Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free A novel support vector machine robust model based electrical equaliser for coherent optical orthogonal frequency division multiplexing systems

  • Author(s): Sofien Mhatli 1 ; Hichem Mrabet 1, 2 ; Iyad Dayoub 3 ; Elias Giacoumidis 4
    • View affiliations
    • Affiliations: 1: Tunisia Polytechnic School, SERCOM-Lab, Carthage University, La Marsa, Tunis, Tunisia ;
      2: College of Computation and Informatics, IT Department, Saudi Electronic University, Medina Mounawara Branch, Saudi Arabia ;
      3: Université Lille Nord de France, IEMN-DOAE (CNRS UMR 8520), UVHC 59313 Valenciennes, France ;
      4: Centre for Ultrahigh bandwidth Devices for Optical Systems (CUDOS) and Institute of Photonics and Optical Science (IPOS), School of Physics, University of Sydney, NSW 2006, Sydney, Australia
  • Source: Volume 11, Issue 7, 11 May 2017, p. 1091 – 1096
    DOI:  10.1049/iet-com.2016.1115 , Print ISSN 1751-8628, Online ISSN 1751-8636
© The Institution of Engineering and Technology
Received 18/09/2016, Accepted 18/01/2017, Revised 29/12/2016, Published 23/01/2017

Classifiers, such as artificial neural networks non-linear equaliser (ANN-NLE), Wiener–Hammerstein non-linear equaliser, Volterra non-linear equaliser (Volterra-NLE) and support vector machine non-linear equaliser (SVM-NLE), can play a significant role in compensating non-linear imperfections in the optical communications context. Using classifiers to mitigate the non-linear effects in coherent optical orthogonal frequency division multiplexing (CO-OFDM) systems is an interesting idea to be investigated. In this study, a novel support vector machine robust version, specifically adapted to a 100 Gb/s CO-OFDM data structure for long haul distance, is proposed. Firstly, the authors demonstrate that SVM-NLE upgrades the system performance by about 10−1 in terms of bit-error rate compared to Volterra-NLE at optical signal-to-noise ratio equal to 14 dB. Then, they show that it can double the transmission distance up to 1600 km over single mode fibre channel. Furthermore, a performance comparison is performed using 16 quadrature amplitude modulation and 40 Gb/s bit rate for SVM-NLE, ANN-NLE and inverse Volterra series transfer function non-linear equaliser, respectively.

Inspec keywords: support vector machines; error statistics; OFDM modulation; optical communication; telecommunication computing; neural nets; equalisers

Other keywords: optical communications; CO-OFDM data structure; Volterra series transfer function nonlinear equaliser; single mode fibre channel; nonlinear effects; support vector machine robust model; SVM-NLE; Volterra-NLE; support vector machine nonlinear equaliser; electrical equaliser; optical signal-to-noise ratio; Wiener–Hammerstein non-linear equaliser; coherent optical orthogonal frequency division multiplexing systems; artificial neural networks non-linear equaliser; Volterra nonlinear equaliser; bit-error rate; quadrature amplitude modulation

Subjects: Optical communication; Modulation and coding methods; Other topics in statistics; Other topics in statistics; Communications computing; Knowledge engineering techniques; Neural computing techniques; Communication channel equalisation and identification

