137 Gb/s PAM-4 Transmissions at 850 nm over 40 cm Optical Backplane with 25 G Devices with Improved Neural Network-Based Equalization

Abstract

An improved neural network-based equalization method is proposed and experimentally demonstrated. The up-to-137 Gb/s transmission of four level pulse amplitude modulation (PAM-4) signals with 25 G class 850 nm optical devices is achieved over an in-house fabricated 40 cm optical backplane. An in-depth investigation is conducted regarding the impact of delayed taps and spans on equalization performance. A performance comparison of the proposed method with the traditional maximum likelihood sequence estimation (MLSE) and decision feedback equalization (DFE) is also undertaken. For the bit rate from 80 to 100 Gb/s, the proposed method achieves an adopted hard-decision forward error correction (HD-FEC) requirement at a received optical power (RoP) of −9 and −8 dBm, while DFE and MLSE cannot meet the HD-FEC requirement. When the bit rate increases from 120 to 137 Gb/s, the proposed equalization method still successfully maintains the acceptable system performance at an RoP of −4 and −2.5 dBm. Furthermore, the specific bit error rate (BER) performances for varied maximum achievable bit rate under different RoPs by applying MLSE and the proposed method are also analyzed. This provides an important potential solution to realize the future data centers.

An Improved End-to-End Autoencoder Based on Reinforcement Learning by Using Decision Tree for Optical Transceivers

“…A low bit error rate index is exchanged for complexity. The computational complexity analysis [4] of the neural network and Adaboost algorithm is as follows.…”

“…The application of machine learning technique in optical communication systems has been studied in many fields in recent years [1,2]. In the field of optical communication systems, many parts of the system, such as performance monitoring, fiber nonlinearity mitigation, carrier recovery, and equalization, have been optimized by machine learning and a neural network [3][4][5][6]. In particular, as we all know, chromatic dispersion (CD) and nonlinear Kerr effects in the fiber are the main constraint in the improvement of the signal rate in the optical communication system today [7].…”

Enhanced Performance of Artificial-Neural-Network-Based Equalization for Short-Haul Fiber-Optic Communications

“…Several types of NNEs have therefore been exploited for the compensation of the electrical nonlinear impairments in the IMDD short-haul fiber-optic communication systems. These include equalizers that are based on single-layer artificial neural networks (ANNs) [19][20][21], two-layer ANNs [22][23][24], radial basis function neural networks [25], convolutional neural networks [23,26,27], recurrent neural networks [28,29], and multi-layer deep neural networks [6,30]. Although the single-layer-ANN-based equalizers are the most basic option among all other types of NNEs, they are more popular to be practicably utilized in the short-reach fiber-optic applications because of their superiority from the computational cost point of view.…”

Long Short-Term Memory Neural Equalizer

“…Some representative works [11], [12], [13] were using a Bayesian statistical model for channel equalization. Neural network-based approaches are used by some prior works [14], [15], [16], [9] for channels equalization. Some uncommonly used low-speed equalization technologies such as Support Vector Machine based equalizer [17], [18], Fuzzy based networks equalizer [19] were more difficult for hardware implementation and are not elaborated in detail here.…”