Estimation of Solar Radiation Based on Meteorological Data Using Artificial Neural Network (ANN)

Abstract

The most important factor determining the production potential of photovoltaic (PV) systems is the amount of solar radiation they are exposed to. Meteorological events occurring in the atmosphere have a significant effect on the solar radiation that the PV system will be exposed to.In this study, In this study; Estimation methodology based on Artificial Neural Network (ANN) application for determining the amount of solar radiation depanding on meteorological measurements has been presented. Meteorological dataset served as an open access by IEEE PES and measured between 1 January 2015 and 30 May 2015 from the weather station of the Porto Higher Engineering Institute (ISEP) / Porto Polytechnic Institute have been used for analysis. ANN structure is modeled as the feed forward ANN topology using Matlab. Actual measurement and solar irradiance estimation values obtained with the presented approach have been compared and evaluated as statistically. In addition, analysis values have been reviewed and compaired with the global solar radiation calculated as the theoretica. Results show that ANN estimation based on meteorological data can be used with 99% accuracy in sunny and clear weather conditions and 96% in rainy and cloudy weather conditions in determining the amount of solar radiation. The presented approach can be used to determine the generation potential of existing and planned PV plants.

Keywords

• Solar Radiation
• Artificial Neural Network (ANN)
• Meteorological Measurement
• Daily Solar Radiation

Yapay Sinir Ağı (YSA) Kullanılarak Meteorolojik Verilere Dayalı Solar Radyasyon tahmini

Abstract

Fotovoltaik(PV) sistemlerin üretim potansiyelini belirleyen en önemli faktör maruz kaldıkları solar radyasyon miktarıdır. Atmosferde meydana gelen meteorolojik olaylar PV sistemin maruz kalacağı solar radyasyon üzerinde önemli bir etki oluşturmaktadır. Bu çalışmada; meteorolojik ölçümlere bağlı olarak solar radyasyon miktarının belirlenmesi için Yapay Sinir Ağı (YSA) uygulamasına dayalı tahmin metodolojisi sunulmuştur. Analizde, IEEE PES tarafından açık erişim olarak sunulan ve Porto Yüksek Mühendislik Enstitüsü (ISEP)/Porto Politeknik Enstitüsü’ ne ait hava istasyonundan 1 Ocak 2015-30 Mayıs 2015 tarihleri aralığında ölçülen meteorolojik veriler kullanılmıştır. YSA yapısı ileri beslemeli YSA topolojisi kullanılarak Matlab ortamında modellenmiştir. Sunulan yaklaşım ile elde edilen solar radyasyon tahmin değerleri, gerçek ölçüm sonuçları karşılaştırılmış ve istatistiksel olarak değerlendirilmiştir. Ayrıca analiz değerleri, teorik olarak hesaplanan global solar radyasyon modeli ile kıyaslanarak yorumlanmıştır. Sonuçlar Solar radyasyon miktarının belirlenmesinde meteorolojik verilere dayalı olarak gerçekleştirilen YSA tahminin güneşli ve açık hava koşullarında %99, yağışlı ve bulutlu hava koşullarında ise %96 doğrulukla kullanılabileceğini göstermektedir. Sunulan yaklaşım, mevcut ve kurulması planlanan PV tesislerin üretim potansiyelinin belirlenmesinde kullanılabilir.

Keywords

• Yapay Sinir Ağı (YSA)
• Solar Radyasyon
• Meteorolojik Ölçüm
• Günlük Solar Radyasyon

References

1. [1] Reis, R.J.D., Tiba, C., 2012, Atlas soalrimetrico de minas gerais-vol. ii, Companhia Energetica de Minas Gerais. [Online]. Available: http://www.cemig.org.br/A_Cemig_e_o_Futuro/inovacao/Alternativas_Energeticas/Documents/atlas_solarimetrico.pdf.
2. [2] Fröhlich, C. 2012. Total Solar Irradiance Observations, Surveys in Geophysics, Vol. 33, 453-473.
3. [3] BP Statistical Review of World Energy June 2019; http://www.bp.com/statisticalreview
4. [4] Gosumbonggot, J., Nguyen, D., Fujita, G. 2018. Partial Shading and Global Maximum Power Point Detections Enhancing MPPT for Photovoltaic System Operated in Shading Condition. 53rd International Universities Power Engineering Conference (UPEC), Glasgow-UK, 4-7 September.
5. [5] Ishaque, H., Salam, Z., Amjad, M., and Mekhilef, S. 2012. An Improved Particle Swarm Optimization (PSO)-Based MPPT for PV with Reduced Steady-State Oscillation. IEEE Transaction on Power Electronics, Vol. 27, No. 8.
6. [6] Rezk, H., 2016,A compherensive sizing methodology for stand-alone battery-less photovoltaic water pumping system under the Egyptian climate, J. Cogent Eng. 3.
7. [7] Rezk, H., Dousoky, G.M., 2016. Technical and economical analysis of different configurations of stand-alone hybrid renewable power system-A case study. Reneawable Sustainable Energy Rev. Vol. 62, pp. 941-953.
8. [8] Akgül, K., Cikan, M., Demirdelen, T., Tumay, M., 2019. Butterfly optimization algorithm based maximum power point tracking of photovoltaic systems under partial shading condition, Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, DOI:10.1080/15567036.2019.1677818.

