Artificial neural network and neuro fuzzy inference modelling of global solar radiation data using bayesian algorithm for design of solar energy conversion system

  • Authors

    • S Shanmuga Priya
    • Lisa Maria Ubbenjans
    • I Thirunavukkarasu
    2018-04-20
    https://doi.org/10.14419/ijet.v7i2.21.11842
  • Global Solar Radiation, Artificial Neural Networks, Fuzzy Inference Modelling, Root Mean Square Error, Regression Coefficient.

  • Measurement of global solar radiation is particularly required for proper design of solar energy conversion systems. This study investigates the use of software tools like neural networks and fuzzy inference systems for modelling so as to predict global solar radiation using different input parameters based on available weather data. Advantages include simplicity, speed and efficiency, to make short term predictions of global solar radiation at different locations in India, Germany and United Kingdom. It helps in estimation of effectiveness of the applied model which matches solar radiation and other meteorological parameters which are in a non-linear relationship. Bayesian Inference algorithm is used for the current study in estimation of global solar radiation.

     

     

  • References

    1. [1] Araghinejad S, Data-driven modeling: using MATLAB® in water resources and environmental engineering, Springer Science & Business Media, (2013).

      [2] Gulin M, VaÅ¡ak M & Baotic M, “Estimation of the global solar irradiance on tilted surfacesâ€, 17th International Conference on Electrical Drives and Power Electronics, Vol.6, No.4, (2013), pp. 347-353.

      [3] Hejase HA, Assi AH & Al Shamisi MH, “Use of Empirical Regression and Artificial Neural Network Models for Estimation of Global Solar Radiation in Dubai, UAEâ€, Causes, Impacts and Solutions to Global Warming, (2013), pp.61-86.

      [4] Kamali Gh.A, Morad I & Khalili A, “Estimating solar radiation on tilted surfaces with various orientations. A study case in Karaj (Iran)â€, Theor. Appl. Climatol, Vol.84, No.4, (2006), pp.235–241.

      [5] Landau CR, “Optimum tilt of solar panelsâ€, Optimum Tilt of Solar Panels, (2012).

      [6] Mohammadi K, Shamshirband S, Danesh AS, Abdullah MS & Zamani M, “Temperature-based estimation of global solar radiation using soft computing methodologiesâ€, Theoretical and applied climatology, Vol.125, No.1-2, (2016), pp.101-112.

      [7] Gran R, “Solar Variability: Striking a Balance with Climate Changeâ€, Hg. v. NASA. NASA's Goddard Space Flight Center., (2008).

      [8] Teke A, Yıldırım HB & Çelik Ö, “Evaluation and performance comparison of different models for the estimation of solar radiationâ€, Renewable and Sustainable Energy Reviews, Vol.50, (2015), pp.1097-1107.

      [9] Zadeh LA, Fuzzy Logic Toolbox, Membership Functions. World sci books, (1995), pp.19-34.

  • Downloads

  • How to Cite

    Shanmuga Priya, S., Maria Ubbenjans, L., & Thirunavukkarasu, I. (2018). Artificial neural network and neuro fuzzy inference modelling of global solar radiation data using bayesian algorithm for design of solar energy conversion system. International Journal of Engineering & Technology, 7(2.21), 88-93. https://doi.org/10.14419/ijet.v7i2.21.11842