Abstract

To enable the high quality-of-service of reliable and dynamic optical networks, it is essential to implement optical performance monitoring (OPM) for fiber optical transmission link. Being directly related to the quality of optical signal, optical signal-to-noise ratio (OSNR) and chromatic dispersion (CD) have become the most vital parameters to be monitored during OPM implementation. However, most existing simultaneous OSNR and CD monitoring schemes still suffer from high implementation complexity and low accuracy. Here, we demonstrate a joint OSNR and CD monitoring scheme for the digital coherent receiver, enabled by the long short-term memory neural network (LSTM-NN). LSTM-NN is able to identify the mapping from the received data to corresponding OSNR and CD values simultaneously, without manual feature pre-engineering. We carry out an experimental verification for optical signals with variable modulation formats and baud-rates. The mean absolute errors (MAEs) of simultaneous OSNR and CD monitoring are below 0.12 dB and 1.09 ps/nm, respectively, when both OSNR and CD are at the range from 15 to 30 dB and 1360 to 2040 ps/nm for 5/10 Gbaud PDM-16QAM/64QAM optical signals.

© 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Full Article  |  PDF Article
OSA Recommended Articles
Joint OSNR monitoring and modulation format identification in digital coherent receivers using deep neural networks

Faisal Nadeem Khan, Kangping Zhong, Xian Zhou, Waled Hussein Al-Arashi, Changyuan Yu, Chao Lu, and Alan Pak Tao Lau
Opt. Express 25(15) 17767-17776 (2017)

Multi-task deep neural network (MT-DNN) enabled optical performance monitoring from directly detected PDM-QAM signals

Yijun Cheng, Songnian Fu, Ming Tang, and Deming Liu
Opt. Express 27(13) 19062-19074 (2019)

Modulation format identification and OSNR monitoring using density distributions in Stokes axes for digital coherent receivers

Anlin Yi, Lianshan Yan, Hengjiang Liu, Lin Jiang, Yan Pan, Bin Luo, and Wei Pan
Opt. Express 27(4) 4471-4479 (2019)

References

  • View by:
  • |
  • |
  • |

  1. E. Yoshida, “Large-capacity, long-haul optical transport network based on 100 Gb/s/ch no-guard-interval coherent optical OFDM technology,” in Conference on Lasers and Electro-Optics/Pacific Rim 2009, (Optical Society of America, 2009), paper ThH1_1.
    [Crossref]
  2. G. Liga, T. Xu, A. Alvarado, R. I. Killey, and P. Bayvel, “On the performance of multichannel digital backpropagation in high-capacity long-haul optical transmission,” Opt. Express 22(24), 30053–30062 (2014).
    [Crossref] [PubMed]
  3. J. D. Downie, J. Hurley, D. Pikula, and X. Zhu, “Ultra-long-haul 112 Gb/s PM-QPSK transmission systems using longer spans and Raman amplification,” Opt. Express 20(9), 10353–10358 (2012).
    [Crossref] [PubMed]
  4. J. D. Downie, J. Hurley, and D. Pikula, “Transmission of 256 Gb/s PM-16QAM and 128 Gb/s PM-QPSK signals over long-haul and submarine systems with span lengths greater than 100 km,” in European Conference and Exhibition on Optical Communication (ECOC, 2013), paper Tu.1.D.3.
    [Crossref]
  5. F. N. Khan, C. Lu, and A. P. T. Lau, “Optical Performance Monitoring in Fiber-Optic Networks Enabled by Machine Learning Techniques,” in Optical Fiber Communication Conference, OSA Technical Digest (Optical Society of America, 2018), paper M2F.3.
    [Crossref]
  6. L. Baker-Meflah, B. Thomsen, J. Mitchell, and P. Bayvel, “Simultaneous chromatic dispersion, polarization-mode-dispersion and OSNR monitoring at 40Gbit/s,” Opt. Express 16(20), 15999–16004 (2008).
    [Crossref] [PubMed]
  7. F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
    [Crossref]
  8. X. Wu, J. A. Jargon, R. A. Skoog, L. Paraschis, and A. E. Willner, “Applications of Artificial Neural Networks in Optical Performance Monitoring,” J. Lightwave Technol. 27(16), 3580–3589 (2009).
    [Crossref]
  9. X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
    [Crossref]
  10. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput. 9(8), 1735–1780 (1997).
    [Crossref] [PubMed]
  11. M. Sundermeyer, H. Ney, and R. Schlüter, “From Feedforward to Recurrent LSTM Neural Networks for Language Modeling,” IEEE T. Audio Speech 23(3), 517–529 (2015).
  12. A. Alahi, K. Goel, V. Ramanathan, A. Robicquet, F. Li, and S. Savarese, “Social LSTM: Human Trajectory Prediction in Crowded Spaces,” in Computer Vision and Pattern Recognition (IEEE, 2016), pp. 961–971.
  13. W. Mo, C. L. Gutterman, Y. Li, G. Zussman, and D. C. Kilper, “Deep Neural Network Based Dynamic Resource Reallocation of BBU Pools in 5G C-RAN ROADM Networks,” in Optical Fiber Communication Conference, OSA Technical Digest (Optical Society of America, 2018) pp. Th1B-4.
    [Crossref]
  14. Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Trans. Neural Netw. 5(2), 157–166 (1994).
    [Crossref] [PubMed]
  15. M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, and M. Kudlur, “Tensorflow: A system for large-scale machine learning,” in Proceedings of Operating Systems Design and Implementation (USENIX, 2016), pp 265–283.
  16. C. J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Clim. Res. 30(1), 79–82 (2005).
    [Crossref]
  17. B. Li, Y. Liu, and X. Wang, “Gradient Harmonized Single-stage Detector,” presented at AAAI Conference on Artificial Intelligence (AAAI 2019) Hawaii, USA, 27 Jan. –15 Feb. 2019.
  18. E. Kauder, History of Marginal Utility Theory (Princeton University, 2015).

