Channel Learning Model Applicability in Changing MIMO Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AI-based information transmission methods in Massive MIMO systems face performance degradation due to channel learning models being inapplicable when the location of terminal devices changes or the communication environment changes.
Innovation Solution
A method to determine the applicability of channel learning models by evaluating long-term statistical characteristics, scheduling information, data transmission performance, and scenario changes, reducing the need for extensive calculations and signaling exchange.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the first channel learning model and the second channel learning model obtained through offline training are directly applied to an online information transmission process, then the information transmission can be performed efficiently, but if a location of the terminal device changes or a communication environment changes, the channel learning models may not be applicable, causing performance degradation
Solution Approach 1:
The terminal device determines whether the first channel learning model is applicable by evaluating current channel conditions, and feeds back this applicability information to the network device. The network device then determines whether the second channel learning model is applicable based on the received feedback. This feedback mechanism enables the system to adapt to changes in terminal device location or communication environment, resolving the contradiction between transmission efficiency and model applicability.
Solution Approach 2:
The system transitions from static offline-trained channel learning models to dynamic adaptability assessment. The terminal device and network device continuously evaluate model applicability based on current conditions, allowing the system to adapt dynamically to environmental changes while maintaining efficient information transmission when conditions permit.
2Measurement precision
If the terminal device determines model applicability with assistance from the network device through extensive signaling exchange, then the determination can be comprehensive, but the signaling complexity and processing load increase
Solution Approach 1:
The model applicability determination process is segmented into two parts: the terminal device performs initial assessment and determines whether the first channel learning model is applicable, then feeds back this determination. The network device performs secondary assessment based on the feedback to determine whether the second channel learning model is applicable. This segmentation reduces signaling complexity while maintaining comprehensive determination accuracy.
Data Source
AI summary
This application provides communication methods and communications apparatuses. In an example method, a first communications apparatus determines whether a first channel learning model is applicable, where the first channel learning model is used to determine first channel information based on target channel information, and a data amount of the first channel information is less than a data amount of the target channel information. The first communications apparatus sends a first message in response to determining that the first channel learning model is not applicable, where the first message is used to indicate that the first channel learning model is not applicable. According to the example method, the first communications apparatus can determine applicability of the first channel learning model without assistance of a second communications apparatus.