AI Traffic QoS Configuration for Computing Power and Latency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current QoS configuration mechanisms for AI traffic do not adequately consider the characteristic information of AI traffic, leading to unsatisfied requirements and poor user experience.

Innovation Solution

Generate a QoS configuration for AI traffic flows that includes information about the AI model's computing power, latency, and user experience requirements, and transmit this configuration to communication apparatuses to enhance QoS management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If current QoS configuration mechanisms are used for AI traffic, then general traffic transmission is supported, but AI traffic specific requirements (computing power, latency) are not satisfied

Engineering Contradiction:
ImproveQoS configuration adaptability to AI traffic characteristicsVSAvoidAI traffic requirement satisfaction
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent introduces AI-specific QoS parameters (computing power requirements, latency requirements, model information) that are applied locally to AI traffic flows. The QoS configuration is customized for AI traffic by adding fields such as AI model identifier, computing power requirements, and latency requirements, allowing differential treatment of AI traffic versus general traffic to satisfy specific AI workload demands.

Inventive Principle:
Principle #3Local quality

2Reliability

If QoS configuration includes detailed AI model information, then AI traffic requirements are better satisfied, but configuration complexity increases

Engineering Contradiction:
ImproveAI traffic requirement satisfactionVSAvoidQoS configuration complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-configuring QoS parameters for AI traffic flows before transmission. The network device receives AI traffic flow information in advance, determines appropriate QoS parameters based on AI model characteristics and requirements, and configures these parameters proactively. This allows the system to prepare QoS settings ahead of time, reducing real-time complexity while ensuring AI traffic requirements are met.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20260025320A1Communication method and apparatus, and computer-readable storage medium
Publication Date: 2026.01.22 HUAWEI TECH CO LTD
  • US20260025320A1 patent drawing
  • US20260025320A1 patent drawing
  • US20260025320A1 patent drawing

AI summary

This application relates to a communication method and apparatus, and a computer-readable storage medium. Including, a core network device generates a quality of service QoS configuration of a traffic flow, and sends the QoS configuration to a communication apparatus. The traffic flow is associated with an AI model. The QoS configuration includes information associated with the AI model. The information indicates at least one of the following: a requirement, in terms of computing power, of training or inference of the AI model; or a requirement, in terms of a latency, of training or inference of the AI model. Then, the communication apparatus may perform transmission of the traffic flow based on the QoS configuration. In this way, a requirement of the AI traffic can be more adequately satisfied and user experience of the AI traffic can be improved.