access icon free Modelling and comparison for low-voltage broadband power line noise using LS-SVM and wavelet neural networks

© The Institution of Engineering and Technology
Received 27/04/2018, Accepted 08/10/2018, Revised 10/09/2018, Published 10/10/2018

This study is to construct the autoregressive models for the low-voltage broadband power line communication (PLC) channel noise by two machine learning algorithms, namely the least square support vector machine (LS-SVM) and wavelet neural networks. The main work is to compare the two classical machine learning algorithms and also compare them with the traditional Markovian–Gaussian method. To verify their availability and ability to adapt to the time-variant PLC channels, noise measurements for low-voltage PLC channels in indoor and outdoor scenarios are carried out. The accuracy and efficiency of the two models are studied and compared based on a large amount of measurement data. The results show that both of the noise models can simulate and adapt to the time-variant low-voltage broadband PLC channels very well. The LS-SVM model is found to have shorter simulation time and higher accuracy. Moreover, the proposed noise models are also compared with the traditional Markovian–Gaussian model. The results show that both the proposed noise models exhibit higher accuracy and lower complexity, especially that the LS-SVM is more appropriate to be applied as a noise generator in PLC link and network level simulations instead of the current Markovian–Gaussian model.

Inspec keywords: autoregressive processes; wavelet neural nets; support vector machines; time-varying channels; telecommunication channels; carrier transmission on power lines; learning (artificial intelligence); telecommunication computing; least squares approximations

Other keywords: classical machine learning algorithms; Markovian–Gaussian model; noise models; time-variant low-voltage broadband PLC channels; noise generator; wavelet neural networks; autoregressive models; measurement data; shorter simulation time; least square support vector machine; low-voltage broadband power line communication channel noise; low-voltage PLC channels; LS-SVM model; network level simulations; time-variant PLC channels; noise measurements

Subjects: Other topics in statistics; Other topics in statistics; Communications computing; Neural computing techniques; Power line systems; Knowledge engineering techniques; Interpolation and function approximation (numerical analysis); Interpolation and function approximation (numerical analysis)

