Wireless Congestion Control for AI/ML Terminal Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in efficiently performing congestion control based on whether a terminal participates in AI/ML operation in a wireless communication system in a wireless communication system.
Innovation Solution
A method and device for performing congestion control in a wireless communication system by determining whether to perform congestion control based on AI/ML operation, utilizing AI/ML related information from an application function (AF) and non-access stratum (NAS) messages to manage network functions and terminals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If congestion control is applied to all terminals, then network overload is reduced, but AI/ML operation performance deteriorates
Solution Approach 1:
The patent applies different congestion control treatments to different terminal types. AI/ML terminals are identified through specific indicators (e.g., AI/ML operation indication, specific DNN/S-NSSAI) and excluded from conventional congestion control mechanisms like NAS message rejection and backoff timer application. This local differentiation ensures that while regular terminals receive congestion control to maintain network stability, AI/ML terminals maintain their operation performance without being adversely affected by congestion control measures.
2Reliability
If congestion control messages are transmitted to terminals, then network congestion is managed, but AI/ML operation timing is delayed
Solution Approach 1:
The patent extracts AI/ML terminals from the conventional congestion control message flow. By identifying terminals engaged in AI/ML operations through specific indicators, the network function excludes these terminals from receiving congestion control messages such as NAS rejection messages and backoff timer notifications. This extraction ensures that congestion management messages are directed only to regular terminals, preventing timing delays in AI/ML operations while still managing network congestion effectively.
3Device complexity
If uniform congestion control policy is applied, then implementation simplicity is maintained, but AI/ML service quality deteriorates
Solution Approach 1:
The patent implements differentiated congestion control policies based on terminal type. Network functions examine specific indicators to identify AI/ML terminals, including AI/ML operation indication information, specific DNN (Data Network Name), S-NSSAI (Single Network Slice Selection Assistance Information), and terminal state information. Based on this identification, the system applies appropriate congestion control measures: regular terminals receive standard congestion control treatment, while AI/ML terminals are excluded from certain congestion control mechanisms to maintain their service quality. This local quality approach balances implementation complexity with service quality requirements.
Data Source
AI summary
A method of operating a network function in a wireless communication system may comprise obtaining artificial intelligence (AI)/machine learning (ML) related information from an application function (AF), determining whether to perform congestion control on a first terminal based on the obtained AI/ML related information, receiving a non-access stratum (NAS) message from the first terminal, and performing congestion control based on the NAS message. Whether to perform congestion control on the first terminal may be determined based on whether the first terminal participates in AI/ML operation.