Improved Artificial Neural Network for Grid-Connected Photovoltaic System Output Prediction

  • Authors

    • Shahril Irwan Sulaiman
    • Norfarizani Nordin
    • Ahmad Maliki Omar
    2019-01-18
    https://doi.org/10.14419/ijet.v8i1.7.25967
  • photovoltaic, multi-layer feedforward neural network, solar irradiance, ambient temperature, module temperature.
  • This paper presents the output prediction of Grid-Connected Photovoltaic (GCPV) system using a multi-layer feedforward neural network. Conventional prediction requires mathematical expressions that need to be updated whenever new system is investigated. However, the introduction of Artificial Neural Network (ANN) in this study eliminated the need for using mathematical expressions. The MLFNN inputs were set to be Solar Irradiance (SI), Ambient Temperature (AT) and Module Temperature (MT) with the respective both current and previous five-minute values while the sole output was set to be the AC power from the GCPV system. The MLFNN was implemented in two stages, i.e. the training and testing. The results showed that the MLFNN model had outperformed the existing MLFNN model using SI and AT as inputs without previous five-minute values in producing the lowest Root Mean Square Error (RMSE) and highest correlation coefficient during both training and testing processes.

     

     

  • References

    1. [1] N. Apergis, J. E. Payne, K. Menyah, and Y. Wolde-Rufael, "On the causal dynamics between emissions, nuclear energy, renewable energy, and economic growth," Ecological Economics, vol. 69, pp. 2255-2260, 2010.

      [2] C. De Boer and I. Catsburg, "A report: The impact of nuclear accidents on attitudes toward nuclear energy," The Public Opinion Quarterly, vol. 52, pp. 254-261, 1988.

      [3] S. Jacobsson and A. Johnson, "The diffusion of renewable energy technology: an analytical framework and key issues for research," Energy policy, vol. 28, pp. 625-640, 2000.

      [4] A. V. Herzog, T. E. Lipman, and D. M. Kammen, "Renewable energy sources," Encyclopedia of Life Support Systems (EOLSS). Forerunner Volume-‘Perspectives and Overview of Life Support Systems and Sustainable Development, 2001.

      [5] I. Dincer, "Renewable energy and sustainable development: a crucial review," Renewable and Sustainable Energy Reviews, vol. 4, pp. 157-175, 2000.

      [6] J. L. Sawin, F. Sverrisson, K. Seyboth, R. Adib, H. E. Murdock, C. Lins, I. Edwards, M. Hullin, L. H. Nguyen, and S. S. Prillianto, "Renewables 2017 Global Status Report," 2013.

      [7] P.N.A.M. Yunus, S.I. Sulaiman and A.M. Omar, “Online performance monitoring of grid-connected photovoltaic system using hybrid improved fast evolutionary programming and artificial neural network,†Indonesian Journal of Electrical Engineering and Computer Science, vol. 8, no. 2, pp. 399-406, 2017.

      [8] T. N. Hussain, S. I. Sulaiman, I. Musirin, S. Shaari, and H. Zainuddin, "A hybrid artificial neural network for grid-connected photovoltaic system output prediction," in Computers & Informatics (ISCI), 2013 IEEE Symposium on, 2013, pp. 108-111.

      [9] M. H. B. KARAMI, "Application of neural networks in short-term load forecasting," network, vol. 1, p. 2, 2005.

      [10] N. Suraweera and D. Ranasinghe, "Adaptive Structural Optimisation of Neural Networks," ICTer, vol. 1, 2008.

      [11] M. J. Cooke and G. L. Lebby, "An optimal design method for multilayer feedforward networks," in System Theory, 1998. Proceedings of the Thirtieth Southeastern Symposium on, 1998, pp. 507-511.

      [12] W. Laosiritaworn and N. Chotchaithanakorn, "Artificial neural networks parameters optimization with design of experiments: An application in ferromagnetic materials modeling," Chiang Mai J. Sci, vol. 36, pp. 83-91, 2009.

      [13] I. Basheer and M. Hajmeer, "Artificial neural networks: fundamentals, computing, design, and application," Journal of Microbiological Methods, vol. 43, pp. 3-31, 2000.

      [14] D. Gao, P. Wand, and H. Liang, "Optimization of hidden nodes and training times in ANN-QSAR model," Environ Informat Arch, vol. 5, pp. 464-468, 2007.

      [15] N. Nordin, S.I. Sulaiman and A.M. Omar, “Prediction of AC power output in grid-connected photovoltaic system using artificial neural network with multi-variable inputs,†in 2016 IEEE Conference on Systems, Process and Control, Melaka, 16-18 December 2016, pp. 192-195.

      [16] M. Dorofki, A. H. Elshafie, O. Jaafar, O. A. Karim, and S. Mastura, "Comparison of artificial neural network transfer functions abilities to simulate extreme runoff data," International Proceedings of Chemical, Biological and Environmental Engineering, vol. 33, pp. 39-44, 2012.

      [17] Ö. A. Dombaycı and M. Gölcü, "Daily means ambient temperature prediction using artificial neural network method: A case study of Turkey," Renewable energy, vol. 34, pp. 1158-1161, 2009.

      [18] S. I. Sulaiman, I. Musirin and T. K. A. Rahman, "Prediction of grid-photovoltaic system output using three-variate ANN models," WSEAS Transactions on Information Science and Applications, vol. 6, no. 8, pp. 1339-1348, August 2009.

  • Downloads

  • How to Cite

    Irwan Sulaiman, S., Nordin, N., & Maliki Omar, A. (2019). Improved Artificial Neural Network for Grid-Connected Photovoltaic System Output Prediction. International Journal of Engineering & Technology, 8(1.7), 126-132. https://doi.org/10.14419/ijet.v8i1.7.25967