Computation efficient sparse DNN nonlinear equalization for IM/DD 112 Gbps PAM4 inter-data center optical interconnects
Govind Sharan Yadav, Chun-Yen Chuang, Kai-Ming Feng, Jyehong Chen, Young-Kai Chen
Abstract
In this Letter, we propose and experimentally demonstrate a novel, to the best of our knowledge, sparse deep neural network-based nonlinear equalizer (SDNN-NLE). By identifying only the significant weight coefficients, our approach remarkably reduces the computational complexity, while still upholding the desired transmission accuracy. The insignificant weights are pruned in two phases: identifying the significance of each weight by pre-training the fully connected DNN-NLE with an adaptive L2-regularization and then pruning those insignificant ones away with a pre-defined sparsity. An experimental demonstration is conducted on a 112 Gbps PAM4 link over 40 km standard single-mode fiber with a 25 GHz externally modulated laser in O-band. Our experimental results illustrate that, for the 112 Gbps PAM4 signal at a received optical power of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> <mml:mrow class="MJX-TeXAtom-ORD"> <mml:mo>−</mml:mo> </mml:mrow> <mml:mrow class="MJX-TeXAtom-ORD"> <mml:mn>5</mml:mn> </mml:mrow> <mml:mspace width="thickmathspace"/> <mml:mrow class="MJX-TeXAtom-ORD"> <mml:mi mathvariant="normal">d</mml:mi> <mml:mi mathvariant="normal">B</mml:mi> <mml:mi mathvariant="normal">m</mml:mi> </mml:mrow> </mml:math> over 40 km, the proposed SDNN-NLE exhibits promising solutions to effectively mitigate nonlinear distortions and outperforms a conventional fully connected Volterra equalizer (VE), conventional fully connected DNN-NLE, and sparse VE by providing 71%, 63%, and 41% complexity reduction, respectively, without degrading the system performance.