Radial Basis Function for Solar Irradiance Forecasting in Equatorial Areas Marcello Anderson F. B. Lima, Paulo C. M. Carvalho, Arthur P. de S. Braga, Renata I. S. Pereira, Sandro C. S. Jucá, Luis M. Fernández-Ramírez, Josileudo R. Leite   2019/07/15

Abstract

Photovoltaic (PV) solar generation is gaining an increasing attention due to technological advances such as higher efficiency and life of PV cells and cost reduction. Due to its vast territory, Brazil is composed of regions that can explore renewable energy sources for electricity generation, and the solar resource is found satisfactorily in several areas of the country. This article presents a solar irradiance prediction mechanism developed using data collected in Fortaleza-CE, Brazil. Due to the fact of its characteristic of unpredictability for this resource, many researchers look for several methods to take the generation of this type of energy. The predictions were performed using a Radial Basis Function (RBF) a computational model based on the human nervous system, it is a technical and effective for time series forecasting, which is a relatively complex problem, Artificial Neural Network (ANN) with the advancement of 1 hour. In the ANN performance, a total of 34.4% forecasts underestimated solar energy availability, 7% of the forecasts obtained error 0 and 58.6% of forecasts overestimated the solar resource. A total of 62.33% of forecasts was between -10% and 10% of forecast error. The prediction mean error was 5.93% and the Mean Absolute Percentage Error (MAPE) was 11.43%.

Authors and affiliations

Marcello Anderson F. B. Lima1, Paulo C. M. Carvalho1, Arthur P. de S. Braga1, Renata I. S. Pereira1, Sandro C. S. Jucá2, Luis M. Fernández-Ramírez3, Josileudo R. Leite4
1. Department of Electrical Engineering. Federal University of Ceará– UFC. Campus Pici, Ceará (Brazil)
2. Academic Master’s Degree in Renewable Energy (PPGER). Federal Institute of Ceará (IFCE). Maracanaú Campus, Ceará (Brazil)
3. Research Group in Electrical Technologies for Sustainable and Renewable Energy (PAIDI-TEP-023). Department of Electrical Engineering, University of Cadiz (UCA) Escuela Politécnica Superior de Algeciras, Cádiz (Spain)
4. Department of IndustrialMechatronics. Federal Institute of Ceará (IFCE). Limoeiro do Norte Campus, Ceará (Brazil)

Key words

Solar Forecast, Solar Energy, Artificial Neural Network, Radial Base Function.

