AUTHOREA
Log in
Sign Up
Browse Preprints
LOG IN
SIGN UP
Essential Site Maintenance
: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at
[email protected]
in case you face any issues.
Wantao Li
Member of:
Universidad Politécnica de Cataluna
Public Documents
1
GPU-Based Implementation of Pruned Artificial Neural Networks for Digital Predistorti...
Wantao Li
and 5 more
July 29, 2024
This paper presents a feature selection technique based on ℓ1 regularization to select the most relevant weights of artificial neural networks (ANNs) for digital predistortion (DPD) linearization of wideband radio-frequency (RF) power amplifiers (PAs). The proposed pruning method is applied to the first hidden layer of a feed-forward real-valued time-delay neural network, commonly used for DPD purposes. In addition, this paper presents the ANN-based DPD implementation using a graphic processing unit (GPU) with compute unified device architecture (CUDA) units. Thanks to the proposed pruning strategy, it is possible to reduce the ANN complexity significantly, thereby achieving a higher data throughput with the GPUbased implementation. The trade-off among RF performance metrics, number of model parameters and throughput of the GPU implementation is evaluated considering the linearization of a high-efficiency pseudo-Doherty load modulated balanced amplifier (LMBA). The linearized PA operating at 2 GHz RF frequency delivers a mean output power of 40 dBm with around 50% power efficiency when being excited with 5G new radio signals with up to 200 MHz bandwidth and 8 dB peak-to-average power ratio (PAPR). The real-time GPU implementation of the ANN-based DPD can meet the linearity specifications with a throughput circa 1 GSa/s.