Linearized wideband and multi-carrier link based on TL-ANN

Abstract

The analog photonics link (APL) is widely used in microwave photonics. However, in wideband and multi-carrier systems, the third inter-modulation distortion (IMD3) and cross-modulation distortion (XMD) will jointly limit the spurious-free dynamic range (SFDR) of links. In this paper, we experimentally present a linearized wideband and multi-carrier APL, in which the IMD3 and XMD are mitigated simultaneously by using artificial neural networks with transfer learning (TL-ANN). In this experiment, with different artificial neural networks, which are trained with the knowledge obtained from the two- or three-sub-carrier system, the IMD3 and XMD are suppressed by 21.71 dB and 11.11 dB or 22.38 dB and 16.73 dB, and the SFDR is improved by 13.4 dB or 14.3 dB, respectively. Meanwhile, compared with previous studies, this method could reduce the training time and training epochs to 16% and 25%.