AI Service Policy Updates Through NEF-PCF Core Network Coordination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of flexibly and dynamically modifying artificial intelligence (AI) service policies in a core network environment is not adequately addressed by existing technologies, necessitating a solution that ensures seamless and reliable updates without disrupting ongoing services.
Innovation Solution
A method and apparatus for updating AI service policies involving multiple network elements, including an Application Function (AF), Network Exposure Function (NEF), Unified Data Repository (UDR), Policy Control Function (PCF), Session Management Function (SMF), and User Plane Function (UPF), enabling flexible and dynamic policy updates through coordinated interactions and data exchanges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If AI service policy is updated dynamically in core network, then service flexibility and adaptability are improved, but system complexity and coordination overhead increase
Solution Approach 1:
The policy update process is divided into distinct functional segments: AF initiates update, NEF validates and forwards, UDR stores policy data, PCF processes and generates PCC rules, SMF applies rules to sessions, and UPF executes at user plane. Each segment handles specific tasks independently, reducing overall system complexity while enabling dynamic updates.
Solution Approach 2:
Multiple intermediary network elements (NEF, UDR, PCF) are introduced between AF and UPF to facilitate coordinated policy updates. These intermediaries manage the complexity of policy propagation through standardized interfaces, allowing flexible updates without directly increasing the complexity of the core update mechanism.
2Manufacturing precision
If policy update process involves multiple network elements, then policy control precision is improved, but update time and processing delay increase
Solution Approach 1:
The UDR stores policy information in advance before updates are needed. When policy update is required, the pre-stored information can be quickly retrieved and processed by PCF, reducing the time needed for policy propagation through multiple network elements while maintaining precise control.
Solution Approach 2:
The policy update process is designed to continue useful actions without interruption - AF can initiate updates at any time, NEF validates continuously, UDR stores persistently, PCF processes immediately, and UPF applies changes without disrupting ongoing service operations, ensuring continuous service while achieving precise policy control.
3Ease of manufacture
If existing policy update mechanisms are used, then implementation simplicity is maintained, but service reliability during updates deteriorates
Solution Approach 1:
The system implements dynamic policy updates where PCC rules can be modified in real-time without disrupting ongoing service sessions. The SMF and UPF dynamically apply new policies to active sessions, ensuring service reliability during updates while maintaining implementation simplicity through automated rule processing.
Solution Approach 2:
The system prepares policy update mechanisms in advance with proper error handling and validation at each network element. NEF validates update requests before processing, PCF checks policy consistency, and SMF/UPF have prepared fallback mechanisms, cushioning against potential failures and ensuring service reliability during updates.
Data Source
AI summary
A method and an apparatus for updating an artificial intelligence (AI) service policy are provided. The method is performed by an application function (AF) network element, and includes: sending an AI service policy update request to a network exposure function (NEF) network element, in which the AI service policy update request comprises an identifier of the AF network element, and updated policy information; and receiving a policy update response returned by the NEF network element.