AI/ML Entity Delay Management in 5G Networks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing telecommunication systems face challenges in efficiently managing the activation and switching delays of artificial intelligence and machine learning (AI/ML) entities, which affects performance and latency in 5G and beyond networks.

Innovation Solution

An apparatus and method that transmit and update delay information associated with AI/ML entities, including activation and switching delays, between network devices and terminal devices, enabling dynamic management and optimization of AI/ML entity performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If AI/ML entities are activated or switched in real-time, then system adaptability and performance optimization are improved, but activation delay and switching delay increase

Engineering Contradiction:

ImproveAI/ML entity adaptabilityVSAvoidactivation delay and switching delay

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-configuring multiple AI/ML entities with their performance parameters and delay characteristics before actual activation. The network device stores information about supported AI/ML entities including their activation delays and switching delays in advance, enabling faster decision-making when activation is needed without experiencing full activation delay from scratch.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamics by enabling dynamic selection and switching between multiple AI/ML entities based on real-time network conditions and performance requirements. The system can dynamically adjust which AI/ML entity is active by utilizing pre-configured entities and their associated delay characteristics, making the system adaptable while managing activation and switching delays through informed decision-making.

Inventive Principle:

Principle #15Dynamics

2Productivity

If delay information is transmitted and updated between network devices and terminal devices, then AI/ML entity performance is optimized, but system complexity increases

Engineering Contradiction:

ImproveAI/ML entity performanceVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies feedback by implementing a mechanism where terminal devices transmit first information indicating supported AI/ML entities and their delay characteristics to network devices. The network device uses this feedback information to make informed decisions about entity activation and switching, optimizing performance while managing system complexity through structured information exchange.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent uses delay information as an intermediary element that mediates between the terminal device and network device. This intermediary carries structured information about AI/ML entity characteristics, enabling coordinated decision-making without requiring direct complex interactions between all system components, thus optimizing performance while controlling overall system complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250031068A1Mechanism for functionality based life cycle management

Publication Date: 2025.01.23 NOKIA TECHNOLOGIES OY

AI summary

The present disclosure relates to a solution for functionality-based performance monitoring. In particular, a solution is proposed to enable functionality-based performance monitoring via sending updates on the configured/identified functionalities using applicable conditions framework. In this way, it can improve performance of the AI/ML entity.