model without requiring external intervention or complex manual configuration, thereby managing model complexity internally while maintaining high accuracy.
Solution Approach 2:
The system uses feedback from the formulation context parameters to guide analysis model selection. The context information fed into the selection process includes analysis type, target object, time period, and area, which collectively provide feedback that determines the optimal model choice. This feedback mechanism enables accurate model selection while keeping the system manageable through structured decision-making.
3Ease of operation
If analysis models are selected without considering formulation context, then the ease of operation is improved, but the relevance of analysis results to specific use cases deteriorates
Solution Approach 1:
The formulation context parameters are determined in advance as part of the request processing, before analysis model selection occurs. The system preliminarily evaluates context information such as analysis type, target, time, and area to prepare for appropriate model selection. This preliminary action ensures that use case relevance is maintained while keeping the operational process streamlined through pre-established context evaluation.
Solution Approach 2:
The NWDAF function serves multiple purposes by using a universal context evaluation mechanism that handles diverse analysis requests. The same context determination process applies to all types of statistical and predictive analysis requests, making the system versatile across different use cases while maintaining operational simplicity through a unified approach.
4Adaptability or versatility
If context information is collected and processed for each analysis request, then the adaptability to different use cases is improved, but the loss of time in processing requests increases
Solution Approach 1:
The system performs partial context evaluation by focusing on the essential formulation context parameters needed for model selection, rather than processing all possible context information. By selectively evaluating only the necessary context elements (analysis type, target, time, area), the system achieves use case adaptability while minimizing processing time through targeted rather than exhaustive context analysis.
Data Source
AI summary
A method for processing a request for statistical or predictive analysis received by a first application entity of a communications network originating from a second application entity of the network. The method includes: determining, from at least one item of information conveyed by the request, a context in which the request was formulated by the second application entity; performing the requested statistical or predictive analysis by using an analysis model selected according to the determined context; and providing at least one result of the analysis performed in response to the request from the second application entity.