EVALUATION OF SEQUENTIAL MINIMAL OPTIMIZATION (SMO) IN ESTIMATING BEAM SOLAR FRACTION AT NORMAL INCIDENCE TRANSMITTED (ktbd).
DOI:
https://doi.org/10.59627/cbens.2016.1908Keywords:
SVM, Insolation Ratio, WEKAAbstract
In this work, the Sequential Minimal Optimization (SMO) algorithm is used to estimate the beam solar fraction at normal incidence transmitted on terrestrial surface (ktbd). The Radial Basis Function (RBF) kernel is used for regression. The statistical model (#M3) is developed and compared with the model (SMO3). The input variable used is the insolation ratio (n / N) [n is the sunshine and N the photoperiod]. 13 years of measurements were used to Botucatu - SP region. Two named database typical year (AT) and atypical year (AAT), selected of the total base of 13, are used to validate the models. In the evaluation of the models were used: Relative Mean Bias Error (rMBE), Relative Root Mean Square Error (rRMSE), percentage relative error (℮) and Willmott index of agreement (d). The SMO3 has better accuracy than the model (#M3). The validation with AT and AAT was satisfactory. Finally, SMO3's performance in the wet and dry season is analyzed to verify the influence of clouds, aerosols and water vapor in the dispersion of estimates and increased in the errors. The SMO estimated ktbd with better precision and can be used.
Downloads
References
Ångström, A. K., 1924. Solar and terrestrial radiation. Quarterly Journal of the Royal Meteorological Society, v.50, p.121.
Beyer, H. G., Fauter, M., Schumann, K., Schenk, H., Meyer, R., 2010. Synthesis of DNI time series with sub-hourly time resolution. In: 16th SolarPACES Conference. Perpignan (France).
Blanc, P. et al., 2014. Direct normal irradiance related definitions and applications: the circumsolar issue. Solar Energy, v.110, p.561–77.
Chen, J-L, Li, G-S, Wu, S-J., 2013. Assessing the potential of support vector machine for estimating daily solar radiation using sunshine duration. Energy Conversion and Management, v.75, p. 311–318.
Chen, J-L, LI, G-S., 2014. Evaluation of support vector machine for estimation of solar radiation from measured meteorological variables. Theoretical and Applied Climatology, v.115, p.627–638.
Chen, J-L., Li, G-S., Xiao, B-B., Wen, Z-F., LV, M-Q., Chen, C-D., Jiang, Y., Wang, X-X., Wu, S-J., 2015. Assessing the transferability of support vector machine model for estimation of global solar radiation from air temperature.
Energy Conversion and Management, v.89, p. 318–329.
Codato, G., Oliveira, A. P., Soares, J., Escobedo, J. F., Gomes, E. G., Dal Pai, A., 2008. Global and diffuse solar irradiances in urban and rural areas in southeast Brazil. Theoretical and Applied Climatology, v. 93, p.57–73.
Escobedo, J. F., Gomes, E. N., Oliveira, A. P., Soares, J., 2011. Ratios of UV, PAR and NIR components to global solar radiation measured at Botucatu site in Brazil. Renewable Energy, v.36, p.169-178.
Fernandez-Peruchena, C., Blanco, M., Bernardos, A., 2014. Generation of series of high frequency DNI years consistente with annual and monthly long-term averages using measured DNI data. Energy Procedia, v.49, p. 2321–2329.
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten. I. H., 2009. The WEKA Data Mining Software:An Update, SIGKDD Explorations, Volume 11, Issue 1.
Heinemann, A. B., Van Oort, P. A. J., Fernandes, D. S., Maia, A. H. N., 2012. Sensitivity of APSIM/ORYZA model due to estimation errors in solar radiation. Bragantia, Campinas, v. 71, n. 4, p.572-582.
Jamieson, P. D., Porter, J. R., Wilson, D. R., 1991. A test of the computer simulation model ARC-WHEAT1 on wheat crops grown in New Zealand. Field Crops Research, v.27, p.337-350.
Kotti, M. C., Argiriou, A. A., Kazantzidis, A., 2014. Estimation of direct normal irradiance from measured global and correct diffuse horizontal irradiance. Energy, v.70, p.382-392.
Lorena, A. C., Jacintho, L. F. O., Siqueira, M. F., Giovanni, R., Lohmann, L. G., Carvalho, A. C. P. L. F., Yamamoto, M., 2011. Comparing machine learning classifiers in potential distribution modelling. Expert Systems with Applications, v.38, p.5268–5275.
Mohammadi, K., Shamshirband, S., Anisi, M. H., Alam, K, A., Petkovic, D., 2015. Support vector regression based prediction of global solar radiation on a horizontal surface. Energy Conversion and Management, v.91, p.433–441.
Padovan, A., Del Col., Sabatelli, V., Marano, D., 2014. DNI estimation procedures for the assessment of solar radiation availability in concentrating systems. Energy Procedia, v. 57, p.1140-1149.
PLATT, J., 1998. Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines. Redmond: Microsoft Research. 21 p. TechReport.
Santos, C. M. et al., 2014. On modeling global solar irradiation using air temperature for Alagoas State, Northeastern Brazil. Energy, v.71, p.388-398.
Smola, A. J., Schölkopf, B., 2004. A tutorial on support vector regression. Statistics and Computing, v.14, p.199-222.
Vapnik, V. N. 1995. The nature of statistical learning theory. New York: Springer.
Viana, T. S., Ruthera, R., Martins, F. R., Pereira, E. B., 2011. Assessing the potential of concentrating solar photovoltaic generation in Brazil with satellite-derived direct normal irradiation. Solar Energy, v.85, p.486–495.
Witten, I. H., Frank, E., Hall, M. A., 2011. Data Mining: Practical Machine Learning Tools and Techniques. 3rd ed, 630p.
WMO - World Meteorological Organization., 1981. Meteorological Aspects of the Utilization of Solar Radiation as na Energy Source. World Meteorological Organization Technical Note No. 172, WMO-No. 557, Geneva, p. 298.
Yadav, A. K., Chandel, S. S., 2015. Solar energy potential assessment of western Himalayan Indian state of Himachal Pradesh using J48 algorithm of WEKA in ANN based prediction model. Renewable Energy, v.75, p.675-693.
