Cluster analysis for classification and forecasting of solar irradiance in Durban, South Africa

Keywords: numerical weather prediction, cloud cover, k-means, classes

Abstract

Clustering of solar irradiance patterns was used in conjunction with cloud cover forecasts from Numerical Weather Predictions for day-ahead forecasting of irradiance. Beam irradiance as a function of time during daylight was recorded over a one-year period in Durban, to which k-means clustering was applied to produce four classes of day with diurnal patterns characterised as sunny all day, cloudy all day, sunny morning-cloudy afternoon, and cloudy morning-sunny afternoon. Two forecasting methods were investigated. The first used k-means clustering on predicted daily cloud cover profiles. The second used a rule whereby predicted cloud cover profiles were classified according to whether their average in the morning and afternoon were above or below 50%. In both methods, four classes were found, which had diurnal patterns associated with the irradiance classes that were used to forecast the irradiance class for the day ahead. The two methods had a comparable success rate of about 65%; the cloud cover clustering method was better for sunny and cloudy days; and the 50% rule was better for mixed cloud conditions.

References

Aguiar, L.M., Pereira, B., Lauret, P., Dia ́z, F. and David, M. 2016. Combining solar irradiance measurements, satellite-derived data and a numerical weather pre-diction model to improve intra-day solar forecasting. Renewable Energy 97: 599–610.
https://doi.org/10.1016/j.renene.2016.06.018
Badosa, J., Haeffelin, M. and Chepfer, H. 2013. Scales of spatial and temporal variation of solar irradiance on Reunion tropical island. Solar Energy 88: 42–56.
https://doi.org/10.1016/j.solener.2012.11.007
Badosa, J., Haeffelin, M., Kalecinski, N., Bonnardot, F. and Jumaux, G. 2015. Reliability of day-ahead solar irradiance forecasts on Reunion Island depending on synoptic wind and humidity conditions. Solar Energy 115: 306–321.
https://doi.org/10.1016/j.solener.2015.02.039
Brooks, M.J., du Clou, S., van Niekerk, W.L., Gauche ́, P., Mouzouris, M.J., Meyer, R., van der Westhuizen, N., van Dyk, E.E and Vorster, F.J. 2015. SAURAN: A new resource for solar radiometric data in Southern Africa. Journal of Energy in Southern Africa 26(1): 2–10.
Diabaté, L., Blanc, P. and Wald, L. 2004. Solar radiation climate in Africa. Solar Energy 76: 733–744.
Gastón-Romeo, M., Leon, T., Mallor, F. and Rami ́rez-Santigosa, L. 2011. A morphological clustering method for daily solar radiation curves. Solar Energy 85, 1824-1836.
Halkidi, M., Batistakis, Y. and Vazirgiannis, M. 2001. On clustering validation techniques. Intelligent Infor-mation Systems 17: 107–145.
https://doi.org/10.1023/A:1012801612483
Harrouni, S., Guessoum, A. and Maafi, A. 2005. Classifi-cation of daily solar irradiation by fractional analysis of 10-min-means of solar irradiance. Theoretical and Applied Climatology 80: 27–36.
https://doi.org/10.1007/s00704-004-0085-0
Ineichen, P. and Perez, R. 2002. A new airmass inde-pendent formulation for the Linke turbidity coeffi-cient. Solar Energy 73: 151–157.
https://doi.org/10.1016/S0038-092X(02)00045-2
Inman, R.H., Pedro, H.T.C. and Coimbra, C.F.M. 2013. Solar forecasting methods for renewable energy in-tegration. Progress in Energy and Combustion Sci-ence 39: 535–576.
https://doi.org/10.1016/j.pecs.2013.06.002
Jeanty, P., Delsaut, M., Trovalet, L., Ralambondrainy, H., Lan-Sun-Luk, J.D., Bessafi, M., Charton, P. and Chabriat, J.P. 2013. Clustering daily solar radiation from Reunion Island using data analysis methods. In: Proceedings of the International Conference on Renewable Energies and Power Quality (ICREPQ'13), Bilbao, Spain.
https://doi.org/10.24084/repqj11.340
Jolliffe, I.T. 2002. Principal component analysis. Spring-er, New York.
Kunene, K., Brooks, M.J., Roberts, L.W. and Zawilska, E. 2013. Introducing GRADRAD: The greater Dur-ban radiometric network. Renewable Energy 49: 259–262.