9. [9] Angstrom, A., 1924. Solar and terrestrial radiation. Roy. Met. Soc., vol. 50, pp. 121-127.
10. [10] Prescott, J. A., 1940. Evaporation from a Water Surface in Relation to Solar Radiation. Trans. R. Soc. S. Austr., Vol. 64, pp. 114-118.
11. [11] Hourmitz, B., 1945. Insolation in relation to cloudiness and cloud density. J. Met., Vol. 2, pp. 154-156.
12. [12]Daneshyar, M., 1978. Solar radiation statistics for iran. Solar Energy, Vol. 21, pp. 345-349.
13. [13] Davies, J., Abdel-Wahab, A., andMekay, D., 1984. Estimating solar irradiance on horizontal surface. Int. J. Sol. Energy, Vol. 2, pp. 405.
14. [14] Abdel-Wahab M., 1985. Simple model for estimation of global solar radiation. Solar and Wind Technology, Vol. 2, no. 1, pp. 69-71.
15. [15] Srivastava, S. K., Sinoh, O. P., and Pandy, G. N. 1993. Estimation of global solar radiation in uttar pradesh (india) and comparison of some existing correlations. Solar Energy, Vol. 51, No. 1, pp. 27-29.
16. [16] Abdel-Wahab, M., 1993. New approach to estimate angstrom coefficient. Solar Energy, Vol. 51, pp. 241-245.
17. [17] El-Shazly, S. M., 1994. Solar radiation component at Qena-Egypt. DOJARAS Quart J. Hungarian Meteorol. Service, Vol. 101, pp. 215-231.
18. [18] Bodescu, V. 1997. Verification of some very simple clear and cloudy sky models to evaluate global solar irradiance. Solar Energy, Vol. 61, No 4, pp. 251-264.
19. [19] Khalil S. A. and Fathy. A. M. 2008. An empirical method for estimating global solar radiation over Egypt. Acta Polytechnica, Vol. 48, no. 5, pp. 48-53.
20. [20] El‐Nouby Adam, M. 2010. Effect of stratospheric ozone in uvb solar radiation reaching the earth's surface at qena, egypt. Atmospheric Pollution Research, vol. 1, pp. 155-160.
21. [21] Mekhtoup, F.B.S. 2014. PV cell temperature/PV output Relationships Homer Methodology Calculation, Ipco, Vol. 2, No. 1, pp. 1-12.
22. [22] Moh. Zaenal Efendi, Farid Dwi Murdianto, Rengga Eka Setiawan. 2017. Modelling and Simuşation of MPTT Sepic Converter Using Modified PSO to Owercome Partial Shading Impact on DC Microgrid System. International Electronics Symposium on Engineering Technology and Application (IES-ETA).
23. [23] Bora. B., Gupta. K., Kumar, A., Renu, O.S., Dahiya, R. 2013. Artificial Neural Network based Modelling of PV Module to Predict the output. 4th International Conference on Advances in Energy Researchhe, held at IIT Bombay.
24. [24] Ceylan, I., Erkaymaz, E., Gedik, E., Gurel, A.E. 2014. The prediction of photovoltaic module temperature with artificial neural network. Case Study Therm. Eng., Vol. 3, pp. 11-20.
25. [25] Priya, S.S., Iqbal, M.H. 2015. Solar irrradiance predicrtion using Artificial Neural Network. International Journal of Computer Application, Vol. 116, No.16, pp. 28-31.
26. [26] Benghanem, A.M., Mellit, A., Alamri, S.N. 2009. ANN-based modelling and estimation of daily global solar radiation data: A case study. Energy Convers. Management System, Vol. 50, No. 7, pp.1644-1655.
27. [27] Behrang, M.A., Assareh, E., Ghanbarzadeh, A., Noghrehabadi, A.R.. 2018. The potetial of different artificial neural network (ANN) techniques in daily global solar radiation modelling, IOP Conf. Series: Journal of Physics: Conf. Series 1049-012088, 2018, doi:10.1088/17426596/1049/1/012088.
28. [28] Elizondo, D., Hoogenboom, G., Mcclendon,R.W.1994.Developme-nt of Neural network model to predict daily solar radiation, Agric Forest Meteorol, Vol. 71, pp. 115-132.
29. [29] Williams, B.D., Zazueta, F.S.. 1994. Solar radiation estimation via neural network, In: ASAE, editör, Sixth International Conference on computer in agriculture, Cancun, Mexico.
