Performance Analysis of Evolutionary ANN for Output Prediction of a Grid-Connected Photovoltaic System

Authors: S.I Sulaiman, T.K Abdul Rahman, I. Musirin, S. Shaari

Abstract:

This paper presents performance analysis of the Evolutionary Programming-Artificial Neural Network (EPANN) based technique to optimize the architecture and training parameters of a one-hidden layer feedforward ANN model for the prediction of energy output from a grid connected photovoltaic system. The ANN utilizes solar radiation and ambient temperature as its inputs while the output is the total watt-hour energy produced from the grid-connected PV system. EP is used to optimize the regression performance of the ANN model by determining the optimum values for the number of nodes in the hidden layer as well as the optimal momentum rate and learning rate for the training. The EPANN model is tested using two types of transfer function for the hidden layer, namely the tangent sigmoid and logarithmic sigmoid. The best transfer function, neural topology and learning parameters were selected based on the highest regression performance obtained during the ANN training and testing process. It is observed that the best transfer function configuration for the prediction model is [logarithmic sigmoid, purely linear].

Keywords: Artificial neural network (ANN), Correlation coefficient (R), Evolutionary programming-ANN (EPANN), Photovoltaic (PV), logarithmic sigmoid and tangent sigmoid.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1079914

References:

[1] I. Ashraf and A. Chandra, "Artificial neural network based models for forecasting electricity generation of grid connected solar PV power plant", Int. Journal of Global Energy Issues, vol. 21, no. 1/2, pp. 119-130, 2004.
[2] M. Balzani and A. Reatti, "Neural network based model of a PV array for the optimum performance of PV system", in Proc. PhD Research in Microelectronics and Electronics Conf., vol. 2, 2005, pp. 123-126.
[3] X. Yao, "Evolving artificial neural networks", in Proc. Of the IEEE, vol. 87, no. 9, 1999.
[4] S.I. Sulaiman, T.K. Abdul Rahman, and I. Musirin, "ANN-based technique with embedded data filtering capability for predicting total AC power from grid-connected photovoltaic system", in Proc. 2nd International Power Engineering and Optimization Conference (PEOCO2008), 2008, pp. 272-277.
[5] X. Yao and Y. Liu, "Towards designing artificial neural networks by evolution", Applied Mathematics and Computation, vol. 91, pp. 83-90, 1998.
[6] D.B. Fogel, "An introduction to simulated evolutionary optimization", IEEE Transactions on Neural Networks, vol. 5, pp. 3-14, 1994.
[7] L.J. Fogel, "Autonomous automata", Industrial Research, vol. 4, no. 1, pp.14-19, 1962.
[8] T. Back and H.-P. Schwefel, "Evolutionary computation: an overview", in Proc. IEEE International Conference on Evolutionary Computation (ICEC-96), 1996, pp. 20-29.
[9] M. Sarkar and B. Yegnanarayana, "Feedforward neural networks configuration using evolutionary programming", in Proc. International Conference on Neural Networks, vol. 1, 1997, pp. 438-443.
[10] K. Peng, S.S. Ge, and C. Wen, "An algorithm to determine neural network hidden layer size and weight coefficients", in Proc. 15th IEEE International Symposium on Intelligent Control (ISIC 2000), 2000, pp. 261-266.
[11] B. Yegnanarayana, Artificial Neural Networks, New Delhi: Prentice Hall of India, 2006, ch. 1.
[12] S.R. Wenham, M.A. Green, and M.E. Watt. Applied Photovoltaics. Centre for Photovoltaic Devices and Systems, Sydney: The University of New South Wales, 1995, ch. 1.
[13] W.M. Jenkins, "Neural network weight training by mutation", Computers & Structures, vol. 84, pp. 2107-2112, 2006.
[14] M. Annunziato, I. Bertini, A. Pannicelli and S. Pizzuti, "Evolutionary feed-forward neural networks for traffic prediction", in Proc. International Congress on Evolutionary Methods for Design, Optimization and Control with Applications to Industrial Problems (EUROGEN 2003), 2003, pp. 1-8.
[15] J. Fang and Y. Xi, "Neural network design based on evolutionary programming", Artificial Intelligence in Engineering, vol. 11, pp. 155-161, 1997.
[16] M.F. Augusteijn and T.P. Harrington, "Evolving transfer functions for artificial neural networks", Neural Computing and Applications, vol. 13, pp. 38-46, 2004.
[17] D. Johari, T.K. Abdul Rahman and I. Musirin, "Artificial Neural Network Based Technique for Lightning Prediction", in Proc. 5th Student Conference on Research and Development (SCOReD 2007), 2007.
[18] O.A. Dombaycr and M. Golcu, "Daily means ambient temperature prediction using artificial neural network method: a case study of Turkey", Renewable Energy, vol. 34, no. 4, pp. 1158-1161, 2009.
[19] W. Gao, "Study of new evolutionary neural network", in Proc. 2nd International Conference on Machine Learning and Cybernetics, 2003, pp. 1287-1292.
[20] I. Musirin and T.K. Abdul Rahman, "Evolutionary programming based optimization technique for maximum loadability estimation in electric power system", in Proc. National Power and Energy Conference (PECon), 2003, pp. 205-210.
[21] S.I. Sulaiman, T.K. Abdul Rahman and I. Musirin, "Semi automatic design of two-hidden layer feedforward ANN for grid-photovoltaic system out prediction", in Proc. International Graduate Conference of Engineering and Science, 2008, pp. 91-96.
[22] F.I Hassim, I. Musirin and T.K. Abdul Rahman, "Voltage stability margin enhancement using Evolutionary Programming (EP)", in Proc. 4th Student Conference on Research and Development (SCOReD 2006), 2006, pp. 235-240.