4.7 Article

High Dynamic Range 100G PON Enabled by SOA Preamplifier and Recurrent Neural Networks

Journal

JOURNAL OF LIGHTWAVE TECHNOLOGY
Volume 41, Issue 11, Pages 3522-3532

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JLT.2023.3249046

Keywords

Semiconductor optical amplifiers; Gain; Passive optical networks; Optical saturation; Preamplifiers; Fiber nonlinear optics; Optical distortion; Digital signal processing; four-level pulse amplitude modulation; machine learning; optical fiber communications; passive optical network; semiconductor optical amplifier

Ask authors/readers for more resources

The PON research community has been focusing on future systems that aim to achieve 100 Gb/s and above. Digital signal processing, specifically the use of spectrally efficient 4-level pulse amplitude modulation (PAM4), is seen as a key technology for these systems. Semiconductor Optical Amplifiers (SOA) are being investigated as receiver preamplifiers to compensate for the high signal-to-noise ratio requirements of PAM4.
In recent years the PON research community has focused on future systems targeting 100 Gb/s/. and beyond, with digital signal processing seen as a key enabling technology. Spectrally efficient 4-level pulse amplitude modulation (PAM4) is seen as a cost-effective solution that exploits the ready availability of cheaper, low-bandwidth devices, and Semiconductor Optical Amplifiers (SOA) are being investigated as receiver preamplifiers to compensate PAM4's high signal-to-noise ratio requirements and meet the demanding 29 dB PON loss budget. However, SOA gain saturation-induced patterning distortion is a concern in the context of PON burst-mode signalling, and the 19.5 dB loud-soft packet dynamic range expected by the most recent ITU-T 50G standards. In this article we propose a recurrent neural network equalisation technique based on gated recurrent units (GRU-RNN) to not only mitigate SOA patterning affecting loud packet bursts, but to also exploit their remarkable effectiveness at compensating non-linear impairments to unlock the SOA gain saturated regime. Using such an equaliser we demonstrate > 28 dB system dynamic range in 100 Gb/s PAM4 system by using SOA gain compression in conjunction with GRU-RNN equalisation. We find that our proposedGRU-RNNhas similar equalisation capabilities as non-linear Volterra, fully connected neural network, and long short-term memory based equalisers, but observe that feedback-based RNN equalisers are more suited to the varying levels of impairment inherent to PON burst-mode signalling due to their low input tap requirements. Recognising issues surrounding hardware implementation of RNNs, we investigate a multi-symbol equalisation scheme to lower the feedback latency requirements of our proposed GRU-RNN. Finally, we compare equaliser complexities and performances according to trainable parameters and real valued multiplication operations, finding that the proposedGRU-RNN equaliser is more efficient than those based on Volterra, fully connected neural networks or long short-term memory units proposed elsewhere.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available