access icon free Performance of different kernel functions for LS-SVM-GWO to estimate flashover voltage of polluted insulators

© The Institution of Engineering and Technology
Received 25/10/2017, Accepted 11/04/2018, Revised 13/03/2018, Published 16/04/2018

This work attempts to clarify the potentials of hybrid model based on least-squares support vector machine (LS-SVM) and a novel meta-heuristic algorithm called Grey Wolf optimiser (GWO) in high-voltage applications, considering several kernel functions. The selection of the suitable kernel function and its parameters play an important role in the performance of LS-SVM. For this purpose, GWO is proposed in this study as an efficient optimisation approach to adjust the parameters of various kernel functions such as linear kernel (Lin), radial basis function kernel, polynomial kernel (poly) and multi-layer perceptron kernel. Afterwards, the LS-SVM with the most appropriate kernel function is designed to model flashover voltage of polluted high-voltage insulators. The performance of the developed model is compared with the previous works. The results confirm high capabilities of the proposed hybrid model for the prediction of the flashover voltage of polluted insulators.

Inspec keywords: least squares approximations; optimisation; flashover; power engineering computing; support vector machines; insulator contamination

Other keywords: polynomial kernel; least-squares support vector machine; polluted high voltage insulator; radial basis function kernel; meta-heuristic algorithm; flashover voltage estimation; multilayer perceptron kernel; Grey Wolf optimisation approach; LS-SVM-GWO

Subjects: Power engineering computing; Dielectric breakdown and discharges; Other topics in statistics; Interpolation and function approximation (numerical analysis); Other topics in statistics; Interpolation and function approximation (numerical analysis); Power line supports, insulators and connectors; Optimisation techniques; Optimisation techniques; Knowledge engineering techniques

