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

access icon free Effective prediction model for Hungarian small-scale solar power output

© The Institution of Engineering and Technology
Received 10/03/2017, Accepted 02/08/2017, Revised 30/07/2017, Published 04/08/2017

Owing to critical role of photovoltaic (PV) power in oncoming energy market, an accurate PV power forecasting model is demanded. In this paper, an effective solar power prediction model composed of variational mode decomposition, information-theoretic feature selection, and forecasting engine with high learning capability is proposed. The feature selection method is based on information-theoretic criteria and an optimisation algorithm. The forecasting engine is multilayer perceptron neural network equipped with modified Levenberg–Marquardt learning algorithm. An evolutionary algorithm is also incorporated into the training mechanism of the forecasting engine to enhance its learning capability. Effectiveness of the proposed PV prediction model is illustrated on a Hungarian solar power plant.

Inspec keywords: learning (artificial intelligence); feature selection; photovoltaic power systems; power engineering computing; solar power stations; multilayer perceptrons; load forecasting; variational techniques; evolutionary computation

Other keywords: information-theoretic criteria; Hungarian solar power plant; forecasting engine training mechanism; Levenberg–Marquardt learning algorithm; PV power; Hungarian small-scale solar power output; energy market; learning capability enhancement; evolutionary algorithm; photovoltaic power; optimisation algorithm; effective solar power prediction model; multilayer perceptron neural network; PV power forecasting model; variational mode decomposition; forecasting theoretic feature selection

Subjects: Power system planning and layout; Mathematical analysis; Solar power stations and photovoltaic power systems; Optimisation techniques; Power engineering computing; Data handling techniques; Mathematical analysis; Knowledge engineering techniques; Optimisation techniques; Neural computing techniques

