Channel Environment Classification for Uniform AI Channel Coding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AI/ML based channel codes suffer from unequal error protection due to memory effects, leading to reduced system performance, particularly with small input block lengths, and adding padding bits to address this issue reduces code rate.
Innovation Solution
A circular buffer aided AI/ML based channel coding scheme is introduced to address unequal error protection without reducing the code rate, utilizing an input circular buffer to determine the statistics of the underlying wireless channel.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If padding bits are added to address unequal error protection, then error protection is improved, but code rate is reduced
Solution Approach 1:
The patent segments the input information bits into multiple blocks and processes them through separate AI/ML-based encoders. This segmentation allows each block to be encoded independently, preventing error propagation and ensuring uniform error protection across all information bits without requiring padding bits, thus maintaining the original code rate.
2Reliability
If memory effects are used in AI/ML based channel codes, then coding performance is improved, but unequal error protection occurs
Solution Approach 1:
The patent applies preliminary actions by processing input information bits through multiple stages of AI/ML-based encoding. The first encoder processes the entire input, while subsequent encoders process segmented blocks with memory effects applied selectively. This preliminary multi-stage encoding ensures uniform error protection while maintaining coding performance.
Data Source
AI summary
UE capability for support of machine-learning (ML) based channel environment classification may be reported by a user equipment to a base station, where the channel environment classification classifies a channel environment of a channel between the UE and a base station based on one or more of UE speed or Doppler spread, UE trajectory, frequency selectivity or delay spread, coherence bandwidth, coherence time, radio resource management (RRM) metrics, block error rate, throughput, or UE acceleration. The user equipment may receive configuration for ML based channel environment classification, including at least enabling/disabling of ML based channel environment classification. When ML based channel environment classification is enabled, UE assistance information for ML based channel environment classification, and/or an indication of the channel environment (which may be a pre-defined channel environment associated with a lookup table), may be transmitted by the user equipment to the base station.