Modulation Format Identification in Mode Division Multiplexed Optical Networks

Waddah S Saif,Amr M Ragheb,Saleh A Alshebeili,Tariq A Alshawi,Hussein E Seleem

doi:10.1109/access.2019.2949201

Abstract

In this paper, we address the problem of modulation format identification (MFI) for few mode fiber (FMF) transmission in elastic optical networks (EONs). The MFI accuracy is studied under different FMF channel conditions including mode coupling (MC), optical signal-to-noise ratio (OSNR), and chromatic dispersion (CD). Artificial neural network, trained using features extracted from the asynchronous in-phase quadrature histogram (IQH), is proposed to investigate the identification accuracy. Extensive simulation results have been conducted to identify six modulation schemes widely used in polarization division multiplexing coherent optical networks. This includes PDM-BPSK, PDM-QPSK, PDM-8QAM, PDM-16QAM, PDM-32QAM, and PDM-64QAM transmitted at 10 Gbaud network transmission speed. The results show that the proposed MFI achieves a successful average identification accuracy exceeding 98% in the presence of low MC when the incoming signal OSNR is greater than 20 dB. However, the effect of high MC and CD = 1100 ps/nm reduces the average accuracy to 90%. Further, the MFI accuracy is investigated under different symbol rates such as 14 and 20 Gbaud.

Highlights

Machine learning (ML) has shown an intensive impact on the recent advances of the optical communication field
We considered modulation format identification for few-mode fiber in optical networks for six commonly used types of polarization division multiplexing (PDM)-QAM and PDM-PSK signals, and the transmission of five propagating spatial modes
The identification is achieved using features extracted from the in-phase quadrature histogram, along with the utilization of a feed-forward artificial neural network

Summary

INTRODUCTION

Machine learning (ML) has shown an intensive impact on the recent advances of the optical communication field. MFI in SMF-based optical networks has been investigated thoroughly in the last few years In this regard, the asynchronous amplitude histogram (AAH) [13]–[15] and the cumulative distribution function (CDF) [16], [17] of the received samples have been exploited in the feature-based recognition algorithms. Besides the traditional SMF’s impairments, FMF has its own impairments that limit the communication over such type of SDM networks; an example of which is the mode coupling (MC) effect resulting from the lateral misalignment of optical connectors. The modulation pool includes six formats commonly used in polarization division multiplexing (PDM) coherent optical systems, and transmitted at 10 Gbaud network speed. It is expected that the IQH improves the MFI performance accuracy in comparison with the onedimensional methods such as the AAH [14]

MFI USING ANN TRAINED WITH IQH

RESULTS AND DISCUSSION

CONCLUSION