You are here

SIZING OF A STAND-ALONE PHOTOVOLTAIC SYSTEM BASED ON NEURAL NETWORKS AND GENETIC ALGORITHMS: APPLICATION FOR REMOTE AREAS

Journal Name:

Publication Year:

Author NameUniversity of Author
Abstract (2. Language): 
In literature several methodologies based on artificial intelligence techniques (neural networks, genetic algorithms and fuzzy-logic) have been proposed as alternatives to conventional techniques to solve a wide range of problems in various domains. The purpose of this work is to use neural networks and genetic algorithms for the prediction of the optimal sizing coefficient of Stand-alone Photovoltaic (SAPV) systems in remote areas when the total solar radiation data are not available. A database of total solar radiation data for 40 sites corresponding to 40 locations in Algeria, have been used to determine the iso-reliability(sizing) curves of a SAPV system (CA, CS) for each site. Initially, the genetic algorithm (GA) is used for determining the optimal coefficient (CAop, CSop) for each site by minimizing the optimal cost (objective function). These coefficients allow the determination of the number of PV modules and the capacity of the battery. Subsequently, a feed-forward neural network (NN) is used for the prediction of the optimal coefficient in remote areas based only on geographical coordinates. For this, 36 pairs have been used for the training of the network and 4 pairs have been used for testing and validation of the network. The simulation results have been analyzed and compared with conventional methods in order to show the importance of the proposed methodology. This methodology has been applied for Algerian location, but it can be generalized in the World. The Matlab (R) Ver. 7 has been used for this simulation.
459-469

REFERENCES

References: 

