ML-Assisted Equalization for 50-Gb/s/λ O-Band CWDM Transmission Over 100-km SMF

Abstract

We propose and demonstrate a bidirectional Vanilla recurrent neural network (Vanilla-RNN) based equalization scheme for O-band coarse wavelength division multiplexed (CWDM) transmission. Based on a 4 × 50-Gb/s intensity modulation and direct detection (IM/DD) system, we demonstrate the significantly better bit error rate (BER) performance of the Vanilla-RNN scheme over the conventional decision feedback equalizer (DFE) for both Nyquist on-off keying (OOK) and Nyquist 4-ary pulse amplitude modulation (PAM4) formats. It is shown that the Vanilla-RNN equalizer is capable of compensating for both linear and nonlinear impairments induced by the transceiver and the single-mode fiber (SMF). As a result, up to 100-km and 75-km SMF transmission can be achieved for OOK and PAM4 transmission, respectively. Furthermore, through the comparison with other equalization schemes, including the linear equalizer, 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> -order Volterra equalizer, and Volterra+DFE, it is demonstrated that the Vanilla-RNN equalizer achieves the best BER performance. In the meantime, it also exhibits lower implementation complexity when compared to Volterra-based schemes. Our results show that the Vanilla-RNN scheme is a viable solution for realizing simple and effective equalization. This work serves as an exploration and offers useful insights for future implementations of reach-extended O-band CWDM IM/DD systems.