Link Adaptation Policy Selection via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional link adaptation methods in wireless communication technologies face challenges in achieving optimal bitrates due to inaccurate channel quality reports, especially in scenarios with rapidly varying channel conditions and inter-cell interference.
Innovation Solution
The use of a Machine Learning (ML) algorithm to dynamically select a link adaptation policy (LAP) based on patterns in channel quality reports and additional measurements, such as neighbor cell activity, to optimize the Block Error Rate (BLER) target for each User Equipment (UE).
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a fixed common BLER target is used for link adaptation, then the implementation is simple and robust, but the transmission performance deteriorates in scenarios with rapidly varying channel conditions and inter-cell interference
Solution Approach 1:
The patent applies dynamics by transitioning from a fixed BLER target to a dynamic BLER target that adapts to varying channel conditions. The system monitors channel quality reports and adjusts the BLER target accordingly, allowing the link adaptation to respond to rapidly changing interference patterns and maintain optimal transmission performance across different scenarios.
Solution Approach 2:
The patent changes the parameter of BLER target from a fixed value to a variable parameter that depends on channel conditions. By adjusting the BLER target parameter based on observed channel quality and interference patterns, the system optimizes transmission performance while maintaining implementation simplicity through parameter-based adaptation rather than complex algorithmic changes.
2Reliability
If a high BLER target is used to compensate for inaccurate channel quality reports, then the robustness of data transmission is improved, but the throughput and spectral efficiency decrease substantially
Solution Approach 1:
The patent applies local quality by tailoring the BLER target specifically to each UE's local channel conditions rather than using a universal high BLER target for all UEs. Each UE receives a customized BLER target based on its individual channel quality reports and interference experience, allowing robustness to be maintained only where needed while preserving throughput and spectral efficiency for UEs with good channel conditions.
Solution Approach 2:
The patent dynamically changes the BLER target parameter for each UE based on its specific channel conditions and interference patterns. This parameter adaptation allows the system to use higher BLER targets only when necessary for robustness while maintaining lower, more efficient BLER targets for UEs with stable channels, thereby optimizing the trade-off between reliability and productivity.
3Productivity
If dynamically adjusting the BLER target based on estimated uncertainty of channel quality reports is implemented, then the transmission performance is improved, but the device complexity and implementation challenges increase
Solution Approach 1:
The patent uses feedback from channel quality reports and HARQ BLER measurements to dynamically adjust the BLER target. The system continuously monitors transmission outcomes and uses this feedback to refine the BLER target estimation, creating a closed-loop adaptation mechanism that improves transmission performance while keeping the implementation relatively simple through direct feedback utilization.
Solution Approach 2:
The link adaptation system performs self-service by automatically adjusting its own BLER target based on observed channel conditions and transmission performance. Rather than requiring external control or complex algorithms, the system uses its own measurements and feedback to autonomously optimize its operation, reducing implementation complexity while maintaining high transmission performance.
4Stability of the object's composition
If channel quality reports are systematically filtered by terminals to remove fast variations, then the report stability is improved, but the measurement precision deteriorates and introduces errors in channel quality assessment
Solution Approach 1:
The patent applies inversion by reversing the conventional approach: instead of filtering out fast variations to achieve stability, the system embraces and utilizes these fast variations as valuable information. By inverting the filtering operation, the system can accurately capture rapid channel changes and adapt the BLER target accordingly, resolving the contradiction between report stability and measurement precision.
Solution Approach 2:
The patent applies dynamics by making the BLER target adaptive to dynamic channel conditions rather than relying on filtered, stable reports. The system continuously adjusts the BLER target based on real-time channel quality information, allowing it to accommodate fast variations and maintain both accurate measurement and appropriate transmission robustness despite the instability of the underlying channel conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems for dynamically selecting a link adaptation policy, LAP. In some embodiments, the method includes generating a machine learning, ML, model, wherein generating the ML model comprises providing training data to an ML algorithm. The method further includes using channel quality information, additional information, and the ML model to select a LAP from a set of predefined LAPs. In some embodiments, the additional information comprises: neighbor cell information about a second cell served by a second TRP, distance information indicating a distance between a UE and a first TRP, and/or gain information indicating a radio propagation gain between the UE and the serving node. The method further includes the first TRP transmitting second data to the UE using the selected LAP. P75977-WO1 (3602-1767W1) Page 22