2018 (1)

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

2015 (1)

M. Sundermeyer, H. Ney, and R. Schlüter, “From Feedforward to Recurrent LSTM Neural Networks for Language Modeling,” IEEE T. Audio Speech 23(3), 517–529 (2015).

2014 (1)

2012 (2)

J. D. Downie, J. Hurley, D. Pikula, and X. Zhu, “Ultra-long-haul 112 Gb/s PM-QPSK transmission systems using longer spans and Raman amplification,” Opt. Express 20(9), 10353–10358 (2012).
[Crossref] [PubMed]

F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
[Crossref]

2009 (1)

2008 (1)

2005 (1)

C. J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Clim. Res. 30(1), 79–82 (2005).
[Crossref]

1997 (1)

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput. 9(8), 1735–1780 (1997).
[Crossref] [PubMed]

1994 (1)

Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Trans. Neural Netw. 5(2), 157–166 (1994).
[Crossref] [PubMed]

Alvarado, A.

Baker-Meflah, L.

Bayvel, P.

Bengio, Y.

Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Trans. Neural Netw. 5(2), 157–166 (1994).
[Crossref] [PubMed]

Chen, W.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Downie, J. D.

Fan, X.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Frasconi, P.

Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Trans. Neural Netw. 5(2), 157–166 (1994).
[Crossref] [PubMed]

Hochreiter, S.

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput. 9(8), 1735–1780 (1997).
[Crossref] [PubMed]

Huang, X.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Hurley, J.

Jargon, J. A.

Khan, F. N.

F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
[Crossref]

Killey, R. I.

Lau, A. P. T.

F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
[Crossref]

Liga, G.

Lu, C.

F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
[Crossref]

Matsuura, K.

C. J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Clim. Res. 30(1), 79–82 (2005).
[Crossref]

Mitchell, J.

Ney, H.

M. Sundermeyer, H. Ney, and R. Schlüter, “From Feedforward to Recurrent LSTM Neural Networks for Language Modeling,” IEEE T. Audio Speech 23(3), 517–529 (2015).

Paraschis, L.

Pikula, D.

Ren, F.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Schlüter, R.

M. Sundermeyer, H. Ney, and R. Schlüter, “From Feedforward to Recurrent LSTM Neural Networks for Language Modeling,” IEEE T. Audio Speech 23(3), 517–529 (2015).

Schmidhuber, J.

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput. 9(8), 1735–1780 (1997).
[Crossref] [PubMed]

Shen, T. S. R.

F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
[Crossref]

Simard, P.

Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Trans. Neural Netw. 5(2), 157–166 (1994).
[Crossref] [PubMed]

Skoog, R. A.

Sundermeyer, M.

M. Sundermeyer, H. Ney, and R. Schlüter, “From Feedforward to Recurrent LSTM Neural Networks for Language Modeling,” IEEE T. Audio Speech 23(3), 517–529 (2015).

Thomsen, B.

Wang, J.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Willmott, C. J.

C. J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Clim. Res. 30(1), 79–82 (2005).
[Crossref]

Willner, A. E.

Wu, X.

Xie, Y.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Xu, T.

Zhang, Y.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Zhangsun, T.

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

Zhou, Y.

F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
[Crossref]

Zhu, X.

Clim. Res. (1)

C. J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Clim. Res. 30(1), 79–82 (2005).
[Crossref]

IEEE Photonics J. (1)

X. Fan, Y. Xie, F. Ren, Y. Zhang, X. Huang, W. Chen, T. Zhangsun, and J. Wang, “Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning,” IEEE Photonics J. 10(5), 1–12 (2018).
[Crossref]

IEEE Photonics Technol. Lett. (1)

F. N. Khan, T. S. R. Shen, Y. Zhou, A. P. T. Lau, and C. Lu, “Optical Performance Monitoring Using Artificial Neural Networks Trained With Empirical Moments of Asynchronously Sampled Signal Amplitudes,” IEEE Photonics Technol. Lett. 24(12), 982–984 (2012).
[Crossref]

IEEE T. Audio Speech (1)

M. Sundermeyer, H. Ney, and R. Schlüter, “From Feedforward to Recurrent LSTM Neural Networks for Language Modeling,” IEEE T. Audio Speech 23(3), 517–529 (2015).

