Hybrid Predistorter Control for Satellite HPA Linearization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Satellite communication systems face nonlinear distortions due to high power amplifier (HPA) nonlinearities, especially when operated at saturation points, which are exacerbated by radio interference, leading to degraded transmission performance and increased vulnerability to interference.
Innovation Solution
A hybrid solution combining an on-ground physical-model based predistorter and a machine-learning based PD controller, which uses a carefully selected HPA model and adjusts parameters in real-time to compensate for AM-AM and AM-PM distortions, incorporating a database of environmental and PD parameters to generate correction signals and update the model dynamically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If HPA is operated at saturation points to maximize power efficiency, then power efficiency is improved, but nonlinear distortions increase
Solution Approach 1:
The predistorter applies preliminary anti-action by introducing opposite nonlinear distortions to the input signal before it reaches the HPA. The predistorter characteristics are designed to be the inverse of the HPA's nonlinear characteristics, so that when the signal passes through both the predistorter and HPA, the distortions cancel each other out, allowing the HPA to operate at saturation without degrading transmission performance
Solution Approach 2:
The system dynamically adjusts predistortion parameters based on environmental conditions (temperature, humidity) and operational states. The machine learning model continuously learns and adapts the predistortion characteristics to match changing HPA behavior, maintaining optimal linearization performance across different operating conditions while preserving power efficiency
2Ease of manufacture
If traditional predistortion methods (LUT, polynomial, channel inversion) are used, then implementation is simple, but vulnerability to radio interference increases
Solution Approach 1:
The system implements feedback mechanisms where the actual HPA output is monitored and compared with expected output. The machine learning model uses this feedback to continuously update and refine the predistortion parameters, enabling the system to adapt to radio interference and environmental changes, thereby reducing vulnerability while maintaining implementation feasibility
Solution Approach 2:
The predistortion system transitions from static traditional methods to dynamic adaptive predistortion. The machine learning model enables real-time adjustment of predistortion parameters based on changing environmental conditions and interference levels, making the system resilient to radio interference while maintaining operational simplicity through automated adaptation
3Reliability
If physical-model based PD with machine-learning controller is implemented, then HPA linearity is improved, but device complexity increases
Solution Approach 1:
The system merges physical modeling with machine learning in a hybrid architecture. The physical model provides a foundational understanding of HPA behavior, while the machine learning component adapts to environmental variations and interference. This combination achieves superior linearity performance while managing complexity through the synergistic integration of deterministic physical principles and adaptive learning
4Reliability
If predistortion parameters are adjusted in real-time to compensate for environmental factors, then transmission performance is improved, but computational requirements increase
Solution Approach 1:
The system performs preliminary action by pre-training the machine learning model offline with extensive environmental data and HPA characteristics. This pre-training establishes a robust foundation that enables efficient real-time adaptation with minimal computational resources during actual operation, balancing transmission performance improvement with acceptable computational requirements
Data Source
AI summary
The present disclosure provides a high power amplifier (HPA) linearization method, applied to a ground hub which includes a predistorter and a PD controller. The ground hub is arranged in a satellite communication system together with a transmitter and a satellite transponder, and the satellite transponder includes an HPA. The HPA linearization method includes determining an initial correction signal based on a physical model with a plurality of PD parameters to compensate AM-AM and AM-PM characteristics of the HPA; receiving a signal from the satellite transponder; determining a reward function for an action taken by the PD controller; examining an action-value function for actions taken in a preset past period; taking an action to adjust the plurality of PD parameters for the PD to generate an updated correction signal; sending the update correction signal to the transmitter to compensate the AM-AM and AM-PM characteristics of the HPA.