Optimization of Neurons Number in Artificial Neural Network Model for Predicting the Power Production of PV Module

Hussain Hamdi Khalaf; Ali Nasser Hussain; Zuhair S. Al-Sagar; Abdulrahman Th. Mohammad; Hilal A. Fadhil

doi:10.51173/jt.v6i1.895

Authors

Hussain Hamdi Khalaf Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq.
Ali Nasser Hussain Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq.
Zuhair S. Al-Sagar Technical Institute / Baquba, Middle Technical University, Baghdad, Iraq.
Abdulrahman Th. Mohammad Technical Institute / Baquba, Middle Technical University, Baghdad, Iraq.
Hilal A. Fadhil Electrical and Computer Engineering Faculty, Sohar University, Sohar, Sultanate of Oman

DOI:

https://doi.org/10.51173/jt.v6i1.895

Keywords:

ANN, PV Module, Power Generation, Single Hidden Layer, Neurons

Abstract

In this work, an Artificial Neural Network (ANN) with a backward-propagation technique was used to predict the power generation of the Photovoltaic (PV) module in weather conditions of Baghdad city-Iraq. Experiment tests were investigated in the summer of 2022. Three weather parameters, including: (solar radiation, ambient temperature, and wind speed), the output electrical characteristics of the PV module (voltage, current, power), and module temperature (were measured. Therefore, the dataset of the ANN system consists of four input and one output parameter. Furthermore, the structure of ANN includes a single hidden layer with a backward propagation technique. The main goal of this study was to optimize the number of neurons in the training process. The evaluation of the ANN model depended on the determination coefficient (R) and Root Mean Squared Error (RMSE). The obtained results show that the architecture of ANN is appropriate for predicting the power generated from the PV module. The developed ANN model has good accuracy. Where the MSE is 0.002747 at epoch 9 in the model. Furthermore, the R is recorded as 0.99078, 0.98254, 0.99125, and 0.99005 for training, testing, validation, and all respectively in the proposed model. In addition, the optimization number of neurons in the hidden layer gave sufficient accuracy without referring to the choice of the number of neurons by using the trial-and-error method that most researchers relied.

Downloads

Download data is not yet available.

Author Biographies

Hussain Hamdi Khalaf, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq.

Hilal A. Fadhil, Electrical and Computer Engineering Faculty, Sohar University, Sohar, Sultanate of Oman

References

M. Chowdhury et al., "Current trends and prospects of tidal energy technology," vol. 23, no. 6, pp. 8179-8194, 2021, https://doi.org/10.1007/s10668-020-01013-4.

S. Ogawa and H. J. I.-P. Mori, "Integration of deep Boltzmann machine and generalized radial basis function network for photovoltaic generation output forecasting," vol. 53, no. 2, pp. 12163-12168, 2020, https://doi.org/10.1016/j.ifacol.2020.12.998.

O. Dupré, R. Vaillon, and M. A. J. I. J. o. P. Green, "Experimental assessment of temperature coefficient theories for silicon solar cells," vol. 6, no. 1, pp. 56-60, 2015, https://doi.org/10.1109/JPHOTOV.2015.2489864.

A. K. Tripathi, S. Ray, M. Aruna, and S. J. M. T. P. Prasad, "Evaluation of solar PV panel performance under humid atmosphere," vol. 45, pp. 5916-5920, 2021, https://doi.org/10.1016/j.matpr.2020.08.775.

X. Chen, B. Xu, C. Mei, Y. Ding, and K. J. A. e. Li, "Teaching–learning–based artificial bee colony for solar photovoltaic parameter estimation," vol. 212, pp. 1578-1588, 2018, https://doi.org/10.1016/j.apenergy.2017.12.115.

M. Abuella and B. Chowdhury, "Solar power probabilistic forecasting by using multiple linear regression analysis," in SoutheastCon 2015, 2015, pp. 1-5: IEEE, https://doi.org/10.1109/SECON.2015.7132869.

R. Darbali-Zamora, C. J. Gómez-Mendez, E. I. Ortiz-Rivera, H. Li, and J. Wang, "Solar irradiance prediction model based on a statistical approach for microgrid applications," in 2015 IEEE 42nd Photovoltaic Specialist Conference (PVSC), 2015, pp. 1-6: IEEE, https://doi.org/10.1109/PVSC.2015.7356006.

A. Saberian, H. Hizam, M. Radzi, M. Ab Kadir, and M. J. I. j. o. P. Mirzaei, "Modelling and prediction of photovoltaic power output using artificial neural networks," vol. 2014, 2014, https://doi.org/10.1155/2014/469701.

