High Speed PAM-8 Optical Interconnects with Digital Equalization based on Neural Network

Gaiarin, Simone; Pang, Xiaodan; Ozoliņš, Oskars; Jones, Rasmus T.; Silva, Edson Porto da; Schatz, Richard; Westergren, Urban; Popov, Sergei; Jacobsen, Gunnar; Zibar, Darko

doi:10.1364/acpc.2016.as1c.1

Cited by 40 publications

(29 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For directly modulated lasers systems with direct detection, NNs have been proposed as a method to pre-compensate the signal to increase the tolerance to chromatic dispersion [17]. Furthermore, NNs have also been proposed for equalization in 8-ary pulse amplitude modulated (8PAM) direct-detection systems [18]. In [19], NNs are proposed to mitigate various system impairments for coherent polarization-multiplexed (PM) 16ary quadrature amplitude modulation (QAM).…”

Section: Introductionmentioning

confidence: 99%

Applying Neural Networks in Optical Communication Systems: Possible Pitfalls

Eriksson

Bülow

Leven

2017

IEEE Photon. Technol. Lett.

158

View full text Add to dashboard Cite

Abstract-We investigate the risk of overestimating the performance gain when applying neural network based receivers in systems with pseudo random bit sequences or with limited memory depths, resulting in repeated short patterns. We show that with such sequences, a large artificial gain can be obtained which comes from pattern prediction rather than predicting or compensating the studied channel/phenomena.

show abstract

Section: Introductionmentioning

confidence: 99%

Applying Neural Networks in Optical Communication Systems: Possible Pitfalls

Eriksson

Bülow

Leven

2017

IEEE Photon. Technol. Lett.

158

View full text Add to dashboard Cite

show abstract

“…Deep learning has also been considered for short-reach communications. For instance, in [16] ANNs are considered for equalization in PAM8 IM/DD systems. Bit-error rates (BERs) below the forward error correction (FEC) threshold have been experimentally demonstrated over 4 km transmission distance.…”

mentioning

confidence: 99%

End-to-End Deep Learning of Optical Fiber Communications

Karanov

Chagnon

Thouin

et al. 2018

J. Lightwave Technol.

332

168

View full text Add to dashboard Cite

In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applying it to intensity modulation/direct detection (IM/DD) systems and show that we can achieve bit error rates below the 6.7% hard-decision forward error correction (HD-FEC) threshold. We model all componentry of the transmitter and receiver, as well as the fiber channel, and apply deep learning to find transmitter and receiver configurations minimizing the symbol error rate. We propose and verify in simulations a training method that yields robust and flexible transceivers that allow-without reconfiguration-reliable transmission over a large range of link dispersions. The results from end-to-end deep learning are successfully verified for the first time in an experiment. In particular, we achieve information rates of 42 Gb/s below the HD-FEC threshold at distances beyond 40 km. We find that our results outperform conventional IM/DD solutions based on 2 and 4 level pulse amplitude modulation (PAM2/PAM4) with feedforward equalization (FFE) at the receiver. Our study is the first step towards end-to-end deep learning-based optimization of optical fiber communication systems.

show abstract

“…Only lately, machine learning algorithms have been in the spotlight of the optical communications community 40 . They are being considered for optical network monitoring and optimization 41,42,43 , optical header recognition 44 and mitigation of transmission effects 45,46,47,48,49,50,51,52,53,54 . Still, the drawback of applying these standard tools in ultrafast systems is that they are computationally expensive and still far away from reaching real-time processing at telecom data rates.In the present work, we provide a first validation that neuro-inspired information processing based on photonic implementations can address critical issues in the field of signal processing for high-speed communications.Specifically, we demonstrate that techniques like ELM and RC can offer solutions to data recovery of distorted signals from extended fibre transmission.…”

mentioning

confidence: 99%

Photonic machine learning implementation for signal recovery in optical communications

Argyris

Bueno

Fischer

2018

Sci Rep

141

View full text Add to dashboard Cite

Machine learning techniques have proven very efficient in assorted classification tasks. Nevertheless, processing time-dependent high-speed signals can turn into an extremely challenging task, especially when these signals have been nonlinearly distorted. Recently, analogue hardware concepts using nonlinear transient responses have been gaining significant interest for fast information processing. Here, we introduce a simplified photonic reservoir computing scheme for data classification of severely distorted optical communication signals after extended fibre transmission. To this end, we convert the direct bit detection process into a pattern recognition problem. Using an experimental implementation of our photonic reservoir computer, we demonstrate an improvement in bit-error-rate by two orders of magnitude, compared to directly classifying the transmitted signal. This improvement corresponds to an extension of the communication range by over 75%. While we do not yet reach full real-time post-processing at telecom rates, we discuss how future designs might close the gap.

show abstract

High Speed PAM-8 Optical Interconnects with Digital Equalization based on Neural Network

Abstract: Abstract:We experimentally evaluate a high-speed optical interconnection link with neural network equalization. Enhanced equalization performances are shown comparing to standard linear FFE for an EML-based 32 GBd PAM-8 signal after 4-km SMF transmission.

Cited by 40 publications

References 5 publications

Applying Neural Networks in Optical Communication Systems: Possible Pitfalls

Applying Neural Networks in Optical Communication Systems: Possible Pitfalls

End-to-End Deep Learning of Optical Fiber Communications

Photonic machine learning implementation for signal recovery in optical communications

Contact Info

Product

Resources

About