DeltaDPD: Exploiting Dynamic Temporal Sparsity in Recurrent Neural Networks for Energy-Efficient Wideband Digital Predistortion

IEEE Microwave and Wireless Technology Letters, vol. 35, pp. 772–775

Abstract

Digital predistortion (DPD) is a popular technique to enhance signal quality in wideband radio frequency (RF) power amplifiers (PAs). With increasing bandwidth and data rates, DPD faces significant energy consumption challenges during deployment, contrasting with its efficiency goals. State-of-the-art DPD models rely on recurrent neural networks (RNNs), whose computational complexity hinders system efficiency. This letter introduces DeltaDPD, exploring the dynamic temporal sparsity of input signals and neuronal hidden states in RNNs for energy-efficient DPD, reducing arithmetic operations and memory accesses while preserving satisfactory linearization performance. Applying a TM3.1a 200 MHz-BW 256-QAM OFDM signal to a 3.5-GHz GaN Doherty RF PA, DeltaDPD achieves −50.03 dBc in adjacent channel power ratio (ACPR), −37.22dB in normalized mean square error (NMSE) and −38.52 dB in error vector magnitude (EVM) with 52% temporal sparsity, leading to a$1.8\times $reduction in estimated inference power. The DeltaDPD code is available athttps://www.opendpd.com.

Authors 7

1. Yizhuo Wu

   Delft University of Technology

   Affiliation as printed

   Department of Microelectronics, Delft University of Technology, Delft, The Netherlands

2. Yi Zhu

   Radboud University Medical Center

   Affiliation as printed

   Ampleon Netherlands B.V., Nijmegen, The Netherlands

3. Qinyu Chen Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

4. Anding Zhu

   University College Dublin

   Affiliation as printed

   School of Electrical and Electronic Engineering, University College Dublin, Dublin, Ireland

5. John Gajadharsing

   Radboud University Medical Center

   Affiliation as printed

   Ampleon Netherlands B.V., Nijmegen, The Netherlands

6. Leo C. N. de Vreede

   Delft University of Technology

   Affiliation as printed

   Department of Microelectronics, Delft University of Technology, Delft, The Netherlands

7. Chang Gao

   Delft University of Technology

   Affiliation as printed

   Department of Microelectronics, Delft University of Technology, Delft, The Netherlands