References

    1. 1)
      • 43. Campbell, C.: ‘An introduction to kernel methods radial basis function network: design and applications’ (Springer, Berlin, 2000), pp. 1–31.
    2. 2)
      • 3. Topalis, F.V., Gonos, I.F., Stathopoulos, I.A.: ‘Dielectric behaviour of polluted porcelain insulators’, IEE Proc. Gener., Trans. Distrib. IET, 2001, 148, (4), pp. 269–274.
    3. 3)
      • 16. Asimakopoulou, G.E., Kontargyri, V.T., Tsekouras, G.J., et al: ‘Artificial neural network optimisation methodology for the estimation of the flashover voltage on insulators’, IET Sci. Meas. Technol., 2009, 3, (1), pp. 90–104.
    4. 4)
      • 36. Mustaffa, Z., Sulaiman, M.H., Kahar, M.N.M.: ‘LS-SVM hyper-parameters optimization based on GWO algorithm for time series forecasting’. Fourmtth Int. Conf. Software Engineering and Computer Systems (ICSECS), Kuantan, Pahang, Malaysia, 2015, pp. 183–188.
    5. 5)
      • 20. Chatterjee, A., Rakshit, A., Mukherjee, R.K.: ‘A self-organizing fuzzy inference system for electric field optimization of HV electrode systems’, IEEE Trans. Dielectr. Electr. Insul., 2001, 8, (6), pp. 995–1002.
    6. 6)
      • 13. Ugur, M., Auckland, D.W., Varlow, B.R., et al: ‘Neural networks to analyze surface tracking on solid insulators’, IEEE Trans. Dielectr. Electr. Insul., 1997, 4, (6), pp. 763–766.
    7. 7)
      • 31. Caballero, J., Fernández, L., Garriga, M., et al: ‘Proteometric study of ghrelin receptor function variations upon mutations using amino acid sequence autocorrelation vectors and GA-based LS-SVM’, J. Mol. Graph. Model., 2007, 26, (1), pp. 166–178.
    8. 8)
      • 34. Dos Santos, G.S., Luvizotto, L.G.J., Mariani, V.C., et al: ‘Least squares support vector machines with tuning based on chaotic differential evolution approach applied to the identification of a thermal process’, Expert Syst. Appl., 2012, 39, (5), pp. 4805–4812.
    9. 9)
      • 18. Belkheiri, M., Zegnini, B., Mahi, D.: ‘Modeling the critical flashover voltage of high voltage insulators using artificial intelligence’, J. Intell. Comput. Appl. (JICA), 2009, 2, (2), pp. 137–154.
    10. 10)
      • 9. Farag, A.S., Shwehdi, M.H., Cheng, T.C.: ‘Interfacial breakdown on contaminated electrolytic surfaces’, Eur. Trans. Electr. Power, 1999, 9, (1), pp. 49–56.
    11. 11)
      • 44. Kaytez, F., Taplamacioglu, M.C., Camb, E., et al: ‘Forecasting electricity consumption: a comparison of regression analysis, neural networks and least squares support vector machines’, Int. J. Electr. Power Energy Syst., 2015, 67, pp. 431–438.
    12. 12)
      • 47. Bessedik, S.A., Djekidel, R., Ameur, A.: ‘Improved LS-SVM using ACO to estimate flashover voltage of polluted insulators’, J. Eng. Sci. Technol., 2017, 12, (1), pp. 62–77.
    13. 13)
      • 35. Mustaffa, Z., Yusof, Y., Kamaruddin, S.S.: ‘Enhanced artificial bee colony for training least squares support vector machines in commodity price forecasting’, J. Comput. Sci., 2014, 5, (2), pp. 196–205.
    14. 14)
      • 41. Suykens, J.A.K., Vandewalle, J.: ‘Least squares support vector machine classifiers’, Neural Process. Lett., 1999, 9, (3), pp. 293–300.
    15. 15)
      • 17. Gençoğlu, M.T., Cebeci, M.: ‘Investigation of pollution flashover on high voltage insulators using artificial neural network’, Expert Syst. Appl., 2009, 36, pp. 7338–7345.
    16. 16)
      • 15. Kontargyri, V.T., Gialketsi, A.A., Tsekouras, G.J., et al: ‘Design of an artificial neural network for the estimation of the flashover voltage on insulators’, Electr. Power Syst. Res., 2007, 77, (12), pp. 1532–1540.
    17. 17)
      • 1. Rizk, F.A.M.: ‘Mathematical models for pollution flashover’, Electra, 1981, 78, pp. 71–103.
    18. 18)
      • 23. Erenturk, K.: ‘Adaptive-network-based fuzzy inference system application to estimate the flashover voltage on insulator’, Instrum. Sci. Technol., 2009, 37, (4), pp. 446–461.
    19. 19)
      • 7. Zhicheng, G., Renyu, Z.: ‘Calculation of DC and AC flashover voltage of polluted insulators’, IEEE Trans. Electr. Insul., 1990, 25, (4), pp. 723–729.
    20. 20)
      • 25. Vapnik, V.N.: ‘Statistical learning theory’ (Wiley, New York, USA, 1998).
    21. 21)
      • 4. Aydogmus, Z., Cebeci, M.: ‘A new flashover dynamic model of polluted HV insulators’, IEEE Trans. Dielectr. Electr. Insul., 2004, 11, (4), pp. 577–584.
    22. 22)
      • 10. Bessedik, S.A., Hadi, H., Volat, C., et al: ‘Refinement of residual resistance calculation dedicated to polluted insulator flashover models’, IEEE Trans. Electr. Insul., 2014, 21, (3), pp. 1207–1215.
    23. 23)
      • 30. Mahdjoubi, A.H., Zegnini, B., Belkheiri, M.: ‘A LS-SVM (least squares support vector machines) approach for predicting critical flashover voltage of polluted insulators’, J. Energy Power Eng., 2013, 7, pp. 355–360.
    24. 24)