References

    1. 1)
      • 24. Chaabene, M., Ammar, M.B.: ‘Neuro-fuzzy dynamic model with Kalman filter to forecast irradiance and temperature for solar energy systems’, Renew. Energy, 2008, 33, (7), pp. 1435–1443.
    2. 2)
      • 4. Geraldi, E., Romano, F., Ricciardelli, E.: ‘An advanced model for the estimation of the surface solar irradiance under all atmospheric conditions using MSG/SEVIRI data’, IEEE Trans. Geosci. Remote Sens., 2009, 2, (1), pp. 2–10.
    3. 3)
      • 33. Tasoulis, D.K., Pavlidis, N., Plagianakos, V.P., et al: ‘Parallel differential evolution’. Proc. IEEE Congress Evolution Computation, June 2004, vol. 2, pp. 2023–2029.
    4. 4)
      • 20. Sfetsos, A., Coonick, A.H.: ‘Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques’, Sol. Energy, 2000, 68, (2), pp. 169–178.
    5. 5)
      • 5. Cheng, H., Cao, W., Ge, P.: ‘Forecasting research of long-term solar irradiance and output power for photovoltaic generation system, computational and information sciences (ICCIS)’. 2012 Fourth Int. Conf., 17–19 August 2012.
    6. 6)
      • 23. Cao, J., Lin, X.: ‘Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks’, Energy Convers. Manage., 2008, 49, (6), pp. 1396–1406.
    7. 7)
      • 7. Li, Y., Su, Y., Shu, L.: ‘An ARMAX model for forecasting the power output of a grid connected photovoltaic system’, Renew. Energy, 2014, 66, pp. 78–89.
    8. 8)
      • 35. http://nord-point.hu/napelem/aktualis-termeles/, accessed December 2016.
    9. 9)
      • 37. Weather data website. March 2012. Available at http://wunderground.com/, accessed December 2016.
    10. 10)
      • 11. Bae, K.Y., Jang, H.S., Sung, D.K.: ‘Hourly solar irradiance prediction based on support vector machine and its error analysis’, IEEE Trans. Power Syst., 2017, doi: 10.1109/TPWRS.2016.2569608.
    11. 11)
      • 18. Mellit, A., Pavan, A.M.: ‘A 24 h forecast of solar irradiance using artificial neural network: application for performance prediction of a grid-connected PV plant at Triest, Italy’, Sol. Energy, 2010, 84, (5), pp. 807–821.
    12. 12)
      • 30. Bertsekas, D.P.: ‘Constrained optimization and Lagrange multiplier methods’, in (EDs.): ‘Computer science and applied mathematics’, vol. 1 (Academic, Boston, MA, USA, 1982).
    13. 13)
      • 10. Zhang, N., Behera, P.K.: ‘Solar radiation prediction based on recurrent neural networks trained by Levenberg–Marquardt back propagation learning algorithm’. 2012 IEEE PES Innovative Smart Grid Technologies (ISGT), 2012, pp. 1–7.
    14. 14)
      • 28. Dragomiretskiy, K., Zosso, D.: ‘Variational mode decomposition’, IEEE Trans. Signal Process., 2014, 62, (3), pp. 531–544.
    15. 15)
      • 25. Haque, A.U., Nehrir, M.H., Mandal, P.: ‘Solar PV power generation forecast using a hybrid intelligent approach’. Power and Energy Society General Meeting (PES), July 2013, pp. 1–5.
    16. 16)
      • 9. Reikard, G.: ‘Predicting solar radiation at high resolutions: a comparison of time series forecasts’, Sol. Energy, 2009, 83, (3), pp. 342–349.
    17. 17)
      • 32. Abedinia, O., Amjady, N., Ghasemi, A.: ‘A new meta-heuristic algorithm based on shark smell optimization’, Complexity J., 2014, 21, pp. 97–116.
    18. 18)
      • 27. Nazaripouya, H., Wang, B., Wang, Y., et al: ‘Univariate time series prediction of solar power using a hybrid wavelet-ARMA-NARX prediction method’. 2016 IEEE/PES Transmission and Distribution Conf. and Exposition (T&D), July 2016.
    19. 19)
      • 17. Mellit, A., Kalogirou, S.A., Drif, M.: ‘Application of neural networks and genetic algorithms for sizing of photovoltaic systems’, Renew. Energy, 2010, 35, (12), pp. 2881–2893.
    20. 20)
      • 15. Li, J., Ward, J.K., Tong, J., et al: ‘Machine learning for solar irradiance forecasting of photovoltaic system’, Renew. Energy, 2016, 90, pp. 542–553.
    21. 21)
      • 34. Kozlov, K.N., Samsonov, A.M.: ‘A new migration scheme for parallel differential evolution’. Proc. Fifth Int. Conf. BGRS, July 2006, pp. 141–144.
    22. 22)
      • 14. Lima, M.A.F.B., Carvalho, P.C.M., Carneiro, T.C., et al: ‘Portfolio theory applied to solar and wind resources forecast’, IET Renew. Power Gener., 2017, 11, pp. 973–978.
    23. 23)
      • 1. Chikh, A., Chandra, A.: ‘Adaptive neuro-fuzzy based solar cell model’, IET Renew. Power Gener., 2013, 8, (6), pp. 679–686, doi: 10.1049/iet-rpg.2013.0183.
    24. 24)
      • 31. Abedinia, O., Amjady, N., Zareipour, H.: ‘A new feature selection technique for load and price forecast of electrical power systems’, IEEE Trans. Power Syst., 2017, 32, pp. 62–74.
    25. 25)
      • 29. Hestenes, M.R.: ‘Multiplier and gradient methods’, J. Optim. Theory Appl., 1969, 4, (5), pp. 303–320.
    26. 26)
      • 26. Mandal, P., Madhira, S.T.S., Haque, A.U., et al: ‘Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques’, Procedia Comput. Sci., 2012, 12, pp. 332–337.
    27. 27)
      • 22. Ssekulima, E.B., Anwar, M.B., Al Hinai, A., et al: ‘Wind speed and solar irradiance forecasting techniques for enhanced renewable energy integration with the grid: a review’, IET Renew. Power Gener., 2016, 10, (7), pp. 885–989.
    28. 28)
      • 19. Mellit, A., Benghanem, M., Bendekhis, M.: ‘Artificial neural network model for prediction solar radiation data: application for sizing stand-alone photovoltaic power system’. Proc. IEEE Power Engineering Society, General Meeting, 2005, vol. 1, pp. 40–44.
    29. 29)
      • 6. Colak, I., Yesilbudak, M., Genc, N., et al: ‘Multi-period prediction of solar radiation using ARMA and ARIMA models machine learning and applications (ICMLA)’. 2015 IEEE 14th Int. Conf., 9–11 December 2015.
    30. 30)
      • 13. Fidan, M., Hocaoğlu, F.O., Gerek, Ö.N.: ‘Harmonic analysis based hourly solar radiation forecasting model’, IET Renew. Power Gener., 2015, 9, (3), pp. 218–227.
    31. 31)
      • 3. Mathiesen, P., Brown, J.M., Kleissl, J.: ‘Geostrophic wind dependent probabilistic irradiance forecasts for coastal California’, IEEE Trans. Sustain. Energy, 2013, 4, (2), pp. 510–518.
    32. 32)
      • 21. Hocaoglu, F.O., Gerek, O.N., Kurban, M.: ‘A novel 2d model approach for the prediction of hourly solar radiation’, in Proceedings of DBLP Conference: Computational and Ambient Intelligence, 9th International Work-Conference on Artificial Neural Networks (IWANN 2007), June 20–22 2007, San Sebastiân, Spain, doi: 10.1007/978-3-540-73007-1_90.
    33. 33)
      • 12. Ramedani, Z., Omid, M., Keyhani, A., et al: ‘Potential of radial basis function based support vector regression for global solar radiation prediction’, Renew. Sustain. Energy Rev., 2014, 39, pp. 1005–1011.
    34. 34)
      • 36. University of Oregon solar radiation monitoring laboratory website. March 2012. Available at http://solardat.uoregon.edu/, accessed December 2016.
    35. 35)
      • 16. Quaiyum, S., Rahman, S., Rahman, S.: ‘Application of artificial neural network in forecasting solar irradiance and sizing of photovoltaic cell for standalone systems in Bangladesh’, Int. J. Comput. Appl., 2011, 32, (10), pp. 51–56.
    36. 36)
      • 2. Diyaf, A.G., Mather, R.R., Wilson, J.I.B.: ‘Contacts on polyester textile as a flexible substrate for solar cells’, IET Renew. Power Gener., 2013, 8, (5), pp. 444–450, doi: 10.1049/iet-rpg.2013.0236.
    37. 37)
      • 8. Al-Alawi, S., Al-Hinai, H.: ‘An ANN-based approach for predicting global radiation in locations with no direct measurement instrumentation’, Renew. Energy, 1998, 14, (14), pp. 199–204.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-rpg.2017.0165
Loading

Related content

content/journals/10.1049/iet-rpg.2017.0165
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address