IEEE Trans. Neural Netw. (1)

Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Trans. Neural Netw. 5(2), 157–166 (1994).
[Crossref] [PubMed]

J. Lightwave Technol. (1)

Neural Comput. (1)

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput. 9(8), 1735–1780 (1997).
[Crossref] [PubMed]

Opt. Express (3)

Other (8)

J. D. Downie, J. Hurley, and D. Pikula, “Transmission of 256 Gb/s PM-16QAM and 128 Gb/s PM-QPSK signals over long-haul and submarine systems with span lengths greater than 100 km,” in European Conference and Exhibition on Optical Communication (ECOC, 2013), paper Tu.1.D.3.
[Crossref]

F. N. Khan, C. Lu, and A. P. T. Lau, “Optical Performance Monitoring in Fiber-Optic Networks Enabled by Machine Learning Techniques,” in Optical Fiber Communication Conference, OSA Technical Digest (Optical Society of America, 2018), paper M2F.3.
[Crossref]

E. Yoshida, “Large-capacity, long-haul optical transport network based on 100 Gb/s/ch no-guard-interval coherent optical OFDM technology,” in Conference on Lasers and Electro-Optics/Pacific Rim 2009, (Optical Society of America, 2009), paper ThH1_1.
[Crossref]

A. Alahi, K. Goel, V. Ramanathan, A. Robicquet, F. Li, and S. Savarese, “Social LSTM: Human Trajectory Prediction in Crowded Spaces,” in Computer Vision and Pattern Recognition (IEEE, 2016), pp. 961–971.

W. Mo, C. L. Gutterman, Y. Li, G. Zussman, and D. C. Kilper, “Deep Neural Network Based Dynamic Resource Reallocation of BBU Pools in 5G C-RAN ROADM Networks,” in Optical Fiber Communication Conference, OSA Technical Digest (Optical Society of America, 2018) pp. Th1B-4.
[Crossref]

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, and M. Kudlur, “Tensorflow: A system for large-scale machine learning,” in Proceedings of Operating Systems Design and Implementation (USENIX, 2016), pp 265–283.

B. Li, Y. Liu, and X. Wang, “Gradient Harmonized Single-stage Detector,” presented at AAAI Conference on Artificial Intelligence (AAAI 2019) Hawaii, USA, 27 Jan. –15 Feb. 2019.

E. Kauder, History of Marginal Utility Theory (Princeton University, 2015).

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (6)

Fig. 1
Fig. 1 Schematic of LSTM cell. The circles are arithmetic operators and the rectangles are the neural network layers with tanh and σ (sigmoid) activation functions in the LSTM cell.
Fig. 2
Fig. 2 Schematic of the LSTM-NN enabled joint OSNR and CD monitoring. ts: time step; XIt, XQt, YIt, YQt, OSNRt, and CDt: XI, XQ, YI, YQ, OSNR, and CD at the time step t.
Fig. 3
Fig. 3 System setup of joint CD and OSNR monitoring within the digital coherent receiver: PBS: polarization beam splitter; VOA: variable optical attenuator.
Fig. 4
Fig. 4 MAE of joint OSNR and CD monitoring with respect to the number of time step. The color bar is the number of time step.
Fig. 5
Fig. 5 Simulation results: (a) true OSNR versus the OSNR deviation, (b) true CD versus the CD deviation, (c) MAE of OSNR monitoring with respect to the CD value, (d) MAE of CD monitoring with respect to the OSNR value for 28 Gbaud PDM-16QAM/64QAM, 35 Gbaud PDM-16QAM/64QAM signal, respectively.
Fig. 6
Fig. 6 Experimental results: (a) true OSNR versus the OSNR deviation, (b) true CD versus the CD deviation, (c) MAE of OSNR monitoring with respect to the CD value, (d) MAE of CD monitoring with respect to the OSNR value for 5 Gbaud PDM-16QAM/64QAM, 10 Gbaud PDM-16QAM/64QAM signal, respectively.

Tables (2)

Tables Icon

Table 1 MAEs of the proposed simultaneous OSNR and CD monitoring technique in the simulations

Tables Icon

Table 2 MAEs of the proposed simultaneous OSNR and CD monitoring in the proof-of-concept experiments

Equations (7)

Equations on this page are rendered with MathJax. Learn more.

f t = σ g ( W x f x t + W h f h t 1 + b f )
i t = σ g ( W x i x t + W h i h t 1 + b i )
o t = σ g ( W x o x t + W h o h t 1 + b o )
C t ~ = tan h ( W x C x t + W h C h t 1 + b C )
C t = f t C t 1 + i t C t ~
h t = o t tan h ( C t )
L oss = 1 2 n ( i = 1 n M O S N R i T O S N R i 2 + i = 1 n M C D i T C D i 2 )

Metrics