MLP Back Propagation Artificial Neural Network for Solar Resource Forecasting in Equatorial Areas Marcello Anderson F. B. Lima, Paulo C. M. Carvalho, Arthur P. de S. Braga, Luis M. Fernández Ramírez, Josileudo R. Leite 2018/04/20

Abstract

Renewable energy (RE) resources such as solar are increasingly being used worldwide. Solar resource shows high availability, but presents an intermittent characteristic, causing oscillations in the electricity production. Intermittence is one of the main barriers for the use of solar plants in a system that needs to balance demand and electricity production. Aiming to contribute to a larger use of the solar resource in the world energy matrix, we propose a solar irradiance prediction methodology, developed from data collected in Fortaleza-CE (latitude: -03° 43+, longitude: -38° 32+). Predictions were developed using Multilayer Perceptron (MLP) Back propagation Artificial Neural Network (ANN) with the advance of 1 hour. In the best ANN performance, 41.9% of the predictions obtained up to 5% of error, 58.7% obtained errors lower than 10% and 68.6% obtained errors lower than 15%. MAPE (mean absolute percentage error) of 6.11% was found, which can be considered good, since errors found in previous works reached 20%.

Authors and affiliations

Marcello Anderson F. B. Lima(1), Paulo C. M. Carvalho(1), Arthur P. de S. Braga(1), Luis M. Fernández Ramírez(2), Josileudo R. Leite(3)
1. Department of Electrical Engineering. Federal University of Ceara – UFC. Campus Pici, Ceará (Brazil)
2. Department of Electrical Engineering. University of Cadiz – UCA. Escuela Politécnica Superior de Algeciras, Cádiz (Spain)
3. Department of Industrial Mechatronics. Federal Institute of Education, Science and Technology – IFCE. Campus Limoeiro do Norte, Ceará (Brazil)

Key words

Solar Predictability, Solar Energy, Artificial Neural Networks.

References

[1] UN - Department of Economic and Social Affairs, Population Division, “World Population Prospects: The 2017 Revision, Key Findings and Advance Tables”, New York (2017), pp. 1-8.
[2] IEA, “KEY WORLD ENERGY STATISTICS”, Paris (2016), pp. 26-35.
[3] REN 21, “Renewables 2017: Global Status Report.” Paris (2017), pp.21-27.
[4] MME, “Plano Decenal de Expansão de Energia 2024”, Brasília (2015), pp.408-411.
[5] M. A. B. F. Lima, “Teoria do Portfólio Aplicada à Previsão de Recursos Solar e Eólico”. UFC, Fortaleza (2016).
[6] M. A. B. F. Lima, P. C. M. Carvalho, T. C. Carneiro, et al, “Portfolio theory applied to solar and Wind Resources
Forecast”, IET Renewable Power Generation, Vol. 11, Issue 7, June 2017, p. 973 – 978.
[7] V. Speth, “Wind and solar portfolios and their impact on predictability German case study 2010-2011”. In Proc.
12th wind integration workshop, London, UK, October 2013, pp. 1–6.
[8] S. O. Haykin, “Neural Networks and Learning Machines”, Pearson, New Jersey (2008), pp.1-930.
[9] S. Haykin, “Neural Networks: A Comprehensive Foundation, Prentice Hall, New Jersey (1999), pp.1-897.
[10] C. D. Dumitru, A. Gligor, C. Enachescu, “Solar Photovoltaic Energy Production Forecast Using Neural Networks”, Procedia Technology, Elsevier, Vol. 22, February 2016, pp. 808-815.
[11] M. G. Giorgi, P. M. de Congedo, M. Malvoni, M. 2013.“Photovoltaic power forecasting using statistical methods:
impact of weather data. IET Science, Measurement and Technology”, Vol. 8, Issue 3, May 2014, p. 90 – 97.
[12] S. Kumar, T. Kaur, “Development of ANN Based Model for Solar Potential Assessment Using Various Meteorological Parameters”, Energy Procedia, Elsevier, Vol. 90, December 2016, pp. 587-592.
[13] V. N. Vapnik, “Statistical Learning Theory”, Wiley, New York (1998), pp.1-760.
[14] K. P. Moustris, K. A. Kavvadias, A. I. Kokkosis, A. G Paliatsos, “One day-ahead forecasting of mean hourly global solar irradiation for energy management systems purposes using artificial neural network modeling”. In Proc. Power Generation, Transmission, Distribution and Energy Conversion (MedPower 2016), pp.1-6.
[15] M. Vakili, S. Reza S. Yazdib, K. Kalhor. “Using Artificial Neural Networks for Prediction of Global Solar Radiation
in Tehran Considering Particulate Matter Air Pollution”. Energy Procedia, Elsevier, Vol. 74, August 2015, pp. 1205-1212.
[16] Y. Zhang, M. Beaudin, “Day-Ahead Power Output Forecasting for Small-Scale Solar PhotovoltaicElectricity
Generators”, IEEE Transactions on smart grid. Vol. 6, Issue 5, September 2015, pp. 2253 – 2262.
[17] C. M. Huang, S. J. Chen, S. P. Yang, C. J. Kuo, “One day ahead hourly forecasting for photovoltaic power generation using an intelligent method with weather-based forecasting models”, IET Generation, Transmission e Distribuition, Vol. 9, Issue 14, November 2015, p. 1874 –1882.
[18] C. Yan, J. Xiu, C. Liu, Z. Yang, “A High Concentrated Photovoltaic Output Power Predictive Model Based on Fuzzy Clustering and RBF Neural Network”, Proceedings of CCIS2014, (2014), pp. 384-388.
[19] H. T. C. Pedro, C. F. M. Coimbra “Assessment of forecasting techniques for solar power production with no exogenous inputs”. Solar Energy, Elsevier, Vol. 86, Issue 7, July 2012, pp. 2017-2028.
[20] P. Neelamegam, V. A. Amirtham, “Prediction of solar radiation for solar systems by using ANN models with different backpropagation algorithms”, Journal of Applied Research and Technology, Elsevier, Vol. 14, Issue 3, June 2016, pp. 206-214.
[21] F. Grimaccia, S. Leva, M. Mussetta, E. Ogliari, “ANN Sizing Procedure for the Day-Ahead Output Power Forecast of a PV Plant” Applied Sciences, MDPI, Vol. 7, Issue 6, June 2017, pp. 622-635.