Photonics Research, Volume. 9, Issue 1, B1(2021)

Modulation format identification in fiber communications using single dynamical node-based photonic reservoir computing

Qiang Cai1、†, Ya Guo1,2、†, Pu Li1,3,4、*, Adonis Bogris5, K. Alan Shore6, Yamei Zhang7, and Yuncai Wang3
Author Affiliations
  • 1Key Laboratory of Advanced Transducers and Intelligent Control System, Ministry of Education, Taiyuan University of Technology, Taiyuan 030024, China
  • 2School of Electronics and Information, Northwestern Polytechnical University, Xi'an 710072, China
  • 3School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
  • 4Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University, Shanghai 200444, China
  • 5Department of Informatics and Computer Engineering, University of West Attica, Athens 12243, Greece
  • 6School of Electronic Engineering, Bangor University, Wales LL57 1UT, UK
  • 7Key Laboratory of Radar Imaging and Microwave Photonics, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
  • show less
    Figures & Tables(11)
    Schematic of the MFI based on the P-RC with semiconductor lasers. This system consists of three parts: input layer, reservoir, and output layer. The input u(n) is multiplied by a mask with a period of T, and then the resulting stream S(t)=Mask×u(n) is fed into the reservoir through a modulator. The reservoir is a master-slave configuration constructed by a response laser (R-Laser) with a self-delay feedback loop injected by a drive laser (D-Laser). Note that there are N virtual nodes at each interval θ in the feedback loop with a delay time of T. The transient states of the R-Laser Xi are read out for training the connection weights Wi between the reservoir and the output layer. The final output nodes are weighted by the sums of the transient states ∑XiWi.
    Sketch of the emulated transmission system for asynchronous amplitude histogram generation. EDFA, erbium-doped fiber amplifier; SMF, single-mode fiber; CD/PMD, chromatic dispersion/polarization mode dispersion; BPF, band-pass filter; PD, photodetector; AAH, asynchronous amplitude histogram.
    Typical asynchronous amplitude histograms for (a1)–(a3) OOK, (b1)–(b3) DQPSK, and (c1)–(c3) QAM formats after propagation through the emulated communication channel. From left to right, each column has an OSNR of 12, 19, and 26 dB, while the corresponding CD and the DGD are fixed at 80 ps/nm and 5 ps, respectively.
    (a) Identification error rate on the total (training and test) sample numbers of the binary mask (black), the six-level mask (blue), and the chaos mask signals (red). (b) Dependence of the identification error rate on the total (training and test) sample numbers at different virtual node sizes of 300 (blue) and 400 (red).
    (a) Bifurcation diagram of the output optical intensity versus the injection strength kinj for kf=0.18, IR=1.3Ith, and Δν=−10 GHz. (b) Identification error rate (ER) at different injection strengths kinj (blue dots), while the red curve is plotted by executing a sliding window averaging to the associated data points.
    (a) Bifurcation diagram of the output optical intensity versus the feedback strength kf for kinj=0.2, IR=1.3Ith, and Δν=−10 GHz. (b) Identification ER at different feedback strengths kf (blue dots), while the red curve is plotted by executing a sliding window averaging to the associated data points.
    (a) Bifurcation diagram of the output optical intensity versus the bias current of the R-Laser IR for kinj=0.2, kf=0.15, and Δν=−10 GHz. (b) Identification ER at different bias currents of the R-Laser IR (blue dots), while the red curve is plotted by executing a sliding window averaging to the associated data points.
    (a) Bifurcation diagram of the output optical intensity versus the frequency detuning Δν between the D-Laser and the R-Laser for kinj=0.2, kf=0.15, and IR=1.25Ith. (b) Identification ER at different frequency detunings Δν (blue dots), while the red curve is plotted by executing a sliding window averaging to the associated data points.
    • Table 1. Identification Accuracies for Different Modulation Formats Using the MFI Technique Through Our Laser-Based P-RC Systema

      View table
      View in Article

      Table 1. Identification Accuracies for Different Modulation Formats Using the MFI Technique Through Our Laser-Based P-RC Systema

        Identified Modulation Formats
        OOKDQPSKQAM
      Actual Modulation FormatsOOK95.1%1.4%1.7%
      DQPSK3.2%95.7%2.8%
      QAM1.7%2.9%95.5%
    • Table 2. Identification Accuracies for Different Modulation Formats Using Only the Ridge Regression Algorithm (Without the Reservoir Layer in the System)a

      View table
      View in Article

      Table 2. Identification Accuracies for Different Modulation Formats Using Only the Ridge Regression Algorithm (Without the Reservoir Layer in the System)a

        Identified Modulation Formats
        OOKDQPSKQAM
      Actual Modulation FormatsOOK75.2%8.2%8.5%
      DQPSK15.7%72.6%16.7%
      QAM9.1%19.2%74.8%
    • Table 3. Identification Accuracies for Different Modulation Formats Using the MFI Technique Through the P-RC System with a Typical Noise Value of β=1.5×106a

      View table
      View in Article

      Table 3. Identification Accuracies for Different Modulation Formats Using the MFI Technique Through the P-RC System with a Typical Noise Value of β=1.5×106a

        Identified Modulation Formats
        OOKDQPSKQAM
      Actual Modulation FormatsOOK95.0%1.2%1.8%
      DQPSK3.5%95.5%2.9%
      QAM1.5%3.3%95.3%
    Tools

    Get Citation

    Copy Citation Text

    Qiang Cai, Ya Guo, Pu Li, Adonis Bogris, K. Alan Shore, Yamei Zhang, Yuncai Wang. Modulation format identification in fiber communications using single dynamical node-based photonic reservoir computing[J]. Photonics Research, 2021, 9(1): B1

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Special Issue: DEEP LEARNING IN PHOTONICS

    Received: Sep. 9, 2020

    Accepted: Nov. 13, 2020

    Published Online: Dec. 25, 2020

    The Author Email: Pu Li (lipu8603@126.com)

    DOI:10.1364/PRJ.409114

    Topics