The Library
Attention-aided partial bidirectional RNN-based nonlinear equalizer in coherent optical systems
Tools
Liu, Yifan, Sanchez Silva, Victor, Freire, Pedro J., Prilepsky, Jaroslaw E., Koshkouei, Mahyar J. and Higgins, Matthew D. (2022) Attention-aided partial bidirectional RNN-based nonlinear equalizer in coherent optical systems. Optics Express, 30 (18). 32908-32923 . doi:10.1364/OE.464159 ISSN 1094-4087.
|
PDF
WRAP-Attention-aided-partial-bidirectional-RNN-based-nonlinear-equalizer-in-coherent-optical-systems-Koshkouei-2022.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (2763Kb) | Preview |
Official URL: https://doi.org/10.1364/OE.464159
Abstract
We leverage the attention mechanism to investigate and comprehend the contribution of each input symbol of the input sequence and their hidden representations for predicting the received symbol in the bidirectional recurrent neural network (BRNN)-based nonlinear equalizer. In this paper, we propose an attention-aided novel design of a partial BRNN-based nonlinear equalizer, and evaluate with both LSTM and GRU units in a single-channel DP-64QAM 30Gbaud coherent optical communication systems of 20 × 50 km standard single-mode fiber (SSMF) spans. Our approach maintains the Q-factor performance of the baseline equalizer with a significant complexity reduction of ∼56.16% in the number of real multiplications required to equalize per symbol (RMpS). In comparison of the performance under similar complexity, our approach outperforms the baseline by ∼0.2dB to ∼0.25dB at the optimal transmit power, and ∼0.3dB to ∼0.45dB towards the more nonlinear region.
Item Type: | Journal Article | |||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics Q Science > QC Physics T Technology > TK Electrical engineering. Electronics Nuclear engineering |
|||||||||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | |||||||||||||||
Library of Congress Subject Headings (LCSH): | Optical communications -- Research, Neural networks (Computer science), Signal processing -- Research, Digital communications, Nonlinear optics, Single-mode optical fibers , Equalizers (Electronics), Machine learning | |||||||||||||||
Journal or Publication Title: | Optics Express | |||||||||||||||
Publisher: | Optical Society of America | |||||||||||||||
ISSN: | 1094-4087 | |||||||||||||||
Official Date: | 24 August 2022 | |||||||||||||||
Dates: |
|
|||||||||||||||
Volume: | 30 | |||||||||||||||
Number: | 18 | |||||||||||||||
Page Range: | 32908-32923 | |||||||||||||||
DOI: | 10.1364/OE.464159 | |||||||||||||||
Status: | Peer Reviewed | |||||||||||||||
Publication Status: | Published | |||||||||||||||
Access rights to Published version: | Open Access (Creative Commons) | |||||||||||||||
Date of first compliant deposit: | 24 August 2022 | |||||||||||||||
Date of first compliant Open Access: | 30 August 2022 | |||||||||||||||
RIOXX Funder/Project Grant: |
|
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year