Machine-Learned Wireless Mapping and Demapping for Nonlinear Channels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Nonlinearities in wireless communication channels, particularly due to high power amplifiers in satellite systems, hinder accurate reception and efficiency in wireless communication systems.
Innovation Solution
Optimization techniques are applied to both the mapper and demapper using machine learning, such as neural networks, to adjust symbol constellations and compensate for nonlinearity, including predistortion compensation to mitigate distortion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If the high power amplifier operates in a nonlinear region to improve power efficiency, then power efficiency is improved, but reception accuracy deteriorates
Solution Approach 1:
The system applies preliminary predistortion to the transmitted signal before it enters the nonlinear amplifier. The mapper and demapper are jointly optimized in advance to compensate for the known nonlinear characteristics of the amplifier, allowing the system to operate in the nonlinear region while maintaining reception accuracy through pre-applied compensation.
Solution Approach 2:
The system changes the parameters of the symbol constellation through joint optimization of the mapper and demapper. By adjusting constellation point locations and distributions based on the nonlinear channel characteristics, the system adapts the transmission parameters to compensate for amplifier nonlinearity, enabling both high power efficiency and accurate reception.
2Measurement precision
If machine learning techniques are used to optimize mapping and demapping, then reception accuracy is improved, but device complexity increases
Solution Approach 1:
The system employs self-service through automatic joint optimization of the mapper and demapper using machine learning. The neural networks automatically learn and adapt to the channel characteristics and nonlinearities without requiring manual configuration or complex external control systems, reducing operational complexity while maintaining high reception accuracy.
3Measurement precision
If symbol constellations are adjusted to compensate for nonlinearity, then reception accuracy is improved, but manufacturing precision requirements increase
Solution Approach 1:
The system uses feedback through the joint optimization process where the demapper provides information back to the mapper about the received signal characteristics and errors. This feedback loop allows the system to automatically adjust constellation parameters to compensate for nonlinearity, reducing the need for manual precision in constellation configuration while achieving accurate compensation.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for optimization of mapping and demapping for wireless communication channels. In some implementations, a transmitter includes a mapper that has been trained through machine learning training. The transmitter is trained based at least in part on demapper characteristics for a demapper of a receiver. The mapper has parameter values that have been trained to at least partially compensate for non-linear distortion of signals in a wireless communication channel, including through application of non-linear distortion during training. The mapper is configured to map data to be transmitted to symbols in a symbol constellation for transmission. The parameter values of the mapper define characteristics of the symbol constellation including amplitude or phase of the symbols in the symbol constellation.