Abstract

Digital pre-distortion (DPD) is a powerful technique to mitigate transmitter nonlinear distortion in optical transmissions. In this Letter, the identification of DPD coefficients based on the direct learning architecture (DLA) using the Gauss–Newton (GN) method is applied in optical communications for the first time. To the best of our knowledge, this is the first time that the DLA has been realized without training an auxiliary neural network to mitigate optical transmitter nonlinear distortion. We describe the principle of the DLA using the GN method and compare the DLA with the indirect learning architecture (ILA) that uses the least-square (LS) method. Extensive numerical and experimental results indicate that the GN-based DLA is superior to the LS-based ILA, especially in a low signal-to-noise ratio scenario.

© 2023 Optica Publishing Group

Deep Gauss–Newton for phase retrieval

Kannara Mom, Max Langer, and Bruno Sixou
Opt. Lett. 48(5) 1136-1139 (2023)

Pre-equalization scheme for visible light communications with trial-and-error learning

Shupeng Li, Yi Zou, Fangming Liu, and Jian Song
Opt. Lett. 49(6) 1636-1639 (2024)

Wiener-Hammerstein model and its learning for nonlinear digital pre-distortion of optical transmitters

Takeo Sasai, Masanori Nakamura, Etsushi Yamazaki, Asuka Matsushita, Seiji Okamoto, Kengo Horikoshi, and Yoshiaki Kisaka
Opt. Express 28(21) 30952-30963 (2020)

Nonlinear distortion mitigation of DML-based OFDM optical systems with non-orthogonal DFT-precoding

Peiji Song, Zhouyi Hu, Yizhan Dai, and Chun-Kit Chan
Opt. Lett. 48(17) 4613-4616 (2023)

Nonlinearity mitigation for high-speed optical OFDM transmitters using digital pre-distortion

Yuan Bao, Zhaohui Li, Jianping Li, Xinhuan Feng, Bai-ou Guan, and Guifang Li
Opt. Express 21(6) 7354-7361 (2013)