A modified PSO assisted blind modulation format identification scheme for elastic optical networks

Abstract By using a modified particle swarm optimization (M-PSO) design, a novel and blind modulation format identification (MFI) scheme was proposed for elastic optical networks (EONs) in this study. Compared with the traditional PSO algorithm, the sight of each particle in our M-PSO algorithm was strictly restricted to perform search of local extremum points (LEPs) on density distribution histograms (DDHs). In the experiment, the distributions of LEPs on DDHs depended on signals’ modulation formats, and then were regarded as the key identification metric. The proposed MFI scheme did not need prior information of optical signal noise rate (OSNR) in the identification processes, and showed a natural resistance to frequency offset and line width. The feasibility of the proposed scheme was verified by 28 GBaud polarization division multiplexing (PDM)-BPSK/QPSK/8QAM/16QAM transmission system, where the simulation results showed that the lowest OSNRs required to achieve 100% identification rate were all lower than their corresponding 7% forward error correction (FEC) thresholds (BER=3.8e−3). Furthermore, the tolerance of the residual chromatic dispersion (CD), differential group delay (DGD) and nonlinear effect were also verified under the simulation conditions. The study results manifest that the proposed MFI scheme showed interesting robustness to both linear and nonlinear impairments. Moreover, we also demonstrated a relatively simpler calculation complexity under the proposed MFI scheme.

[1]  Changjian Guo,et al.  Stokes space modulation format classification based on non-iterative clustering algorithm for coherent optical receivers. , 2017, Optics express.

[2]  Chao Lu,et al.  Machine learning methods for optical communication systems and networks , 2020 .

[3]  Qian Xiang,et al.  Joint and Accurate OSNR Estimation and Modulation Format Identification Scheme Using the Feature-Based ANN , 2019, IEEE Photonics Journal.

[4]  Xiaoguang Zhang,et al.  Intelligent bandwidth-estimation technique for orthogonal frequency division multiplexing-based elastic optical networking , 2016, IEEE/OSA Journal of Optical Communications and Networking.

[5]  Nannan Zhang,et al.  Identifying modulation formats through 2D Stokes planes with deep neural networks. , 2018, Optics express.

[6]  Kangping Zhong,et al.  Subtraction-Clustering-Based Modulation Format Identification in Stokes Space , 2017, IEEE Photonics Technology Letters.

[7]  Idelfonso Tafur Monroy,et al.  Clustering algorithms for Stokes space modulation format recognition. , 2015, Optics express.

[8]  Gabriella Bosco,et al.  Blind modulation format identification for digital coherent receivers. , 2015, Optics express.

[9]  Roberto Proietti,et al.  Blind modulation format identification using nonlinear power transformation. , 2017, Optics express.

[10]  Chongjin Xie.  Chromatic Dispersion Estimation for Single-Carrier Coherent Optical Communications , 2013, IEEE Photonics Technology Letters.

[11]  Chao Lu,et al.  Modulation Format Identification in Coherent Receivers Using Deep Machine Learning , 2016, IEEE Photonics Technology Letters.

[12]  Ujjwal,et al.  Review and analysis of elastic optical network and sliceable bandwidth variable transponder architecture , 2018 .

[13]  Lin Jiang,et al.  Modulation format identification and OSNR monitoring using density distributions in Stokes axes for digital coherent receivers. , 2019, Optics express.

[14]  Guo Peng,et al.  A Density Clustering Algorithm for Simultaneous Modulation Format Identification and OSNR Estimation , 2020, Applied Sciences.

[15]  Yahia A. Eldemerdash,et al.  Modulation Classification Using Received Signal’s Amplitude Distribution for Coherent Receivers , 2017, IEEE Photonics Technology Letters.

[16]  Mingyi Gao,et al.  Unsupervised Neural Network for Modulation Format Discrimination and Identification , 2019, IEEE Access.

[17]  Ming Tang,et al.  Modulation format identification enabled by the digital frequency-offset loading technique for hitless coherent transceiver. , 2018, Optics express.

[18]  Liang Shu,et al.  Intelligent optical performance monitor using multi-task learning based artificial neural network. , 2019, Optics express.

[19]  Tianwai Bo,et al.  Blind Density-Peak-Based Modulation Format Identification for Elastic Optical Networks , 2018, Journal of Lightwave Technology.

[20]  Lei Zhao,et al.  Modulus mean square-based blind hybrid modulation format recognition for orthogonal frequency division multiplexing-based elastic optical networking , 2019 .

[21]  Min Zhang,et al.  Cost-effective and data size-adaptive OPM at intermediated node using convolutional neural network-based image processor. , 2019, Optics express.

[22]  Lin Jiang,et al.  An Effective Modulation Format Identification Based on Intensity Profile Features for Digital Coherent Receivers , 2019, Journal of Lightwave Technology.

[23]  Zibo Zheng,et al.  Blind and low-complexity modulation format identification scheme using principal component analysis of Stokes parameters for elastic optical networks. , 2020, Optics express.