      • 39. Nitin, M., Urvinder, S., Balwinder, S.S.: ‘Modified Grey Wolf optimizer for global engineering optimization’, Appl. Comput. Intell. Soft Comput., 2016, 16, doi:/10.1155/2016/7950348.
    25. 25)
      • 22. Asimakopoulou, G.E., Kontargyri, V.T., Tsekouras, G.J., et al: ‘A fuzzy logic optimisation methodology for the estimation of the critical flashover voltage on insulators’, Electr. Power Syst. Res., 2011, 81, pp. 580–588.
    26. 26)
      • 21. Cavallini, A., Montanari, G.C., Puletti, F.: ‘A fuzzy logic algorithm to detect electric trees in polymeric insulation systems’, IEEE Trans. Dielectr. Electr. Insul., 2005, 12, (6), pp. 1134–1144.
    27. 27)
      • 14. Jahromi, A.N., El-hag, A.H., Jayaram, S.H., et al: ‘A neural network based method for leakage current prediction of polymeric insulators’, IEEE Trans. Power Deliv., 2006, 21, (1), pp. 506–507.
    28. 28)
      • 12. Ghosh, P.S., Chakravorti, S., Chatterjee, N.: ‘Modelling of critical flashover voltage characteristics of contaminated electrolytic surfaces of insulators using artificial neural network’, J. Inst. Eng., 1995, 76, pp. 50–56.
    29. 29)
      • 26. Suykens, J.A.K., Van Gestel, T., De Brabanter, J., et al: ‘Least squares support vector machines, World Scientific, Singapore’, ISBN 981-238-151-1. 2002.
    30. 30)
      • 19. Aydogmus, Z.: ‘A neural network-based estimation of electric fields along high voltage insulators’, Expert Syst. Appl., 2009, 36, pp. 8705–8710.
    31. 31)
      • 8. Sundararajan, R., Gorur, R.S.: ‘Dynamic arc modeling of pollution flashover of insulators under dc voltage’, IEEE Trans. Dielectr. Electr. Insul., 1993, 28, (2), pp. 209–218.
    32. 32)
      • 46. Gonos, I.F., Topalis, F.V., Stathopoulos, I.A.: ‘Genetic algorithm approach to the modelling of polluted insulators’, IEE Proc. Gener. Transm. Distrib., 2002, 149, (3), pp. 373–376.
    33. 33)
      • 11. Ghosh, P.S., Chakravorti, S., Chatterjee, N.: ‘Estimation of time-to-flashover characteristics of contaminated electrolytic surfaces using a neural network’, IEEE Trans. Dielectr. Electr. Insul., 1995, 2, (6), pp. 1064–1074.
    34. 34)
      • 2. Megriche, D.N., Beroual, A.: ‘Flashover dynamic model of polluted insulators under ac voltage’, IEEE Trans. Dielectr. Electr. Insul., 2000, 7, (2), pp. 283–289.
    35. 35)
      • 40. Yusof, Y., Mustaffa, Z.: ‘Time series forecasting of energy commodity using Grey Wolf optimizer’. Int. Multi Conf. Engineers and Computer Scientists IMECS 2015, Hong Kong, vol. I, 2015.
    36. 36)
      • 6. IEC 815, Guide for the selection of insulators in respect of polluted conditions, 2006.
    37. 37)
      • 32. Guo, X.C., Yang, J.H., Wu, C.G., et al: ‘A novel LS-SVMs hyper-parameter selection based on particle swarm optimization’, Neurocomputing, 2008, 71, (16), pp. 3211–3215.
    38. 38)
      • 37. Sun, W., Liu, M., Liang, D.Y.: ‘Wind speed forecasting based on FEEMD and LSSVM optimised by the bat algorithm’, Energies, 2015, 8, (7), pp. 6585–6607.
    39. 39)
      • 42. Mercer, J.: ‘Function of positive and negative type and their connection with the theory of integral equations’, Philos. Trans. R. Soc. Lond. A, 1909, 209, pp. 415–446.
    40. 40)
      • 29. Bessedik, S.A., Hadi, H.: ‘Prediction of flashover voltage of insulators using least squares support vector machine with particle swarm optimisation’, Electr. Power Syst. Res., 2013, 104, pp. 87–92.
    41. 41)
      • 27. Gençoğlu, M.T., Uyar, M.: ‘Prediction of flashover voltage of insulators using least squares support vector machines’, Expert Syst. Appl., 2009, 36, pp. 10789–10798.
    42. 42)
      • 24. Bessedik, S.A., Hadi, H.: ‘Prediction of flashover voltage of insulators using adaptive neuro-fuzzy inference system’, J. Electr. Eng. (JEE), 2013, 13, (3).
    43. 43)
      • 5. IEC 507, Artificial pollution tests on high-voltage insulators to be used on a.c. systems, 1991.
    44. 44)
      • 33. Zhang, W., Niu, P.: ‘LS-SVM based on chaotic particle swarm optimization with simulated annealing and application’. 2011 Second Int. Conf. Intelligent Control and Information Processing (ICICIP), Harbin, 2011, vol. 2, pp. 931–935.
    45. 45)
      • 45. Ikonomou, K., Katsibokis, G., Panos, G., et al: ‘Cool fog tests on artificially polluted insulators’. Fifth Int. Symp. HV Engineering, Braunschweig, 1987, vol. II, p. 52.13.
    46. 46)
      • 28. Zegnini, B., Mahdjoubi, A.H, Belkheiri, M.: ‘A least squares support vector machines (LS-SVM) approach for predicting critical flashover voltage of polluted insulators’. IEEE Conf. CEIDP, Cancun, Mexico, October 2011, pp. 403–406.
    47. 47)
      • 38. Mirjalili, S., Mirjalili, S.M., Andrew, L.: ‘Grey Wolf optimizer’, Adv. Eng. Softw., 2014, 69, pp. 46–61.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-smt.2017.0486
Loading

Related content

content/journals/10.1049/iet-smt.2017.0486
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading