Summary of Opendpd: An Open-source End-to-end Learning & Benchmarking Framework For Wideband Power Amplifier Modeling and Digital Pre-distortion, by Yizhuo Wu et al.
OpenDPD: An Open-Source End-to-End Learning & Benchmarking Framework for Wideband Power Amplifier Modeling and Digital Pre-Distortion
by Yizhuo Wu, Gagan Deep Singh, Mohammadreza Beikmirza, Leo C. N. de Vreede, Morteza Alavi, Chang Gao
First submitted to arxiv on: 16 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents an open-source framework called OpenDPD, which enables fast exploration and comparison of digital pre-distortion (DPD) models for wideband power amplifiers. The framework is built on PyTorch and includes a dataset for PA modeling and DPD learning. A novel end-to-end learning architecture trains a Dense Gated Recurrent Unit (DGRU)-DPD model that outperforms previous DPD models in a digital transmitter (DTX) architecture with unconventional transfer characteristics. The paper also presents measurement results, showing the proposed DGRU-DPD achieves an ACPR of -44.69/-44.47 dBc and an EVM of -35.22 dB for 200 MHz OFDM signals. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a special tool called OpenDPD that helps people make better digital pre-distortions for power amplifiers. It’s like a recipe book for making DPD models, but instead of recipes, it has code and data. The authors also made a new type of DPD model using a special kind of neural network, which did really well in tests. They even showed how good it was by comparing it to other models. |
Keywords
* Artificial intelligence * Neural network
