Modulation Format Identification Based on an Improved RBF Neural Network Trained With Asynchronous Amplitude Histogram

Sida Li,Jing Zhou,Zhiping Huang,Xiaoyong Sun

doi:10.1109/access.2019.2962749

Abstract

This paper proposed a method of modulation format identification using Radial Basis Function Artificial Neural Network (RBF-ANN) trained with Asynchronous Amplitude Histograms (AAHs). Compare with the traditional RBF-ANN, the proposed method is improved by applying Expectation Maximization (EM), which takes advantage of the statistical feature of AAHs, to select center vector for radial basis function. Assuming distribution of each bin in AAH as Gaussian mixture model (GMM), the mean values of the model can be exploited as the center vector which obtained using EM. This approach ensures that the center vector is unbiased and optimal. The center vector is implemented to RBF-ANN to identify different modulation formats. Numerical simulation results demonstrated that identification accuracy was about 99% for three commonly-used modulation formats within the OSNR between 40 ~ 10dB. And the CD tolerance was 1000ps/nm. In comparison, former center vector selection approaches include K-means and random selection were applied. The result showed that the EM method improved the identification accuracy by 2% to 4% when OSNR = 10dB and CD = 100ps/nm. Owing to its excellent performance, this method can be employed in the next generation optical transport network for auto-adaption modulation format identification.

Highlights

The increasing demands of data bandwidth and line rate in modern information society have motivated the upgrading of optical networks
In this paper we propose a resource saving and precise MFI technique based on the Expectation Maximization (EM) improved Radial Basis Function Artificial Neural Network (RBF-artificial neural networks (ANN)) trained with Asynchronous Amplitude Histograms (AAHs)
It is obvious from the table that the identification accuracy of three considered modulation formats is over 99%

Summary

INTRODUCTION

The increasing demands of data bandwidth and line rate in modern information society have motivated the upgrading of optical networks. OPM technology includes optical signal-tonoise ratio (OSNR) estimation, modulation formats identification(MFI), symbol rate estimation and others fiber link crucial injuries monitoring, to name a few, chromatic dispersion (CD), polarization mode dispersion (PMD) and nonliner interferences. S. Li et al.: Modulation Format Identification Based on an Improved RBF Neural Network Trained With AAH. In paper [2], joint OPM and modulation format/Bit-Rate identification approaches based on CNN was proposed. RBF-ANN trained with eye-diagram had been proved to be of limited practical use in OPM [15] The drawback of this approach is that eye-diagram will deteriorate when lacking of clock recovery and compensation for transmission impairments. In this paper we propose a resource saving and precise MFI technique based on the EM improved RBF-ANN trained with AAHs. AAHs are applied to train the RBF-ANN to identify different modulation formats in optical network. AAH is used as the input of the neuron network to identify modulation formats

STRUCTURE OF RBF-ANN

CENTER VECTOR SELECTION OF WITH EXPECTATION MAXIMIZATION (EM)

RESULTS AND DISCUSSION

CONCLUSION