Bibliographic Details
| Title: |
An adaptive gated dual-branch model for joint compensation of power amplifier distortion and I/Q imbalance. |
| Authors: |
Tang, Shengqiang1 (AUTHOR), Yao, Yao2 (AUTHOR), Li, Mingyu1 (AUTHOR) myli@cqu.edu.cn, Li, Junan1 (AUTHOR), Kong, Shuman1 (AUTHOR), Cai, Tianfu1 (AUTHOR) |
| Source: |
AEU: International Journal of Electronics & Communications. Sep2026, Vol. 215, pN.PAG-N.PAG. 1p. |
| Subjects: |
Transmitters (Communication), Electronic linearization |
| Abstract: |
To address the coupled effects of power amplifier (PA) nonlinearity and in-phase/quadrature (I/Q) imbalance in direct-conversion transmitters, an adaptive gated dual-branch memory polynomial model (AG-DMP) is proposed to achieve their joint compensation. The proposed model consists of a linear memory branch, a nonlinear residual branch, and an attention gating mechanism. The linear memory branch explicitly captures the dominant linear dynamics and memory effects, while the nonlinear branch employs a lightweight multilayer perceptron (MLP) to learn residual nonlinear distortions that cannot be adequately described by the linear branch. The outputs of the two branches are then adaptively fused by the attention gating mechanism, enabling the model to dynamically adjust their relative contributions under different operating conditions. To validate the proposed method, forward behavioral modeling and digital predistortion (DPD) experiments were conducted using measured broadband transmitter data. The results demonstrate that AG-DMP achieves higher modeling accuracy in forward modeling and superior suppression of spectral regrowth in DPD linearization. Overall, the predistortion system based on the proposed AG-DMP model provides an efficient solution for the joint compensation of multiple radio frequency (RF) front-end impairments in broadband transmitters, while maintaining a favorable balance between performance and implementation complexity. [ABSTRACT FROM AUTHOR] |
|
Copyright of AEU: International Journal of Electronics & Communications is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |