AI Model Transfer During Wireless Handover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication systems lack defined procedures for efficiently transferring or delivering artificial intelligence (AI) models during handover in wireless communication systems, leading to potential transfer failures, especially when the user equipment (UE) is at the edge of a cell or when the size or number of AI models increases.
Innovation Solution
A method and apparatus for efficiently transferring or delivering AI models in a wireless communication system, involving a first base station that receives a measurement report from a terminal, transfers a handover request message to a second base station with AI model information, determines an AI model for transfer based on response messages, and transfers the determined AI model back to the terminal along with a handover message.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI models are transferred during handover without defined procedures, then the handover process can proceed, but transfer failures occur especially when UE is at cell edge or AI model size increases
Solution Approach 1:
The patent applies preliminary action by determining the AI model to be transferred in advance during the handover request phase. The source base station identifies and prepares the appropriate AI model before the actual handover execution, ensuring that the model is ready for transfer and reducing the risk of transfer failures during the critical handover moment.
Solution Approach 2:
The patent uses the handover request message as an intermediary carrier to transport AI model information between base stations. The target base station's AI model information is embedded within the handover request message, facilitating reliable model transfer without requiring separate dedicated signaling channels, thus improving reliability while managing complexity.
2Reliability
If AI model information is included in handover messages, then model transfer can be achieved, but signaling overhead increases
Solution Approach 1:
The patent extracts only the essential AI model information (such as model identifiers, parameters, or references) rather than transferring complete AI models through signaling messages. This extraction approach enables reliable model transfer by ensuring the necessary information is conveyed while significantly reducing the signaling overhead and message size.
Solution Approach 2:
The patent performs preliminary determination of which AI model to transfer during the handover request phase, allowing the actual model data to be prepared and transferred through more efficient channels later. This separates the decision-making signaling (low overhead) from the actual model transfer, reducing signaling message size while ensuring transfer success.
3Reliability
If AI model transfer is performed during handover, then service continuity is maintained, but transfer time and resource usage increase
Solution Approach 1:
The patent applies preliminary action by determining and preparing the AI model during the handover request phase, before the actual handover execution. This advance preparation ensures that when the handover is executed, the AI model transfer can proceed immediately without delay, maintaining service continuity while minimizing the time loss during the critical handover moment.
Solution Approach 2:
The patent ensures continuity of useful action by integrating AI model transfer into the existing handover signaling flow. The AI model information is transmitted through the established handover message exchanges, allowing the model transfer to occur continuously alongside the handover procedure without interrupting or pausing the handover process, thus maintaining service continuity while optimizing time usage.
Data Source
AI summary
The disclosure relates to a 5G or 6G communication system for supporting higher data transfer rates. A method performed by a first base station in a communication system is provided. The method includes receiving a measurement report from a terminal, transferring, to a second base station, a handover request message including information for transferring an artificial intelligence (AI) model, determining a first AI model for transferring the AI model of the terminal based on a response message for a handover request and AI information of the terminal previously received from the terminal, the handover request including response information to the information for transferring the AI model received from the second base station, and transferring, to the terminal, the determined first AI model and a message for performing handover.