Forecasting Photovoltaic Energy Generation using Multilayer Perceptron Neural Network Model

Kafayat Adeyemi, Victor Eniola, Musa Tanko Zarmai, Muhammad Uthman, Godwin Mong Kalu-Uka, Eli Jidere Bala

Abstract


Solar power grid integration has increased tremendously in the global electricity market. However, further increase in solar power grid integration has been restricted by the intermittent nature of solar energy supply. For this reason, researchers have developed different mathematical models which could predict the available solar energy radiation and the actual solar photovoltaic energy generated at a given location. Hence, the present study proposes a novel (enhanced multilayer perceptron neural network, MLPNN) model for predicting the daily solar energy generated by a 1.2 MW PV power plant. The stability of the MLPNN model was compared with results obtained from the multiple nonlinear regression (MNR) model and the generalized regression neural network (GRNN) model. The results showed that the enhanced MLPNN model outpaced the MNR and the GRNN models by presenting the lowest normalized root mean square error (nRMSE), the lowest minimum absolute percentage error (MAPE), and the best coefficient of determination (RSQ) for both the rainy [6.09, 5.93, 93.53]% and the dry [6.12, 4.16, 90.77]% seasons, respectively.


Keywords


Photovoltaic, energy, forecasting, artificial neural network, data-preprocessing.

Full Text:

PDF

References


A. Zaaoumi, A. Bah, M. Ciocan, P. Sebastian, M. Balan, A. Mechaqrane, and M. Alaoui, "Estimation of the energy production of a parabolic trough solar thermal power plant using analytical and artificial neural networks models", Renewable Energy, vol. 170, pp. 620-638, 2021.

I. Jebli, F. Belouadha, M. L. Kabbaj, and A. Tilioua, "Prediction of solar energy guided by pearson correlation using machine learning", Energy, vol. 224, pp. 120109, 2021.

N. Basurto, Á. Arroyo, R. Vega, H. Quintián, J. Calvo-Rolle, and Á. Herrero, "A Hybrid Intelligent System to forecast solar energy production", Computers & Electrical Engineering, vol. 78, pp. 373-387, 2019.

H. Lan, C. Zhang, Y. Hong, Y. He, and S. Wen, "Day-ahead spatiotemporal solar irradiation forecasting using frequency-based hybrid principal component analysis and neural network", Applied Energy, vol. 247, pp. 389-402, 2019.

R. Azimi, M. Ghayekhloo, and M. Ghofrani, "A hybrid method based on a new clustering technique and multilayer perceptron neural networks for hourly solar radiation forecasting", Energy Conversion and Management, vol. 118, pp. 331-344, 2016.

Cannizzaro, D., Aliberti, A., Bottaccioli, L., Macii, E., Acquaviva, A. and Patti, E., "Solar radiation forecasting based on convolutional neural network and ensemble learning", Expert Systems with Applications, vol. 181, pp. 115167, 2021.

Wang, S., Zhang, Y., Zhang, C. and Yang, M., "Improved artificial neural network method for predicting photovoltaic output performance", Global Energy Interconnection, vol. 3(6), pp. 553-561, 2020.

M. Raza, N. Mithulananthan, and A. Summerfield, "Solar output power forecast using an ensemble framework with neural predictors and Bayesian adaptive combination", Solar Energy, vol. 166, pp. 226-241, 2018.

Z. Yang, M. Mourshed, K. Liu, X. Xu, and S. Feng, "A novel competitive swarm optimized RBF neural network model for short-term solar power generation forecasting", Neurocomputing, vol. 397, pp. 415-421, 2020.

L. Liu, D. Liu, Q. Sun, H. Li, and R. Wennersten, "Forecasting Power Output of Photovoltaic System Using A BP Network Method", Energy Procedia, vol. 142, pp. 780-786, 2017.

N. Nguyen, L. D. Bui, B. Doan, E. Sanseverino, D. Cara, and Q. Nguyen, "A new method for forecasting energy output of a large-scale solar power plant based on long short-term memory networks a case study in Vietnam", Electric Power Systems Research, vol. 199, pp. 107427, 2021.

A. Di Piazza, M. C. Di Piazza, G. La Tona, and M. Luna, "An artificial neural network-based forecasting model of energy-related time series for electrical grid management", Mathematics and Computers in Simulation, vol. 184, pp. 294-305, 2021.

M. Mansoor, F. Grimaccia, S. Leva, and M. Mussetta, "Comparison of echo state network and feed-forward neural networks in electrical load forecasting for demand response programs", Mathematics and Computers in Simulation, vol. 184, pp. 282-293, 2021.

J. Zhong, L. Liu, Q. Sun, and X. Wang, "Prediction of Photovoltaic Power Generation Based on General Regression and Back Propagation Neural Network", Energy Procedia, vol. 152, pp. 1224-1229, 2018.

J. Liu, L. Wang, X. Guo, Q. Yang, and W. Yan, "Pattern recognition based photovoltaic power forecast using generalized regression neural network", 2017 Chinese Automation Congress (CAC), pp. 4114-4118, 2017.

Z. Pang, F. Niu, and Z. O’Neill, "Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons", Renewable Energy, vol. 156, pp. 279-289, 2020.

M. Colak, M. Yesilbudak, and R. Bayindir, "Forecasting of Daily Total Horizontal Solar Radiation Using Grey Wolf Optimizer and Multilayer Perceptron Algorithms", 2019 8th International Conference on Renewable Energy Research and Applications (ICRERA), pp. 939-942, 2019.

C. Ozoegwu, "Artificial neural network forecast of monthly mean daily global solar radiation of selected locations based on time series and month number", Journal of Cleaner Production, vol. 216, pp. 1-13, 2019.

S. Mohanty, P. Patra, and S. Sahoo, "Prediction of global solar radiation using nonlinear auto regressive network with exogenous inputs (narx)", 2015 39th National Systems Conference (NSC), pp. 1-6, 2015.

A. Elsheikh, S. Sharshir, M. Abd Elaziz, A. Kabeel, W. Guilan, and Z. Haiou, "Modeling of solar energy systems using artificial neural network: A comprehensive review", Solar Energy, vol. 180, pp. 622-639, 2019.




DOI (PDF): https://doi.org/10.20508/ijrer.v12i4.13306.g8599

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is cited in SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics);

IJRER has been cited in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2025; 

h=35,

Average citation per item=6.59

Last three Years Impact Factor=(1947+1753+1586)/(146+201+78)=5286/425=12.43

Category Quartile:Q4