Uplink LLR Decoding With ML-Tuned Soft Demapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in high-speed communication networks like LTE and 5G is efficiently processing uplink transmissions due to the mixing of reference signals with data, requiring special processing to account for resource elements containing reference signals, and the need for efficient descrambling, combining, and decoding of data and uplink control information (UCI).
Innovation Solution
A decoder system utilizing log-likelihood ratio (LLR) optimization is employed to categorize uplink control information (UCI) into different categories, perform descrambling and combining, and use machine learning to adjust soft-demapping parameters for enhanced processing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If reference signals are mixed with data in uplink transmissions, then spectral efficiency is improved, but processing complexity increases due to the need to account for resource elements containing reference signals
Solution Approach 1:
The patent segments the uplink transmission processing by categorizing resource elements into different types (data, UCI, reference signals) and processing them through separate pathways. The RE identifier categorizes each RE, and the combiner/extractor processes different UCI types separately, allowing the system to handle mixed transmissions while managing complexity through structured segmentation.
Solution Approach 2:
The patent introduces an intermediary categorization layer (RE identifier) that mediates between the mixed uplink transmission and the processing stages. This intermediary component identifies and categorizes each resource element type, enabling subsequent processors to handle only relevant elements without processing overhead from unrelated elements.
2Reliability
If uplink control information is combined from multiple symbols, then decoding accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary categorization of resource elements before combining operations. The RE identifier categorizes each RE in advance, and the combiner/extractor is pre-configured with category information, allowing it to efficiently identify and combine only relevant UCI elements without scanning or processing unrelated data elements during the combining phase.
Solution Approach 2:
The patent segments the combining process by UCI category (ACK, CSI1, CSI2, data), allowing parallel or organized sequential processing of different UCI types. This segmentation enables the system to process multiple UCI categories systematically, improving accuracy through comprehensive combining while managing time through structured organization.
3Reliability
If machine learning is used to dynamically adjust soft-demapping parameters, then system performance is improved, but computational complexity increases
Solution Approach 1:
The patent implements a feedback mechanism where the machine learning circuit continuously monitors system performance and dynamically adjusts soft-demapping parameters based on observed conditions. This feedback loop enables the system to adapt to changing channel conditions and optimization opportunities, improving performance while the ML circuit manages computational complexity through learned patterns rather than exhaustive search.
Data Source
AI summary
Methods and apparatus for decoding received uplink transmissions using log-likelihood ratio optimization. In an embodiment, a method includes soft-demapping resource elements based on soft-demapping parameters as part of a process to generate log-likelihood ratios (LLR) values, decoding the LLRs to generate decoded data, and identifying a target performance value. The method also includes determining a performance metric from the decoded data, and performing a machine learning algorithm that dynamically adjusts the soft-demapping parameters to move the performance metric toward the target performance value.