https://doi.org/10.1016/j.renene.2012.01.019
Lleti ́, R., Ortiz, M.C., Sarabia, L.A. and Sa ́nchez, M.S. 2004. Selecting variables for k-means cluster analy-sis by using a genetic algorithm that optimises the silhouettes. Analytica Chimica Acta 515: 87–100.
Lorenz, E., Hurka, J., Heinemann, D. and Beyer, H.G. 2009. Irradiance forecasting for the power prediction of grid-connected photovoltaic systems. IEEE Jour-nal of Selected Topics in Applied Earth Observations and Remote Sensing 2: 2–10.
https://doi.org/10.1109/JSTARS.2009.2020300
Lysko, M.D. 2006. Measurements and models of solar irradiance. PhD Thesis. Norwegian University of Sci-ence and Technology.
Maafi, A. and Harrouni, S. 2003. Preliminary results of the fractal classification of daily solar irradiances. So-lar Energy 75: 53–61.
https://doi.org/10.1016/S0038-092X(03)00192-0
MacQueen, J.B. 1967. Some methods for classification and analysis of multivariate observations. In: Pro-ceedings of 5th Berkeley Symposium on Mathemati-cal Statistics and Probability, University of California.
Mathiesen, P., Collier, C. and Kleissl, J. 2013. A high-resolution, cloud-assimilating numerical weather prediction model for solar irradiance forecasting. So-lar Energy 92: 47–61.
https://doi.org/10.1016/j.solener.2013.02.018
McCandless, T.C., Haupt, S.E. and Young, G.S. 2014. Short term solar radiation forecasts using weather re-gime-dependent artificial intelligence techniques. In: Proceedings of the 12th Conference on Artificial and Computational Intelligence and its Applications to the Environmental Sciences: Applications of Artificial Intelligence Methods for Energy. Atlanta, Georgia.
McCandless, T.C., Haupt, S.E., Young, G.S. and Annun-zio, A.J. 2015. A regime-dependent Bayesian ap-proach to short-term solar irradiance forecasting. In: Proceedings of the13th Conference on Artificial Intel-ligence: Applications of Artificial Intelligence Methods for Energy-Part II. Phoenix, Arizona.
Muselli, M., Poggi, P., Notton, G. and Louche, A. 2000. Classification of typical meteorological days from global irradiation records and comparison between two Mediterranean coastal sites in Corsica Island. Energy Conversion and Management 41: 1043–1063.
https://doi.org/10.1016/S0196-8904(99)00139-9
Perez, R., Moore, K., Wilcox, S., Renne, D. and Zelenka, A. 2007. Forecasting solar radiation: Preliminary evaluation of an approach based upon the national forecast database. Solar Energy 81: 809–812.
https://doi.org/10.1016/j.solener.2006.09.009
Remund, J., Perez, R. and Lorenz, E. 2008. Comparison of solar radiation forecasts for the USA. In: Proceed-ings of the 23rd European Photovoltaic Solar Energy Conference, Valencia, Spain.
Rousseeuw, P.J. 1957. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics 20: 53–65.
https://doi.org/10.1016/0377-0427(87)90125-7
Sandia National Laboratories (SNL). 2012. Pv_lib toolbox for matlab.pvpmc.sandia.gov/applications/pv_lib-toolbox/matlab/ [Accessed 30 August 2017].
Soubdhan, T., Emilion, R. and Calif, R. 2009. Classifica-tion of daily solar radiation distributions using a mix-ture of Dirichlet distributions. Solar Energy 83: 1056–1063.
https://doi.org/10.1016/j.solener.2009.01.010
Zagouras, A., Inman, R.H. and Coimbra, C.F.M. 2014. On the determination of coherent solar microclimates for utility planning and operations. Solar Energy 102: 173–188.
https://doi.org/10.1016/j.solener.2014.01.021
Zawilska, E. and Brooks, M.J. 2011. An assessment of the solar resource for Durban, South Africa. Renew-able Energy 36: 3433–3438.
https://doi.org/10.1016/j.renene.2011.05.023
Zhandire, E. 2017. Solar resource classification in South Africa using a new index. Journal of Energy in Southern Africa 28(2): 61–70.
https://doi.org/ 10.17159/2413-3051/2017/v28i2a1640
Views
  • Abstract 14
  • pdf 11
Views and downloads are with effect from 11 January 2018
Published
2018-06-22