[1] Haas, A., “The value of photovoltaic
electricity for society“, Solar Energy,
Vol;54, pp.25-31. 1995
[2] Barra, L., Catalanotti, S., Fontana, F.,
Lavorante, F., “An analytical method to
determine the optimal size of a photovoltaic
plant”, Solar Energy;Vol:33:pp.509,1984.
[3] Bartoli, B., Cuomo, V., Fontana, F., Serio,
C., Silvestrini, V. “The design of
photovoltaic plants: an optimization
procedure”. Applied Energy; Vol:18, pp.87-
1984.
[4] Klein S.A. and Beckman W.A.,” Loss of
load probabilities for stand alone PV”, Solar
Energy ,Vol:39, pp.499-505, 1987.
[5] Bucciarelli L.L.Jr, “Estimating loss of load
probabilities of stand alone photovoltaic
solar energy system”. Solar Energy, Vol:32,
pp.205-211, 1984.
[6] Gordon, J.M., “Optimal sizing of stand
alone photovoltaic solar power systems”.
Solar Cells;Vol.20, pp.295, 1987.
[7] Keller L., and Affolter P., “Optimizing the
panel area of photovoltaic system in relation
to the static inverter practical results”, Solar
Energy, Vol:55: pp.1-7, 1995.
[8] Shrestha G.B., and Goel L., “A study on
optimal sizing of stand-alone photovoltaic
stations”, IEEE Trans. on Energy
Conversion, Vol:13, pp.373-378, 1999.
Sizing Of A Stand-Alone Photovoltaic System Based On Neural Networks And Genetic Algorithms:
Application For Remote Areas
Adel MELLIT
468
[9] Groumpos P.P., and Papageorgiou G., “An
optimal sizing method for PV power
system”, Solar Energy, Vo:38, pp.314-351.
1987.
[10]Agha K. R., and Sbita M. N, “On the sizing
parameters for stand-alone solar-energy
systems”, Applied Energy, Vol.65, No:1-4,
pp.73-84. 2000.
[11] Shrestha, G.B., and Goel, L., “A study on
optimal sizing of stand-alone photovoltaic
stations”. IEEE Transactions on Energy
Conversion; Vol:13, No:4, pp. 373–378,
1998.
[12]Maghraby H.A.M., and Shwehdi M.H, Al-
Bassam, G.K., “Probabilistic assessment of
photovoltaic (PV) generation systems”.
IEEE Transactions on Power Systems,
Vol:17, No:1, pp.205-208, 2002.
[13] Egido M., and Lorenzo E., “The sizing of
sand-alone PV systems: A Review and a
proposed new method”, Solar Energy
Materials and Solar Cells, Vol:26 , pp.51-
69, 1992.
[14]Markvart T., Fragaki A., and Ross J.N,
“PV system sizing using observed time
series of solar radiation”, Solar Energy;
Vol:80, pp.46–50, 2006.
[15]Koutroulis E and Kolokotsa D , Potirakis A
and Kalaitzakis K, “Methodology for
optimal sizing of stand-alone
photovoltaic/wind-generator systems using
genetic algorithms”, Solar Energy; Vol:80,
pp.1072-1088, 2006.
[16] Mellit A, Benghanem M., Hadj Arab. A,
and Guessoum. A, “Spatial modeling of the
optimal sizing stand-alone photovoltaic
system Using spline function”, Proc. of 14th
International Photovoltaic Science and
Engineering Conference, Thailand, pp.114-
115. 2004.
[17] Mellit. A, Benghanem. M, Hadj Arab A.,
and Guessoum A., “Sizing the Stand-Alone
photovoltaic systems using the neural
networks adaptive model”, Proceedings of
8th Arab International Solar Energy
Conference and the World Renewable
Energy Congress, Bahrain, 2004.
[18] Mellit A., Benghanem M., Hadj Arab A. and
A. Guessoum, “Modeling of sizing the
photovoltaic system parameters using
artificial neural network”. Proc. of IEEE,
CCA, Istanbul, Vol:1, pp.353-357, 2003.
[19] Mellit A., Benghanem M., Hadj Arab A. and
Guessoum A., “Identification and modelling
of the optimal sizing combination of standalone
photovoltaic systems using the radial
basis function networks”. Proceedings of
WREC VIII, Denver, USA. August 31,
September 3, 2004 on CD-ROM.
[20] Mellit A., Benghanem M., Hadj Arab A.,
Guessoum A.and Moulai K., “Neural
Network Adaptive Wavelets for Sizing of
Stand-Alone Photovoltaic Systems”, Second
IEEE International Conference on
Intelligent Systems Vol: 1, pp.365-370,
2004.
[21] Mellit A., Benghanem M., Hadj Arab A.,
and Guessoum A., “An adaptive artificial
neural network model for sizing of standalone
photovoltaic system: Application for
isolated sites in Algeria”. Renewable
Energy, Vol:80, No:10, pp.1501-1524, 2005.
[22] Mellit A., Benghanem M., Hadj Arab A. and
Guessoum A., “An adaptive Wavenet model
for sizing of stand-alone Photovoltaic
system”, Proceedings of IEEE, ICM,
Istanbul,: pp.1-6, 2004.
[23]Hontoria L. Aguilera J. and Zufiria P. An
application of the multilayer perceptron:
Solar radiation maps in Spain” Solar
Energy, 2005; Vol: 78, pp.313-319, 2005.
[24] Mellit A. and Kalogirou S.A., “Application
of neural networks and genetic algorithms
for predicting the optimal sizing coefficient
of photovoltaic supply (PVS) systems”. In
World Renewable Energy Congress IX 19-
25 August 2006 Florence, Italy.(on CDROM).
[25] Mellit A., Benghanem M., Hadj Arab A.,
and Guessoum A., “A simplified model for
generating sequence of daily global solar
radiation data: using artificial neural
network and a library of Markov transition
matrices”, Solar Energy, Vol:79, No.5,
pp.468-482. 2005.
[26]Aguiar R.J. Collares-Perrira M. and Conde
J.P. “Simple procedure for generating
sequences of daily radiation values using
library of Markov transition matrices”, Solar
Energy; Vol:40, pp.269-279, 1988.
[27] Holland J.H., “Adaptive in neural and
artificial systems”, University of Michigan
Press, Ann Arbor, 1975.
Sizing Of A Stand-Alone Photovoltaic System Based On Neural Networks And Genetic Algorithms:
Application For Remote Areas
Adel MELLIT
469
[28] [28] Kalogirou S.A, “Artificial neural
networks in renewable energy systems
applications: a review”. Renewable and
Sustainable Energy Reviews, Vol:5, pp.373-
401. 2001.
[29] [29] Haykin S., Neural networks. A
comprehensive foundation, IEEE press,
MacMillan, NewYork. 1994.
[30] [30] Hagan M. T. and Menhaj M.,
“Training feedforward networks with the
Marquardt algorithm”, IEEE Transactions
on Neural Networks,;Vol:5,No:6, pp.989-
993, 1994.Press, Available online 30 June
2006.
Adel Mellit, was born at 21-july-1974, (H. Dey, Algiers), Algeria. He received his B.Elect.
Eng. (Hons) from University of Blida in 1997 and MSc in Electronics option Renewable
Energy from University of Science technologies Algiers in 2001 and PhD in Electronics
option Renewable Energy from University of Science technologies Algiers in 2006. His
research interest includes: Application of the Artificial intelligence techniques (Neural
networks, Fuzzy sets, Genetic Algorithm, Neuro-fuzzy, Wavelet, Wavenet, Fuzzy-wavelet)
in Photovoltaic power supply system, modelling, control, prediction, fault diagnostic,
supervision, optimization. He has authored and co-authored more then 30 technical papers in
international journals and conferences. To date, he received more than 10 citations from his
works. He is a Member of JP Wavelet Journal and WSEAS. He is now an assistant professor
at CUYFM, and USDB Algeria.

Thank you for copying data from http://www.arastirmax.com