Compensation of Fiber Nonlinearities in Digital Coherent Systems Leveraging Long Short-Term Memory Neural Networks

Deligiannidis, Stavros; Bogris, Adonis; Mesaritakis, Charis; Kopsinis, Yannis

doi:10.1109/jlt.2020.3007919

Cited by 92 publications

(50 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an example, using the CRNN equalizer at -2 dBm launch power, we observe a Q-factor improvement of 0.73 dB in the SC case and a 2.14 dB improvement in the WDM case when compared to the reference Q-factor level (Regular DSP). This effect was also reported by means of numerical simulations in [4], where it was stated that LSTM layers are able to "deterministically" track sufficiently slow XPM effects in scenarios where no information on neighbor channels is fed into the NN-based equalizer.…”

Section: Resultssupporting

confidence: 54%

“…Next, we investigate the performance of the new equalizer in the WDM scenario with 96 channels. In this experiment, we specifically aim to identify whether the biLSTM is capable to compensate for any of the cross-phase modulation (XPM) distortions, as it was observed numerically in [4]. Our results confirm that the NN equalizer architectures that involve a biLSTM layer are able to partially compensate for the XPM induced distortions.…”

Section: Introductionsupporting

confidence: 59%

See 1 more Smart Citation

Complex-Valued Neural Network Design for Mitigation of Signal Distortions in Optical Links

Freire

Neskornuik

Napoli

et al. 2021

J. Lightwave Technol.

View full text Add to dashboard Cite

show abstract

Section: Resultssupporting

confidence: 54%

Section: Introductionsupporting

confidence: 59%

Complex-Valued Neural Network Design for Mitigation of Signal Distortions in Optical Links

Freire

Neskornuik

Napoli

et al. 2021

J. Lightwave Technol.

View full text Add to dashboard Cite

show abstract

“…In the context of channel equalization, the LSTM was suggested in [35], [36] to reduce the transmission impairments in IM/DD systems with pulse amplitude modulation (PAM). The LSTM-based approach was developed further in [17], where, for the first time, the biLSTM was used in an optical coherent system to compensate for fiber nonlinearities, but only in a simulation environment. Additionally, it was shown that the biLSTM also outperformed a low-complexity DBP [17].…”

Section: B Long Short-term Memory Nnsmentioning

confidence: 99%

“…a simple densely connected feedforward NN architecture), convolutional NNs (CNN) [13], [14], echo state networks (ESN) [15], and long short-term memory (LSTM) NNs [16], is efficient in improving optical system-level performance. However, the test of similar NN architectures in coherent optical systems has been carried out, mainly, numerically [17]- [20], or in short-haul experiments [21]- [24]. It is worth noticing that some very recent works evaluated the functioning of NN-based equalizers in metro/long-haul trials [4], [5], [8]- [10].…”

Section: Introductionmentioning

confidence: 99%

Performance Versus Complexity Study of Neural Network Equalizers in Coherent Optical Systems

Freire

Osadchuk

Spinnler

et al. 2021

J. Lightwave Technol.

123

View full text Add to dashboard Cite

We present the results of the comparative performance-versus-complexity analysis for the several types of artificial neural networks (NNs) used for nonlinear channel equalization in coherent optical communication systems. The comparison is carried out using an experimental set-up with the transmission dominated by the Kerr nonlinearity and component imperfections. For the first time, we investigate the application to the channel equalization of the convolution layer (CNN) in combination with a bidirectional long short-term memory (biLSTM) layer and the design combining CNN with a multilayer perceptron. Their performance is compared with the one delivered by the previously proposed NN-based equalizers: one biLSTM layer, three-dense-layer perceptron, and the echo state network. Importantly, all architectures have been initially optimized by a Bayesian optimizer. First, we present the general expressions for the computational complexity associated with each NN type; these are given in terms of real multiplications per symbol. We demonstrate that in the experimental system considered, the convolutional layer coupled with the biLSTM (CNN+biLSTM) provides the largest Q-factor improvement compared to the reference linear chromatic dispersion compensation (2.9 dB improvement). Then, we examine the trade-off between the computational complexity and performance of all equalizers and demonstrate that the CNN+biLSTM is the best option when the computational complexity is not constrained, while when we restrict the complexity to some lower levels, the three-layer perceptron provides the best performance.

show abstract

“…Simplified RNN models have therefore been considered, focusing on TD-FNNs, 5,10,11 and RC. 10,11,[14][15][16] Alternative lower-complexity RNNs architectures such as gated recurrent units (GRUs), 12 and long short-term memory (LSTM) 13 have been applied mainly to coherent transmission so far.…”

Section: Neural Networkmentioning

confidence: 99%

Machine-learning-based equalization for short-reach transmission: neural networks and reservoir computing

Ros¹,

Ranzini

Dischler

et al. 2021

Metro and Data Center Optical Networks and Short-Reach Links IV

View full text Add to dashboard Cite

The substantial increase in communication throughput driven by the ever-growing machine-to-machine communication within a data center and between data centers is straining the short-reach communication links. To satisfy such demand-while still complying with the strict requirements in terms of energy consumption and latency-several directions are being investigated with a strong focus on equalization techniques for intensitymodulation/direct-detection (IM/DD) transmission. In particular, the key challenge equalizers need to address is the inter-symbol interference introduced by the fiber dispersion when making use of the low-loss transmission window at 1550 nm. Standard digital equalizers such as feed-forward equalizers (FFEs) and decision-feedback equalizers (DFEs) can provide only limited compensation. Therefore more complex approaches either relying on maximum likelihood sequence estimation (MLSE) or using machine-learning tools, such as neural network (NN) based equalizers, are being investigated. Among the different NN architectures, the most promising approaches are based on NNs with memory such as time-delay feedforward NN (TD-FNN), recurrent NN (RNN), and reservoir computing (RC). In this work, we review our recent numerical results on comparing TD-FNN and RC equalizers, and benchmark their performance for 32-GBd on-off keying (OOK) transmission. A special focus will be dedicated to analyzing the memory properties of the reservoir and its impact on the full system performance. Experimental validation of the numerical findings is also provided together with reviewing our recent proposal for a new receiver architecture relying on hybrid optoelectronic processing. By spectrally slicing the received signal, independently detecting the slices and jointly processing them with an NN-based equalizer (wither TD-FNN or RC), significant extension reach is shown both numerically and experimentally.

show abstract

Compensation of Fiber Nonlinearities in Digital Coherent Systems Leveraging Long Short-Term Memory Neural Networks

Cited by 92 publications

References 23 publications

Complex-Valued Neural Network Design for Mitigation of Signal Distortions in Optical Links

Complex-Valued Neural Network Design for Mitigation of Signal Distortions in Optical Links

Performance Versus Complexity Study of Neural Network Equalizers in Coherent Optical Systems

Machine-learning-based equalization for short-reach transmission: neural networks and reservoir computing

Contact Info

Product

Resources

About