Base Station MCS Adaptation Using AI-Predicted SINR Offsets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing link adaptation methods fail to accurately adjust modulation and coding schemes (MCS) in scenarios of rapid channel changes due to reliance on long-term historical reports and fixed adjustment steps, leading to suboptimal throughput.
Innovation Solution
Utilizing an AI network to predict short-term SINR offsets based on channel-related information, including block error rate (BLER) and decoding feedback, to dynamically determine MCS for edge UEs, enhancing accuracy and adaptability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If long-term historical report information and fixed adjustment step are used for channel tracking, then system stability is maintained, but the ability to satisfy MCS adjustment requirements in rapid channel change scenarios deteriorates
Solution Approach 1:
The patent applies dynamics by making the MCS adjustment mechanism adaptive rather than fixed. The AI network dynamically adjusts MCS based on real-time channel conditions, user equipment type (edge UE vs. center UE), and historical performance feedback. This allows the system to transition between stable long-term tracking and rapid adaptation modes, resolving the contradiction between stability and adaptability in different operational scenarios
2Ease of manufacture
If CQI is periodically reported for link adaptation, then implementation simplicity is maintained, but real-time channel quality reflection deteriorates due to channel fading and user movement
Solution Approach 1:
The patent implements feedback mechanisms where the base station uses decoded feedback values from user equipment to continuously refine SINR offset estimates and adjust MCS. This closed-loop feedback system allows the periodic CQI reports to be supplemented with real-time adjustments based on actual decoding performance, thereby maintaining implementation simplicity while improving real-time channel quality accuracy
Solution Approach 2:
The system performs preliminary actions by pre-calculating and storing SINR offsets for different channel conditions and user equipment types. When channel changes occur, the base station can quickly retrieve and apply appropriate pre-computed offsets rather than calculating from scratch, enabling faster response to channel variations while maintaining the simplicity of periodic CQI reporting
3Measurement precision
If AI network is used to predict short-term SINR offset for edge UEs, then MCS accuracy in rapid channel change scenarios is improved, but system complexity increases
Solution Approach 1:
The patent applies local quality by differentiating treatment between edge UEs and center UEs. The AI-based short-term SINR offset prediction is specifically applied to edge UEs that experience more severe channel variations, while center UEs can use simpler methods. This localized application of complex AI processing only where needed improves MCS accuracy for vulnerable users without unnecessarily increasing system complexity for all users
Data Source
AI summary
An example embodiment may provide a method to be performed by a base station and/or a network node, and relevant devices. The method may include: acquiring channel related information of a target user equipment (UE); acquiring a modulation and coding scheme (MCS) determined based on MCS related information, the MCS related information being acquired by an artificial intelligence (AI) network based on the channel related information; and, transmitting the determined MCS to the target UE, the target UE comprising an edge UE, the number of MCS change value of the edge UE being greater than the number of MCS change value of a center UE. The steps in this scheme can be implemented by a trained artificial intelligence method. The corresponding MCS related information may be acquired by an AI network based on the channel related information of the target UE, and the MCS of the target UE may then be determined by using the acquired MCS related information. Since the MCS related information acquired by the AI network can accurately reflect the channel state of the target UE, the determined MCS is more accurate, and the user throughput is thus improved.