Distortion Probing Reference Signals for PA Nonlinearity Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In wireless communications, distortion of transmission waveforms due to nonlinear responses from transmission components, such as power amplifiers, hinders successful reception, and existing methods fail to efficiently mitigate this distortion while maintaining power efficiency.
Innovation Solution
A neural network model is used to learn the nonlinear response of transmission components based on distortion probing reference signals with varying peak to average power ratios, allowing for the training of additional models to compensate for distortion and improve power efficiency by estimating transmission and reception metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If reference signals with high peak to average power ratio are transmitted to probe distortion, then distortion measurement accuracy is improved, but transmission power efficiency deteriorates
Solution Approach 1:
The patent transmits reference signals with excessively high peak to average power ratio beyond normal operating conditions to probe and characterize the full extent of nonlinear distortion in the power amplifier, enabling accurate measurement of distortion characteristics that can then be compensated during actual data transmission
Solution Approach 2:
The patent performs preliminary distortion characterization by transmitting probe reference signals before actual data transmission, using the measured distortion characteristics to pre-train neural network models that will compensate for distortion during subsequent communications, thereby improving overall system performance
2Reliability
If neural network models are trained with distortion probing signals, then compensation accuracy for nonlinear responses is improved, but system complexity increases
Solution Approach 1:
The patent creates a virtual copy of the nonlinear distortion characteristics by training a neural network model to replicate the power amplifier's distortion behavior, allowing the system to simulate and compensate for distortion effects without requiring additional physical hardware components
Solution Approach 2:
The patent replaces physical distortion compensation hardware with software-based neural network models that run on existing processing units, substituting complex mechanical or electronic compensation circuits with algorithmic solutions that achieve similar or superior performance
Data Source
AI summary
Methods, systems, and devices for wireless communications are described. A first device and a second device may communicate via a channel. The first device may generate and transmit a reference signal, which may be a distortion probing reference signal with a high peak to average power ratio. In one implementation, the first device may use the reference signal as an input for a neural network model to learn a nonlinear response of the second device transmission components. In another implementation, the second device may sample the generated reference signal, and use the samples as inputs for a neural network model to learn the nonlinear response. The first device and the second device may exchange signaling based on learning the nonlinear response, and each device may compensate for the nonlinear response when communicating via the channel.