References

[1] NAÇÕES UNIDAS. “Apesar de baixa fertilidade, mundo terá 9,8 bilhões de pessoas em 2050”, DESENVOLVIMENTO SUSTENTÁVEL. Bruxelas, 22 June 2017. Available at: < https://nacoesunidas.org/apesar-de-baixa-fertilidade-mundo-tera-98-bilhoes-de-pessoas-em-2050/>. Access at: 30 August. 2018.
[2] MINISTÉRIO DE MINAS E ENERGIA – MME (Brasil) “Boletim Mensal de Monitoramento do sistema elétrico brasileiro”, December de 2017, (2017). Available at: <http://www.mme.gov.br/documents/1138781/0/Boletim+de+Monitoramento+do+Sitema+El%C3%A9trico+-+Dezembro+-+2017.pdf/89e16453-fc2e-46fd-b5fd-aa6951daf934>. Access at: 30 August 2018.
[3] ITERNATIONAL ENERGY AGENCY – IEA. “Key world energy statistics 2017”, Paris (2017). Available at: <https://www.iea.org/publications/freepublications/publication/KeyWorld2017.pdf>.Acess at: 30 August 2016.
[4] M. A. F. B. Lima. “The Portifolio Theory applied to the forecasting of solar and wind resources”, Dissertation (Master in Electrical Engineering) - Department of Electrical Engineering, Federal University of Ceará, Fortaleza, (2016).
[5] P. Chaudhary, M. Rizwan, “Energy management supporting high penetration of solar photovoltaic generation for smart grid using solar forecasts and pumped hydro storage system”, Renewable Energy, Elsevier, v.118, April 2018, p. 928-946.
[6] C.B. Martínez-Anido, A. Florita, B. M. Hodge, “The impact of improved solar forecasts on bulk power system operations in ISO-NE”, Technical Report NREL/CP- 5D00-62817. National Renewable Energy Laboratory, Golden, Colorado, (2017).
[7] G. M. Yagli, D. Yang, D. Srinivasan. “Reconciling solar forecasts: Sequential reconciliation”, Solar Energy, Elsevier, v.179, February 2019, p. 391-397.
[8] C. Voyant, G. Notton, S. Kalogirou, et al, “Machine learning methods for solar radiation forecasting: A review”, Renewable Energy, Elsevier, v.105, May 2017, p. 569-582.
[9] M. L. Aguiar, B. Pereira, P. Lauret, et al, “Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting”, Renewable Energy, v.97, november 2016. p. 599-610.
[10] M. David, F. Ramahatana, P. J. Trombe, et al, “Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models”, Solar Energy, Elsevier, v.133, August 2016, p. 55-72.
[11] L. Jiaming, J. K. Ward, J. Tong, et al, “Machine learning for solar irradiance forecasting of photovoltaic system”, Renewable Energy, Elsevier, v.90, May 2016, p. 542-553.
[12] A. T. Eseye, J. Zhang, D. Zheng, “Short-term Photovoltaic Solar Power Forecasting Using a Hybrid Wavelet-PSOSVM Model Based on SCADA and Meteorological Information”, Renewable Energy, Elsevier, v.118, April 2018, p. 357-367.
[13] H. Bouzgou, C. A. Gueymard, “Minimum redundancy – Maximum relevance with extreme learning machines for global solar radiation forecasting: Toward an optimized dimensionality reduction for solar time series”, Solar Energy, Elsevier, v.158, December 2017, p. 595-609.
[14] S. Suna, S.Wanga, G. Zhanga, et al, “A decomposition-clustering-ensemble learning approach for solar radiation forecasting”, Solar Energy, Elsevier, v.163, March 2018, pp. 189-199.
[15] D. Yanga, J. Kleisslb, C. A. Gueymard, et al, “History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining”, Solar Energy, Elsevier, v.168, July 2018, pp. 60-101.
[16] S. Haykin, “Redes Neurais: princípios e prática”, bookman, Porto Alegre (2001), pp.1-902.
[17] M. A. F. B. Lima, P. C. M. Carvalho, A. P. S. Braga, L. M. F. Ramírez, J. R. Leite, “MLP Back Propagation Artificial Neural Network for Solar Resource Forecasting in Equatorial Areas”, Renewable Energy and Power Quality Journal (RE&PQJ), (2018), pp.175-180.
[18] H. Jiang, Y. Dong, J. Wang, et al, “Intelligent optimization models based on hard-ridge penalty and RBF for forecasting global solar radiation”, Energy Conversion and Management, Elsevier, v.95, May 2015, pp. 42-58.
[19] M. Awad, I. Qasrawi, “Enhanced RBF neural network model for time series prediction of solar cells panel depending on climate conditions (temperature and irradiance)”, Neural Computing and Applications, Springer, v.30, September 2018, pp. 1757–1768.
[20] M. Dhimish, V. Holmes, B. Mehrdadi, et al, “Comparing Mamdani Sugeno fuzzy logic and RBF ANN network for PV fault detection”, Energy Conversion and Management, Elsevier, v.95, March 2018, pp. 257-274.
[21] J. G. Kim, D. H. Kim, W. S. Yoo, et al, “Daily prediction of solar power generation based on weather forecast information in Korea”, Renewable Power Generation, IET, v.11, Issue 10, March 2017, p. 1268-1273.
[22] C. M. Huang, S. J. Chen, S. P. Yang, C. J. Kuo, “One day ahead hourly forecasting for photovoltaic powercgeneration using an intelligent method with weather-based forecasting models”, Generation, Transmission e Distribuition, IET, v. 9, Issue 14, November 2015, p. 1874 – 1882.
[23] 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.
[24] A. Alfadda, S. Rahman, M. Pipattanasomporn, “Solar irradiance forecast using aerosols measurements: A data driven approach”, Solar Energy, Elsevier, v. 170, August 2018, pp. 924-939.
[25] M. Q. Raza, N, Mithulananthan, A. Summerfield, “Solar output power forecast using an ensemble framework with neural predictors and Bayesian adaptive combination”, Solar Energy, Elsevier, May. 2018, v.166, p. 236-241.
[26] R. Meenal, A. I. Selvakumar, “Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters”, Solar Energy, Elsevier, June 2018, v.121, p. 324-343.
[27] 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.