Low-Complexity and Nonlinearity-Tolerant Modulation Format Identification Using Random Forest

A novel low-complexity and nonlinearity-tolerant modulation format identification (MFI) using random forest (RF) is proposed for the flexible coherent receivers (FCRs). The RF-based MFI takes the advantage of distinct features from the amplitude histograms (AHs) and the swarm intelligence of RF to significantly reduce the computational complexity compared with the deep learning-based method. Both numerical simulation and experiments are conducted. The simulation results of polarization multiplexed (PM) 4/8/16/32/64 quadrature amplitude modulation (QAM) wavelength division multiplexing (WDM) systems demonstrate its feasibility and identification performance. In the presence of nonlinear effects, with lower complexity than three other machine learning algorithms (k-nearest neighbors, support vector machine, and deep neural networks), the RF-based MFI can obtain 100% accuracy at the OSNR values greater than or equal to the respective soft decision forward error correction (SD-FEC) threshold. The identification accuracy versus total launch power is experimentally investigated in PM-4/16/32QAM WDM coherent systems. In the case of obvious nonlinear impairments, 100% accuracy can also be achieved above the OSNR corresponding to the SD-FEC threshold. The superiority of the proposed MFI method makes it highly desirable for applications in modulation format-adaptive FCRs.

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

[2]  Chao Lu,et al.  An Optical Communication's Perspective on Machine Learning and Its Applications , 2019, Journal of Lightwave Technology.

[3]  Yuefeng Ji,et al.  Towards converged, collaborative and co-automatic (3C) optical networks , 2018, Science China Information Sciences.

[4]  Min Zhang,et al.  Intelligent constellation diagram analyzer using convolutional neural network-based deep learning. , 2017, Optics express.

[5]  Ming Tang,et al.  Blind and Fast Modulation Format Identification by Frequency-offset Loading for Hitless Flexible Transceiver , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[6]  Xue Chen,et al.  Modulation Format Recognition and OSNR Estimation Using CNN-Based Deep Learning , 2017, IEEE Photonics Technology Letters.

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

[8]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[9]  Yuefeng Ji,et al.  Linewidth-tolerant and multi-format carrier phase estimation schemes for coherent optical m-QAM flexible transmission systems. , 2018, Optics express.

[10]  Changyuan Yu,et al.  Joint OSNR monitoring and modulation format identification in digital coherent receivers using deep neural networks. , 2017, Optics express.

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

[12]  Stephen R. Marsland,et al.  Machine Learning - An Algorithmic Perspective , 2009, Chapman and Hall / CRC machine learning and pattern recognition series.

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

[14]  Tianwai Bo,et al.  Robust and Blind Modulation Format Identification for Elastic Optical Networks , 2018, 2018 European Conference on Optical Communication (ECOC).

[15]  Ming Tang,et al.  Modulation format identification assisted by sparse-fast-Fourier-transform for hitless flexible coherent transceivers. , 2019, Optics express.