Wideband Power Amplifier Behavioral Modeling Using an Amplitude Conditioned LSTM

TL;DR

This paper introduces an amplitude conditioned LSTM model for wideband power amplifier behavioral modeling, significantly improving accuracy and spectral fidelity over traditional methods by explicitly incorporating amplitude-dependent effects.

Contribution

The paper presents a novel AC-LSTM architecture with amplitude-dependent gating and FiLM conditioning, enhancing modeling of wideband PA nonlinearities and memory effects.

Findings

Achieves NMSE of -41.25 dB, outperforming standard LSTM and ARVTDNN.

Provides spectral modeling with ACPR of -28.58 dB, closely matching measured data.

Demonstrates improved time-domain and spectral fidelity in wideband PA modeling.

Abstract

Wideband power amplifiers exhibit complex nonlinear and memory effects that challenge traditional behavioral modeling approaches. This paper proposes a novel amplitude conditioned long short-term memory (AC-LSTM) network that introduces explicit amplitude-dependent gating to enhance the modeling of wideband PA dynamics. The architecture incorporates a Feature-wise Linear Modulation (FiLM) layer that conditions the LSTM's forget gate on the instantaneous input amplitude, providing a physics-aware inductive bias for capturing amplitude-dependent memory effects. Experimental validation using a 100 MHz 5G NR signal and a GaN PA demonstrates that the proposed AC-LSTM achieves a normalized mean square error (NMSE) of -41.25 dB, representing a 1.15 dB improvement over standard LSTM and 7.45 dB improvement over augmented real-valued time-delay neural network (ARVTDNN) baselines. The model also closely matches the measured PA's spectral characteristics with an adjacent channel power ratio (ACPR) of -28.58 dB. These results shows the effectiveness of amplitude conditioning for improving both time-domain accuracy and spectral fidelity in wide-band PA behavioral modeling.