References

    1. 1)
      • 13. Gotz, M., Rapp, M., Dostert, K.: ‘Power line channel characteristics and their effect on communication system design’, IEEE Commun. Mag., 2004, 42, (4), pp. 78–86.
    2. 2)
      • 3. Gassara, H., Rouissi, F., Ghazel, A.: ‘Statistical characterization of the indoor low-voltage narrowband power line communication channel’, IEEE Trans. Electromagn. Compat., 2014, 56, (1), pp. 123–131.
    3. 3)
      • 20. Lu, X., Zou, W., Huang, M.: ‘Robust spatiotemporal LS-SVM modeling for nonlinear distributed parameter system with disturbance’, IEEE Trans. Ind. Electron., 2017, 64, (10), pp. 8003–8012.
    4. 4)
      • 15. Lu, X, Fan, B, Huang, M.: ‘A novel LS-SVM modeling method for a hydraulic press forging process with multiple localized solutions’, IEEE Trans. Ind. Inf., 2015, 11, (3), pp. 663–670.
    5. 5)
      • 4. Zimmermann, M., Dostert, K.: ‘Analysis and modeling of impulse noise in broadband powerline communications’, IEEE Trans. Electromagn. Compat., 2002, 44, (1), pp. 249–258.
    6. 6)
      • 2. Liu, S., Greenstein, L.J.: ‘Interference evaluation of overhead medium-voltage broadband power line systems’, IEEE Trans. Electromagn. Compat., 2010, 52, (4), pp. 866–877.
    7. 7)
      • 23. Zhang, Q.: ‘Using wavelet network in nonparametric estimation’, IEEE Trans. Neural Netw., 1997, 8, (2), pp. 227–236.
    8. 8)
      • 19. Zhao, Z., Yao, C., Zhao, X., et al: ‘Impact of capacitive coupling circuit on online impulse frequency response of a power transformer’, IEEE Trans. Dielectr. Electr. Insul., 2016, 23, (3), pp. 1285–1293.
    9. 9)
      • 7. Laguna-Sanchez, G., Lopez-Guerrero, M.: ‘On the use of alpha-stable distributions in noise modeling for PLC’, IEEE Trans. Power Deliv., 2015, 30, (4), pp. 1863–1870.
    10. 10)
      • 21. Suykens, J.A.K., Brabanter, J., Lukas, L.: ‘Weighted least squares support vector machines: robustness and sparse approximation’, Neuro Comput., 2002, 48, (1), pp. 85–105.
    11. 11)
      • 18. Brison, M., Bensetti, M., Lacerda, R.D., et al: ‘Optimised PLC power transfer on avionic DC power lines: coupling circuit and lightning protection’. IEEE Int. Symp. on Power Line Communications and ITS Applications, Madrid, Spain, April 2017, pp. 1–6.
    12. 12)
      • 17. Sun, W., Lu, W., Li, Q., et al: ‘WNN-LQE: wavelet-neural-network-based link quality estimation for smart grid WSNs’, IEEE. Access., 2017, 5, pp. 12788–12797.
    13. 13)
      • 8. Tlich, M., Chaouche, H., Zeddam, A., et al: ‘Novel approach for PLC impulsive noise modelling’. IEEE Int. Symp. on Power Line Communications and ITS Applications, Dresden, Germany, March–April 2009, pp. 20–25.
    14. 14)
      • 1. Galli, S., Scaglione, A., Wang, Z.: ‘For the grid and through the grid: the role of power line communications in the smart grid’, Proc. IEEE, 2011, 99, (6), pp. 998–1027.
    15. 15)
      • 11. Katayama, M., Yamazato, T., Okada, H.: ‘A mathematical model of noise in narrowband power line communication systems’, IEEE J. Sel. Areas Commun., 2006, 24, (7), pp. 1267–1276.
    16. 16)
      • 10. Dubey, A., Mallik, R.K., Schober, R.: ‘Performance analysis of a power line communication system employing selection combining in correlated log-normal channels and impulsive noise’, IET Commun., 2014, 8, (7), pp. 1072–1082.
    17. 17)
      • 9. Gianaroli, F., Pancaldi, F., Sironi, E., et al: ‘Statistical modeling of periodic impulsive noise in indoor power-line channels’, IEEE Trans. Power Deliv., 2012, 27, (3), pp. 1276–1283.
    18. 18)
      • 14. Suykens, J.A.K., Vandewalle, J.: ‘Least squares support vector machine classifiers’, Neural Process. Lett., 1999, 9, (3), pp. 293–300.
    19. 19)
      • 6. Bert, L.D., Caldera, P., Schwingshackl, D., et al: ‘On noise modeling for power line communications’. IEEE Int. Symp. on Power Line Communications and ITS Applications, Udine, Italy, 2011, pp. 283–288.
    20. 20)
      • 16. Chen, E., Tao, R., Zhao, X.: ‘Channel equalization for OFDM system based on the BP neural network’. 2006 8th Int. Conf. on Signal Processing, Beijing, China, November 2006, vol. 3, pp. 16–20.
    21. 21)
      • 24. Eltholth, A.A.: ‘Spectrum prediction in cognitive radio systems using a wavelet neural network’. IEEE Int. Conf. on Software, Telecommunications and Computer Networks, Split, Croatia, 22–24 September 2016, pp. 1–6.
    22. 22)
      • 12. Meng, H., Guan, Y., Chen, S.: ‘Modeling and analysis of noise effects on broadband power-line communication’, IEEE Trans. Power Deliv., 2005, 20, (2), pp. 630–637.
    23. 23)
      • 22. Clere, S.M., Kennedy, J.: ‘The particle swarm-explosion, stability and convergence in a multidimensional complex space’, IEEE Trans. Evol. Comput., 2002, 6, (1), pp. 58–73.
    24. 24)
      • 5. Cortes, J.A., Díez, L., Canete, F.J., et al: ‘Analysis of the indoor broadband power-line noise scenario’, IEEE Trans. Electromagn. Compat., 2010, 52, (4), pp. 849–858.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-com.2018.5282
Loading

Related content

content/journals/10.1049/iet-com.2018.5282
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading