Link Adaptation via ML-Driven SINR Offset
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current link adaptation techniques in mobile communication systems often inefficiently use resources to guarantee a target Block Error Rate (BLER), leading to suboptimal modulation and coding scheme selections.
Innovation Solution
An apparatus and method that generate a channel quality metric offset based on feedback data, using a loss/reward function to update a model for adjusting the modulation and coding scheme, allowing for dynamic optimization of SINR offset parameters through machine learning techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional link adaptation techniques are used to guarantee a target Block Error Rate (BLER), then transmission reliability is improved, but resource efficiency deteriorates
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting the SINR offset parameter based on feedback data and machine learning model predictions. Instead of using fixed offset values, the system continuously optimizes the offset parameter to achieve target BLER while improving resource efficiency. The model learns optimal offset values that balance reliability and resource utilization by analyzing historical feedback data and adapting to changing channel conditions.
2Reliability
If conservative modulation and coding scheme selections are made to ensure reliable transmission, then transmission reliability is improved, but spectral efficiency deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where the system receives feedback data about actual transmission outcomes (ACK/NACK signals, BLER measurements) and uses this information to update the machine learning model. The model then adjusts MCS selections and SINR offset values to optimize both reliability and spectral efficiency. This closed-loop feedback enables the system to learn from past transmissions and make more accurate MCS decisions that achieve target BLER without being overly conservative.
3Device complexity
If fixed SINR offset parameters are used in link adaptation, then system complexity is reduced, but adaptability to changing channel conditions deteriorates
Solution Approach 1:
The patent applies dynamics by transitioning from fixed SINR offset parameters to dynamic, adaptive offset values generated by a machine learning model. The system continuously updates the offset parameter based on real-time feedback data and changing channel conditions. This dynamic approach allows the link adaptation mechanism to adapt to varying channel characteristics, user equipment capabilities, and traffic patterns while maintaining manageable system complexity through efficient model implementation.
Data Source
AI summary
An apparatus, method and computer program is described including: generating a channel quality metric offset; summing a channel quality metric and the channel quality metric offset to generate an adjusted channel quality metric of a channel of a mobile communication system; setting a modulation and coding scheme for transmitting data over the channel based, at least in part, on the adjusted channel quality metric; obtaining feedback data relating to the success of data transfer over said channel; compiling a loss/reward function based, at least in part, on said feedback data; and updating a model using the loss/reward function, wherein the model is used in the generation of said channel quality metric offset.