Deep Neural Network-Based Digital Pre-Distortion for High Baudrate Optical Coherent Transmission

Bajaj, Vinod; Buchali, Fred; Chagnon, Mathieu; Wahls, Sander; Aref, Vahid

doi:10.1109/jlt.2021.3122161

Cited by 38 publications

(8 citation statements)

References 40 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies have emphasized the effectiveness of Direct Learning Architectures (DLA) and end-to-end (E2E) learning systems in optimizing nonlinear DPD for optical transmission systems [15], [16], [17], [13]. The DLA is an approach specifically designed for optimizing nonlinear DPD, which has consistently shown to outperform the ILA in both wireless and optical communications [12], [13], [18], [17]. E2E learning on the other hand is an approach which envisions the joint co-optimization of various digital signal processing (DSP) components at the transmitter and receiver, not only for nonlinear DPD but also for other modules in VCSEL-based optical interconnects [19].…”

Section: Nonlinear Digital Pre-distortion For Improving Vcsel-mmf Opt...mentioning

confidence: 99%

TDECQ-Based Optimization of Nonlinear Digital Pre-Distorters for VCSEL-MMF Optical Links Using End-to-End Learning

Minelli,

Forghieri,

Shao

et al. 2024

J. Lightwave Technol.

View full text Add to dashboard Cite

We investigate in this paper the use of nonlinear digital pre-distorters (DPDs) for improving the performance of optical transmitters (TX) employing vertical-cavity surfaceemitting lasers (VCSELs), according to the standard transmitter and dispersion eye closure quaternary (TDECQ) compliance test for short-reach intra data center interconnects (DCI) using PAM4 over multi-mode fibers (MMF). We present a convolutional neural network (CNN) approach for nonlinear DPD optimization, suitable for training the pre-distorters using either a direct learning architecture (DLA) or an end-to-end (E2E) learning system. Then, we focus on a novel E2E architecture based on the reference TDECQ specifications for MMF optical links at net 100 Gbps per wavelength (λ). We experimentally implement the proposed methodology over a VCSEL-MMF setup compliant to the TDECQ test requirements. We evaluate the TDECQ performance of an optical TX employing a commercial 850 nm VCSEL at 107.2 Gbps driven at several nonlinear conditions, comparing nonlinear DPDs optimized using both DLA and TDECQ-based E2E approaches. Experimental results show that nonlinear DPD significantly enhances TDECQ performance, enabling compliance with the IEEE P802.3db TM requirements for net 100 Gbps/λ even in scenarios in which, without nonlinear DPD, the TDECQ test would fail due to VCSEL nonlinear distortions. In particular, nonlinear DPDs trained using the TDECQ-based E2E approach exhibit a consistent 0.8 dB gain in terms of TDECQ with respect to using the DLA.

show abstract

Section: Nonlinear Digital Pre-distortion For Improving Vcsel-mmf Opt...mentioning

confidence: 99%

TDECQ-Based Optimization of Nonlinear Digital Pre-Distorters for VCSEL-MMF Optical Links Using End-to-End Learning

Minelli,

Forghieri,

Shao

et al. 2024

J. Lightwave Technol.

View full text Add to dashboard Cite

show abstract

“…The pre-stored FIR coefficients can also be used to reduce the convergence time. Several neural network-based equalization methods have been proposed to achieve more efficient channel equalization [62,63] . For instance, leveraging end-to-end optimized deep neural networks has been shown to highly enhance sensitivity [55] .…”

Section: Coherent Detection Enabled Wide Coveragementioning

confidence: 99%

Untitled

2024

中国光学快报

View full text Add to dashboard Cite

Increasing bandwidth requirements have posed significant challenges for traditional access networks. It is difficult for intensity modulation/direct detection to meet the power budget and flexibility requirements of the next-generation passive optical network (PON) at 100G and beyond considering the new requirements. This is driving researchers to develop novel optical access technologies. Low-cost, wide-coverage, and high-flexibility coherent PON is emerging as a strong contender in the competition. In this article, we will review technologies that reduce the complexity of coherent PON (CPON), enabling it to meet the commercial requirements. Also, advanced algorithms and architectures that can enhance system coverage and flexibility are also discussed.

show abstract

“…7. Such a residual connection has been shown to improve the performance as well as NN training in several communication related applications [46]- [48]. Furthermore, instead of having the raw channel observations y as input, our NN-based equalizer takes a nonlinear feature vector s k as input and generates the k-th equalized signal according to xk = f φ (s k ).…”

Section: A Nonlinear Optical Fiber Channelmentioning

confidence: 99%

Blind Channel Equalization Using Vector-Quantized Variational Autoencoders

Song¹,

Lauinger²,

Wu³

et al. 2023

Preprint

View full text Add to dashboard Cite

State-of-the-art high-spectral-efficiency communication systems employ high-order modulation formats coupled with high symbol rates to accommodate the ever-growing demand for data rate-hungry applications. However, such systems are more vulnerable to linear and nonlinear transmission impairments, and it is important to mitigate the performance loss via digital signal processing. In this paper, we propose a novel machine learning approach for blind channel equalization and estimation using the vector quantized (VQ) variational autoencoder (VAE) framework. The proposed approach generalizes the applicability of the conventional VAE-based equalizer to nonlinear systems employing high-order modulation formats by introducing a codebook component and an associated novel loss function. We evaluate the performance of the proposed method over a linear additive white Gaussian noise channel with intersymbol interference and two nonlinear scenarios. Simulation results show that the proposed method can achieve similar performance as a data aided equalizer using the minimum-mean-squarederror (MMSE) criterion, and outperforms the blind constant modulus algorithm (CMA) and the VAE-based channel equalizer. Furthermore, we show that for the linear channel, the proposed scheme exhibits better convergence properties than the MMSEbased, the CMA-based, and the VAE-based equalizers in terms of both convergence speed and robustness to variations in training batch size and learning rate. I. INTRODUCTIONThe performance of communication systems is constrained by the linear and nonlinear distortions originating from hardware impairments and non-ideal communication channels.

show abstract

Deep Neural Network-Based Digital Pre-Distortion for High Baudrate Optical Coherent Transmission

Cited by 38 publications

References 40 publications

TDECQ-Based Optimization of Nonlinear Digital Pre-Distorters for VCSEL-MMF Optical Links Using End-to-End Learning

TDECQ-Based Optimization of Nonlinear Digital Pre-Distorters for VCSEL-MMF Optical Links Using End-to-End Learning

Untitled

Blind Channel Equalization Using Vector-Quantized Variational Autoencoders

Contact Info

Product

Resources

About