Blind Equalization and Channel Estimation in Coherent Optical Communications Using Variational Autoencoders

Lauinger, Vincent; Buchali, Fred; Schmalen, Laurent

doi:10.1109/jsac.2022.3191346

Cited by 27 publications

(36 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A current publication investigates the generative performance of the VAE in a millimeter-wave UAV scenario [11]. Channel equalization is another domain where the VAE is applied successfully [12][13][14], as well as channel estimation [15].…”

Section: Introductionmentioning

confidence: 99%

CSI Clustering with Variational Autoencoding

Baur

Wurth

Andrei

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Classical methods for model order selection often fail in scenarios with low SNR or few snapshots. Deep learning based methods are promising alternatives for such challenging situations as they compensate lack of information in observations with repeated training on large datasets. This manuscript proposes an approach that uses a variational autoencoder (VAE) for model order selection. The idea is to learn a parameterized conditional covariance matrix at the VAE decoder that approximates the true signal covariance matrix. The method itself is unsupervised and only requires a small representative dataset for calibration purposes after training of the VAE. Numerical simulations show that the proposed method clearly outperforms classical methods and even reaches or beats a supervised approach depending on the considered snapshots.

show abstract

Section: Introductionmentioning

confidence: 99%

CSI Clustering with Variational Autoencoding

Baur

Wurth

Andrei

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…One reason is the recent use of machine learning techniques, more specifically artificial neural networks (ANNs), that can mitigate device and transmission impairments and solve specific tasks that are difficult to solve with traditional methods. In this paper, we focus on the problem of channel equalization, which can profit largely from the use of machine learning and ANNs, see, e.g., [1]- [3].…”

Section: Introductionmentioning

confidence: 99%

Spiking Neural Network Decision Feedback Equalization

Bansbach¹,

Bank²,

Schmalen³

2022

Preprint

View full text Add to dashboard Cite

In the past years, artificial neural networks (ANNs) have become the de-facto standard to solve tasks in communications engineering that are difficult to solve with traditional methods. In parallel, the artificial intelligence community drives its research to biology-inspired, brain-like spiking neural networks (SNNs), which promise extremely energy-efficient computing. In this paper, we investigate the use of SNNs in the context of channel equalization for ultra-low complexity receivers. We propose an SNN-based equalizer with a feedback structure akin to the decision feedback equalizer (DFE). To convert realworld data into spike signals, we introduce a novel ternary encoding and compare it with traditional log-scale encoding. We show that our approach clearly outperforms conventional linear equalizers for three different exemplary channels. We highlight that mainly the conversion of the channel output to spikes introduces a minor performance penalty. The proposed SNN with a decision feedback structure enables the path to competitive energy-efficient transceivers.

show abstract

“…( 2)]), and may not be able to accurately model the interplay between linear and nonlinear distortions that exist in many practical systems. In [27], the VAE-based equalizer was generalized to cope with high-order modulation formats coupled with probabilistic constellation shaping and shown to be more performant than the CMA-based equalizer over a polarizationmultiplexed optical fiber channel. While [27] showed promising performance of the VAE-based equalizer, the approach assumes a linear dispersive channel, and the equalizer training requires a closed-form analytical solution of the evidence lower bound (ELBO) (see [25]- [27] for more details), which is only available for channels that can be described in a simple form (e.g., the linear additive white Gaussian noise (AWGN) channel considered in [25]- [27]).…”

mentioning

confidence: 99%

“…In [27], the VAE-based equalizer was generalized to cope with high-order modulation formats coupled with probabilistic constellation shaping and shown to be more performant than the CMA-based equalizer over a polarizationmultiplexed optical fiber channel. While [27] showed promising performance of the VAE-based equalizer, the approach assumes a linear dispersive channel, and the equalizer training requires a closed-form analytical solution of the evidence lower bound (ELBO) (see [25]- [27] for more details), which is only available for channels that can be described in a simple form (e.g., the linear additive white Gaussian noise (AWGN) channel considered in [25]- [27]). However, many practical communication scenarios, including communication over the optical fiber channel, and transmission with nonideal hardware components (e.g., nonlinear power amplifiers (PAs), quantization-constrained receivers), cannot be accurately modeled in a simple form (e.g., as an AWGN channel).…”

mentioning

confidence: 99%

“…However, many practical communication scenarios, including communication over the optical fiber channel, and transmission with nonideal hardware components (e.g., nonlinear power amplifiers (PAs), quantization-constrained receivers), cannot be accurately modeled in a simple form (e.g., as an AWGN channel). Consequently, the applicability of the VAE-based equalizer proposed in [25]- [27] is limited.…”

mentioning

confidence: 99%

See 1 more Smart Citation

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

Blind Equalization and Channel Estimation in Coherent Optical Communications Using Variational Autoencoders

Cited by 27 publications

References 36 publications

CSI Clustering with Variational Autoencoding

CSI Clustering with Variational Autoencoding

Spiking Neural Network Decision Feedback Equalization

Blind Channel Equalization Using Vector-Quantized Variational Autoencoders

Contact Info

Product

Resources

About