URSP Traffic Mapping for AI/ML Service Analytics in 5G
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to effectively map traffic categories to application AI/ML operation types, leading to inefficiencies in managing and optimizing network resources for various applications.
Innovation Solution
Implementing a mapping of traffic categories to application AI/ML operation types using UE route selection policy (URSP) rules, which utilize connection capabilities, operating system identifiers, application identifiers, and single-network slice assistance information to match traffic categories and filter connections, enabling WTRUs to request and receive analytics and predictions from the 5G core.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If existing systems are used without mapping traffic categories to AI/ML operation types, then system complexity is reduced, but network resource management efficiency deteriorates
Solution Approach 1:
The patent segments traffic management by introducing traffic categories (e.g., gaming, video streaming, enterprise services) and mapping each category to specific AI/ML operation types. This segmentation allows differentiated resource management for different application types, improving overall network resource management efficiency while maintaining manageable system complexity through structured classification.
Solution Approach 2:
The patent introduces URSP rules as an intermediary mechanism that bridges traffic categories and AI/ML operation types. These rules act as a mapping layer that translates application traffic characteristics into appropriate AI/ML operations, enabling efficient resource management without requiring direct complex interactions between all system components.
2Measurement precision
If traffic categories are mapped to AI/ML operation types using multiple parameters, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the matching process into discrete parameters (connection capability, OS identifier, application identifier, S-NSSAI/DNN) that can be evaluated independently. This segmentation allows precise traffic categorization through systematic parameter matching while keeping the complexity manageable by processing one parameter at a time rather than evaluating all parameters simultaneously.
Solution Approach 2:
The patent employs URSP rules that are pre-configured with matching criteria for different traffic categories. By preparing matching rules in advance, the system achieves high measurement precision for traffic categorization without requiring complex real-time analysis, as the matching logic is already established before actual traffic classification occurs.
3Adaptability or versatility
If URSP rules with multiple parameters are used for matching, then adaptability is improved, but ease of operation deteriorates
Solution Approach 1:
The patent creates a universal URSP rule framework that can handle multiple application types (gaming, video streaming, enterprise services) through a common matching mechanism. This multi-functional approach allows the same rule structure to adapt to diverse applications by varying the parameter values, improving versatility while maintaining operational simplicity through a unified configuration paradigm.
Solution Approach 2:
The patent enables adaptability by allowing configuration of specific parameter values (connection capability, OS identifier, application identifier, S-NSSAI/DNN) within the universal URSP rule structure. By changing parameter values rather than restructuring the entire system, the framework achieves high adaptability to different applications while keeping the operational interface simple and consistent.
Data Source
AI summary
A wireless transmit/receive unit (WTRU) may receive a configuration. The configuration may include at least one of an artificial intelligence machine learning (AI/ML) operation type association to a traffic category. The traffic category may correspond to an AI/ML operation traffic category and/or at least one parameter. The WTRU may determine an AI/ML service operation type, for example to be operated by an AI/ML application client on the WTRU. The WTRU may transmit, for example to a network element, a request for analytics and/or a prediction related to the AI/ML service operation type. The request may include an indication of the traffic category and/or the at least one parameter. The WTRU may receive the analytics and/or prediction related to the AIMML service operation type, for example in response to the request.