X. Shao, S. Lu, and H. F. Hamann, "Solar radiation forecast with machine learning," in 2016 23rd International Workshop on Active-Matrix Flatpanel Displays and Devices (AM-FPD), 2016, pp. 19-22: IEEE. https://doi.org/10.1109/AM-FPD.2016.7543604.

T. T. K. Tran, S. M. Bateni, S. J. Ki, and H. J. W. Vosoughifar, "A review of neural networks for air temperature forecasting," vol. 13, no. 9, p. 1294, 2021, https://doi.org/10.3390/w13091294.

S. Sobri, S. Koohi-Kamali, N. A. J. E. c. Rahim, and management, "Solar photovoltaic generation forecasting methods: A review," vol. 156, pp. 459-497, 2018, https://doi.org/10.1016/j.enconman.2017.11.019.

L. Wen, K. Zhou, S. Yang, and X. J. E. Lu, "Optimal load dispatch of community microgrid with deep learning based solar power and load forecasting," vol. 171, pp. 1053-1065, 2019, https://doi.org/10.1016/j.energy.2019.01.075.

M. Moreira, P. Balestrassi, A. Paiva, P. Ribeiro, B. J. R. Bonatto, and S. E. Reviews, "Design of experiments using artificial neural network ensemble for photovoltaic generation forecasting," vol. 135, p. 110450, 2021, https://doi.org/10.1016/j.rser.2020.110450.

M. Fathi and J. A. J. E. R. Parian, "Intelligent MPPT for photovoltaic panels using a novel fuzzy logic and artificial neural networks based on evolutionary algorithms," vol. 7, pp. 1338-1348, 2021, https://doi.org/10.1016/j.egyr.2021.02.051.

S. S. Refaat, O. H. Abu-Rub, and H. Nounou, "ANN based prognostication of the PV panel output power under various environmental conditions," in 2018 IEEE Texas Power and Energy Conference (TPEC), 2018, pp. 1-6: IEEE, https://doi.org/10.1109/TPEC.2018.8312051.

N. M. M. Fahmi, N. A. Zambri, N. Salim, S. S. J. J. o. A. I. T. Yi, and Application, "Power Forecasting from Solar Panels Using Artificial Neural Network in UTHM Parit Raja," vol. 2, no. 1, pp. 18-27, 2021.

R. S. Hadi and O. F. J. A. o. A. U. J. o. E. S. Abdulateef, "Modeling and Prediction of Photovoltaic Power Output Using Artificial Neural Networks Considering Ambient Conditions," vol. 25, no. 5, pp. 623-638, 2018.

I. Kayri, M. T. J. N. C. Gencoglu, and Applications, "Predicting power production from a photovoltaic panel through artificial neural networks using atmospheric indicators," vol. 31, no. 8, pp. 3573-3586, 2019, https://doi.org/10.1007/s00521-017-3271-6.

F. J. Pontes, A. P. De Paiva, P. P. Balestrassi, J. R. Ferreira, and M. B. J. E. S. w. A. Da Silva, "Optimization of Radial Basis Function neural network employed for prediction of surface roughness in hard turning process using Taguchi’s orthogonal arrays," vol. 39, no. 9, pp. 7776-7787, 2012, https://doi.org/10.1016/j.eswa.2012.01.058.

S. Sunder, V. J. I. J. o. I. Yadava, and S. Engineering, "Modelling and optimisation of material removal rate and surface roughness in surface-electrical discharge diamond grinding process," vol. 17, no. 2, pp. 133-151, 2014.

B. Yegnanarayana, Artificial neural networks. PHI Learning Pvt. Ltd., 2009.

M. M. K. E. A. Abdulrazzaq and H. Agha, "Developing Artificial Neural Network and Multiple Linear Regression Models to Predict the Ultimate Load Carrying Capacity of Reactive Powder Concrete Columns."

A. M. Zain, H. Haron, S. N. Qasem, and S. J. A. M. M. Sharif, "Regression and ANN models for estimating minimum value of machining performance," vol. 36, no. 4, pp. 1477-1492, 2012, https://doi.org/10.1016/j.apm.2011.09.035.

M. H. Ahmadi et al., "Evaluation of electrical efficiency of photovoltaic thermal solar collector," vol. 14, no. 1, pp. 545-565, 2020, https://doi.org/10.1080/19942060.2020.1734094.

V. Agarwal, V. Singh, P. Gaur, and R. Agarwal, "PV Output forecasting based on weather classification, SVM and ANN," 2022, https://nopr.niscpr.res.in/handle/123456789/59745.