References

    1. 1)
      • 24. Agrawal, G.P.: ‘Fiber-optic communication systems’ (Wiley, 2012, 4th edn.).
    2. 2)
      • 2. Shieh, W., Djordjevic, I.: ‘OFDM for optical communications’ (Elsevier, Academic Press, 2010).
    3. 3)
      • 29. Giacoumidis, E., Mhatli, S., Le, S.T., et al: ‘Nonlinearities blind equalization for 16-QAM coherent optical OFDM using support vector machines’. ECOC 2016, Dusseldorf, September 2016.
    4. 4)
      • 3. Kaminov, I., Li, T., Willner, A.: ‘Optical fiber telecommunications, volume VIB: systems and network’ (Academic Press, 2013, 6th edn.).
    5. 5)
      • 22. Tawade, L., Pinjarkar, U., Awade, K., et al: ‘An optical OFDM modem with adaptive Volterra equalizer’, J. Opt. Commun., 2015, 30, (1), pp. 7–16.
    6. 6)
      • 4. Shieh, W., Bao, H., Tang, Y.: ‘Coherent optical OFDM: theory and design’, Opt. Express, 2008, 16, (2), pp. 841–859.
    7. 7)
      • 8. Sebald, D.J., Bucklew, J.A.: ‘Support vector machine techniques for nonlinear equalization’, IEEE Trans. Signal Process., 2000, 48, (11), pp. 3217–3226.
    8. 8)
      • 21. Pavel, T., Senderáková, D., Páta, P., et al: ‘Analysis of wiener Hammerstein equalizer for optical OFDM modem’. Proc. of Photonics Devices and Systems Conf., Prague, 2015.
    9. 9)
      • 9. Shulkind, G., Azarathy, M.: ‘Nonlinear digital back propagation compensator for coherent optical OFDM based on factorizing the Volterra series transfer function’, Opt. Express, 2013, 21, (11), pp. 13145–13161.
    10. 10)
      • 13. Jarajreh, M.A., Giacoumidis, E., Aldaya, I., et al: ‘Artificial neural network nonlinear equalizer for coherent optical OFDM’, IEEE PTL, 2014, 27, (4).
    11. 11)
      • 11. Benedetto, S., Biglieri, E., Astellani, V.: ‘Digital transmission theory’ (Prentice-Hall, Englewood Cliffs, NJ, 1987).
    12. 12)
      • 18. Pan, J., Cheng, C.: ‘Nonlinear electrical compensation for the coherent optical OFDM system’, J. Lightwave Technol., 2011, 29, (2), pp. 215–221.
    13. 13)
      • 25. Recommendation ITU-T G.652, Characteristics of a single-mode optical fibre and cable, 2009.
    14. 14)
      • 10. Nowakand, R.D., VanVeen, B.D.: ‘Tensor product basis approximations for Volterra filters’, IEEE Trans. Signal Process., 1996, 44, pp. 36–50.
    15. 15)
      • 1. Mhatli, S., Ghanbarisabagh, M., Tawade, L., et al: ‘Long-reach OFDM WDM–PON delivering 100 Gb/s of data downstream and 2 Gb/s of data upstream using a continuous-wave laser and a reflective semiconductor optical amplifier’, Opt. Lett., 2014, 39, (23), pp. 6711–6714.
    16. 16)
      • 12. Jarajreh, M.A., Rajbhandari, S., Gacoumidis, E., et al: ‘Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals’. CSNDSP, UK, 2014.
    17. 17)
      • 26. Nguyen, T., Mhatli, S., Giacoumidis, E., et al: ‘Fiber nonlinearity equalizer based on support vector classification for coherent optical OFDM’, IEEE Photon. J., 2016, 8, (2)..
    18. 18)
      • 15. Chen, S., Gibson, G.J., N Cowan, C.F., Grant, P.M., ‘Adaptive equalization of finite non-linear channels using multilayer perceptrons’, Signal Processing, Volume 20, Elsevier Science Publishers B.V., pp. 107–119. 1990..
    19. 19)
      • 23. Kharbech, S., Dayoub, I., wingelstein-Colin, M.Z., et al: ‘On classifiers for blind feature-based automatic modulation classification over multiple-input–multiple-output channels’, IET Commun., 2016, 10, (7), pp. 790–795.
    20. 20)
      • 17. Mousa-Pasandi, M.E., Plant, D.V.: ‘Zero-overhead phase noise compensation via decision-direct phase equalizer for coherent optical OFDM’, Opt. Express, 2010, 18, (20), pp. 20651–20660.
    21. 21)
      • 14. Jarajreh, M.A.: ‘Coherent optical OFDM modem employing artificial neural networks for dispersion and nonlinearity compensation in a long-haul transmission system’ (Northumbria University, 2012).
    22. 22)
      • 28. Jarajreh, M., Giacoumidis, E., Aldaya, I., et al: ‘Artificial neural network nonlinear equalizer for coherent optical OFDM’, IEEE Photon. Technol. Lett., 2015, 27, (4), pp. 387–390.
    23. 23)
      • 19. Pan, J., Cheng, C.: ‘Wiener–Hammerstein model based electrical equalizer for optical communication systems’, J. Lightwave Technol., 2011, 29, (16), pp. 2454–2459.
    24. 24)
      • 16. Li, X., Zhong, W.-D., Alphones, A., et al: ‘Channel equalization in optical OFDM systems using independent component analysis’, J. Lightwave Technol., 2014, 32, (18), pp. 3206–3214.
    25. 25)
      • 6. Zhao, C., Chen, Y., Zhang, S., et al: ‘Experimental demonstration of 1.08 Tb/s PDM CO-SCFDM transmission over 3170 km SSMF’, Opt. Express, 2012, 20, (2), pp. 787–793.
    26. 26)
      • 5. Du, L.B., Lowery, A.J.: ‘Improved single channel backpropagation for intra-channel fiber nonlinearity compensation in long-haul optical communication systems’, Opt. Express, 2010, 18, (16), pp. 17075–17088.
    27. 27)
      • 7. Uncini, A., Vecci, L., Campolucci, P., et al: ‘Complex-valued neural networks with adaptive spline activation function for digital radio links nonlinear equalization’’, IEEE Trans. Signal Process., 1999, 47, (2), pp. 505–514.
    28. 28)
      • 27. Giacoumidis, E., Aldaya, I., Jarajreh, M.A., et al: ‘Volterra-based reconfigurable nonlinear equalizer for coherent OFDM’, IEEE Photon. Technol. Lett., 2014, 26, (14), pp. 1383–1386.
    29. 29)
      • 20. Abdulkader, H., Benammar, B., Poulliat, C., et al: ‘Neural networks-based turbo equalization of a satellite communication channel’. Proc. of IEEE 15th Int. Workshop on Signal Processing Advances in Wireless Communications, 2014.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-com.2016.1115
Loading

Related content

content/journals/10.1049/iet-com.2016.1115
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address