30. [30] Mohandes, M., Rehman, S., Halawani, T.O. 1998. Estimation of global solar radiation using artificial neural networks, Renew Energy, Vol. 14. pp. 179-184.
31. [31] Hontoria, L., Riesco, J., Zufuia, P., Aguilera, J. 2000. Application of neural networks in solar radiation fields, Obteinment of solar radiation maps. In 16th European photovoltaic for cemical engineers, Vol. 3, pp. 385-408.
32. [32] Tymvios, F.S., Jacovides, CP., Michaelides, S.C., Scouteli, C. 2005. Comporative study of Angstroms and artificial neural netwoks methodologies in estimating global solar radiaion, Solar Energy, Vol. 78, pp. 752-762.
33. [33] Alam, S., Kaushik, S.C., Garg, S.N. 2006. Computation of beam solar radiation at normal incidence using artificial neural network, Renew Energy, Vol. 31, Issue. 10, Pages 1483-1491.
34. [34] Elminir, H.K., Azzam, Y.A., Younes, F.I. 2007. Prediction of hourly and daily diffuse fraction using neural network, as compared to linear regression models. Energy, Vol. 32(8), pp. 1532-1523.
35. [35] Mubiru, E.J., Banka, K.B. 2008. Estimation of monthly average daily global solar irradiation using arificial neural networks, Solar Energy, Vol. 82(2), pp. 181-187.
36. [36] Basheer I.A., Hajmeer M. 2000. Artificial neural networks: fundamentals, computing, design, and Application,Journal of Microbiological Methods, 43: 3-31.
37. [37] Graupe D. 2007. Princıples of artificial neural networks, (2nd Edition), advanced series on circuits and systems, 6, World Scientific Publishing Co. Pte. Ltd.
38. [38] https://site.ieee.org/pes-iss/data-sets/#weat, Weather data/Porto, Portugal, Weather Station ISEP/IPP.
39. [39] Khatip, T., Mohammed, A., Mohmoud, M., Sopain, K. 2012. Estimating Global Solar Energy Using Multilayer Perception Artificial Neural Network, International Journal of Energy, Issue 1, Vol. 6, pp. 25-33.
40. [40] Khatip, T., Elmenreich, W. 2016. Modelling of Photovoltaic Systems Using Matlab, John Willey & Sons, Inc, p. 3.
41. [41] Basheer I.A., Hajmeer M. 2000. Artificial neural networks: fundamentals, computing, design, and Application,Journal of Microbiological Methods, 43: 3-31.
42. [42] Graupe D. 2007. Princıples of artificial neural networks, (2nd Edition), advanced series on circuits and systems, 6, World Scientific Publishing Co. Pte. Ltd.
43. [43] Cho V.A. 2003. Comparison of three different approaches to tourist arrival forecasting, Tourism Management, 24: 323-330.
44. [44] Wang, X., Xu, D.L., Sun, Z.Z.. 2018. Estimates of energy consumption in China using a self-adaptive multi-verse optimizer-based support vector machine with rolling cross-validation, Energy Vol. 152 539–548.
45. [45] Kankal, M., Akpinar, A., Komurcu, M.I., Ozsahin. T.S. 2011. Modeling and forecasting of Turkey’s energy consumption using socio–economic and demographic variables, Applied Energy Vol 88. pp. 1927–1939.
46. [46] Uzlu, E., Akpınar, A., Öztürk, H.T., Nacar, S., Kankal, M. 2014. Estimates of hydroelectric generation using neural networks with artificial bee colony algorithm for Turkey, Energy 69 (2014) 638–647.
47. [47] Kankal, M., Uzlu, E. 2017. Neural network approach with teaching-learning-based optimization for modeling and forecasting long-term electric energy demand in Turkey, Neural Computing and Applications 28 (2017) 737–747.
48. [48] Sinecen, M., Kaya, B. , Yıldız, Ö. 2017. Aydın ilinde insan sağlığını birincil dereceden etkileyen hava değişkenlerine yönelik yapay sinir ağı tabanlı erken uyarı modeli, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji 5(4) ss. 121–131.
49. [49] Kandıran, E. , Hacınlıyan, A., 2019, Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System, AJIT-e: Online Academic Journal of Information Technology 2019 Bahar/Spring – Cilt/Vol:10‐Sayı/Num:37DOI: 10.5824/1309‐1581.2019.2.002.x