Symbol-Based Over-the-Air Digital Predistortion Using Reinforcement Learning

2021/11/23 by Yibo Wu, Jinxiang Song, Wu, Yibo +9
Engineering · #Advanced Power Amplifier Design #Advancements in Semiconductor Devices and Circuit Design #FOS: Electrical engineering #Radio Frequency Integrated Circuit Design #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2111.11923

openalex publication_date 2021/11/23 · openalex created_date 2021/12/06 · openalex updated_date 2026/07/28

Abstract

We propose an over-the-air digital predistortion optimization algorithm using reinforcement learning. Based on a symbol-based criterion, the algorithm minimizes the errors between downsampled messages at the receiver side. The algorithm does not require any knowledge about the underlying hardware or channel. For a generalized memory polynomial power amplifier and additive white Gaussian noise channel, we show that the proposed algorithm achieves performance improvements in terms of symbol error rate compared with an indirect learning architecture even when the latter is coupled with a full sampling rate ADC in the feedback path. Furthermore, it maintains a satisfactory adjacent channel power ratio.

Citations

• A Generalized Memory Polynomial Model for Digital Predistortion of RF Power Amplifiers

Related

• Over-the-fiber Digital Predistortion Using Reinforcement Learning
• Design and Implementation of a Neural Network Based Predistorter for Enhanced Mobile Broadband
• A Digital Predistortion Scheme Exploiting Degrees-of-Freedom for Massive MIMO Systems
• Efficient attention guided 5G power amplifier digital predistortion
• Reinforcement Learning Based Goodput Maximization with Quantized Feedback in URLLC