NTN Link Adaptation Using Predictive MCS and Repetition Settings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In non-terrestrial network (NTN) communication systems, existing link adaptation techniques fail to accurately adapt to real-time channel conditions due to signal transmission and reception delays, leading to deteriorated communication quality, especially in scenarios with varying line-of-sight and non-line-of-sight conditions.
Innovation Solution
A method and apparatus for determining optimal Modulation and Coding Scheme (MCS) and Repetition Number (REP) for downlink channels using AI-based prediction models that incorporate Channel Quality Indicator (CQI), Signal-to-Interference-plus-Noise Ratio (SINR), and Block Error Rate (BLER) information, even in the absence of Hybrid Automatic Repeat Request (HARQ) feedback, to enhance link adaptation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing link adaptation techniques are used in NTN systems, then the system can operate with current protocols, but communication quality deteriorates due to inability to adapt to real-time channel conditions
Solution Approach 1:
The patent applies preliminary action by predicting future channel conditions and pre-determining optimal MCS and REP parameters before actual data transmission occurs. The AI-based prediction model analyzes historical channel state information and forecasts future channel quality, allowing the system to prepare appropriate transmission parameters in advance, thereby adapting to real-time channel changes without waiting for feedback.
Solution Approach 2:
The patent utilizes feedback mechanisms by incorporating HARQ feedback information and RLC status PDU into the AI prediction model. The model processes historical feedback data to learn from past transmission outcomes and adjust future predictions. This feedback loop enables continuous improvement of prediction accuracy and enhances the system's ability to adapt to changing channel conditions.
2Reliability
If HARQ feedback is used for link adaptation, then transmission reliability can be improved, but system complexity increases and delays are introduced
Solution Approach 1:
The patent applies self-service by enabling the AI prediction model to autonomously determine optimal MCS and REP parameters without requiring complex HARQ feedback processing. The model independently analyzes channel state information and historical data to make prediction decisions, reducing the burden on the feedback mechanism and simplifying the overall system architecture while maintaining high transmission reliability.
Solution Approach 2:
The patent replaces the traditional mechanical HARQ feedback-based link adaptation mechanism with an AI-based prediction system. Instead of relying on explicit feedback loops and complex control algorithms, the system uses machine learning models to predict optimal transmission parameters, substituting the mechanical feedback process with an intelligent prediction approach that reduces system complexity.
3Measurement precision
If AI-based prediction models are used to predict MCS and REP, then link adaptation accuracy improves, but computational requirements increase
Solution Approach 1:
The patent applies parameter changes by optimizing the input parameters fed into the AI prediction model. Instead of using all available raw data, the system selectively processes key parameters such as channel state information, historical MCS and REP values, and HARQ feedback indicators. This parameter selection and transformation approach reduces the computational burden on the AI model while maintaining high prediction accuracy for link adaptation.
Data Source
AI summary
The disclosure relates to a 5G or 6G communication system for supporting higher data rates. The disclosure provides a method performed by a base station of an NTN. The method includes: transmitting, to a terminal, a first PDSCH in first slots, wherein the first slots include at least one slot where the first PDSCH is scheduled without HARQ feedback; receiving, from the terminal, channel quality information and feedback information, wherein the feedback information includes HARQ feedback information and RLC status information associated with a transmission of the first PDSCH in the at least one slot; predicting a MCS and a repetition number for a second PDSCH, based on the information associated with the channel quality information and the feedback information; transmitting, to the terminal, information on the MCS and information on the repetition number; and transmitting, to the terminal, the second PDSCH in second slots.