A Method to Estimation of Global Solar Radiation with Meteorological Parameters under Cloudless Sky Condition using Artificial Neural Network
##plugins.themes.bootstrap3.article.sidebar##
##plugins.themes.bootstrap3.article.main##
Abstract
In this work, variation of global radiation hourly basis and model developed to estimate the radiation under cloudless sky condition were purposed at Lopburi province (14.83°N, 100.62°E). Data of global radiation and meteorological parameters from 2012 to 2017 were investigated. For the variation of global radiation, the maximum and minimum of radiation are 3.46 MJ/m2 in April and 2.40 MJ/m2 in December, and there are some meteorological parameters influencing on the radiation. Therefore, a model for estimation of hourly global solar radiation under cloudless sky condition at this site was proposed based on the artificial neural network (ANN). This ANN has one input layer, two hidden layers and one output layer. The input layer consists of some meteorological parameters that are solar zenith angle, visibility, air temperature, relative humidity, wind speed and air pressure, and the output layer is global solar radiation under clear sky condition. The ANN was trained using the input and output data collected at Lopburi meteorological station during the year: 2012-2014. It was then validated against an independent data at the site for the period of three years (2015-2017). The validation result indicates that the estimated solar radiation under clear sky condition obtained from ANN are in good agreement with that from the measurement, with root mean square difference (RMSD) of 8.52% and mean bias difference (MBD) of 1.22%. Therefore, the model can be applied for estimation of global radiation under cloudless sky condition at other meteorological stations with similar climate. The estimated solar radiation data are useful for management in solar power plant, solar thermal energy system and also for the studies in the atmospheric field.
Keywords: solar radiation, meteorological parameter, artificial neural network
References
Azadeh, A., Maghsoudi, A., Sohrabkhani, S. (2009) An integrated artificial neural networks approach for predicting global radiation. Energy Conversion and Management, 50, 1497–1505.
Benghanem, M., Mellit, A., & Alamri, S. N. (2009). ANN-based modelling and estimation of daily global solar radiation data: A case study. Energy Conversion Management, 50, 1644-1655.
Chiteka, K., & Enweremadu, C. C. (2016). Prediction of global horizontal solar irradiance in Zimbabwe using artificial neural networks. Cleaner Production, 135, 201-711.
Elminir, H.K., Areed, F.F,, Elsayed, T.S.(2005). Estimation of solar radiation components incident on Helwan site using neural networks. Solar Energy, 79, 270–279.
Frank, E., Hall, M. A., & Witten, I. H. (2016). The WEKA Workbench. USA: Morgan Kaufmann.
Hagan, M. T., Demuth, H. B., & Beale, M. H. (1996). Neural Network Design. Retrieved from https://hagan.okstate.edu/NNDesign.pdf
Hongkong, S. (2018). Ann-based model with adaptive observation system for estimation solar irradiance and illuminance on horizontal surface. Journal of Research and Applications in Mechanical Engineering, 6, 82-94.
Iqbal, M. (1983). An Introduction to Solar Radiation. New York: Academic Press.
Janjai, S., Kumharn, W., & Laksanaboonsong, J. (2003). Determination of Angstrom’s turbidity coefficient over Thailand. Renewable Energy, 28, 1685-1700.
Janjai, S., Pankaew, P., & Laksanaboonsong, J. (2009). A model for calculating hourly global solar radiation from satellite data in the tropics. Applied Energy, 86(9), 1450–1457.
Jacovides, C. P., Tymvios, F. S., Boland, J., & Tsitouri, M. (2013). Artificial Neural Network models for estimating daily solar global UV, PAR and broadband radiant fluxes in an eastern Mediterranean site. Atmospheric Research, 152, 138–145.
Kalogirou, S. A. (2001). Artificial neural networks in renewable energy systems applications: A review. Renewable and Sustainable Energy Reviews, 5, 373-401.
Kaushika, N. D., Tomar, R. K., & Kaushik, S. C. (2014). Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations. Solar Energy, 103, 327-342.
Li, J., & Heap, A. D. (2008). A Review of Spatial Interpolation Methods for Environmental Scientists. Australia: Geoscience Australia.
Mellit, A., & Kalogirou, S. A. (2008). Artificial intelligence based forecast models for predicting solar power generation. Progress in Energy and Combustion Science, 34, 574–632.
Mellit, A., Kalogirou, S. A., Hontoria, L., & Shaari, S. (2009). Artificial intelligence techniques for sizing photovoltaic systems: a review. Renewable and Sustainable Energy Reviews, 13, 406–419.
Mubiru, J., Banda, E. J. K. B. (2008). Estimation of monthly average daily global solar irradiation using artificial neural networks. Solar Energy, 82, 181–187.
Pratummasoot, N., Choosri, P., Buntoung, S., & Mundpookhiew, T. (2020). Estimation of Hourly Infrared Padiation Using Artificial Neural Network and Performance Comparison with Semi-Empirical Model at Nakhon Pathom Province. Naresuan University Journal: Science and Technology, 28(4), 102-111.
Patterson, D. W. (1996). Artificial Neural Networks: Theory and Applications. New York: Prentice Hall.
Silva, M. B. P., Escobedo, J. F., Rossi, T. J., Santos, C. M., & Silva, S. H. M. G. (2017). Performance of the Angstrom-Prescott Model (A-P) and SVM and ANN Techniques to Estimate Daily Global Solar Irradiation in Botucatu/SP/Brazil. Journal of Atmospheric and Solar-Terrestrial Physics, 160, 11-23.
Yadava, A. K., Malik, H., & Chandel, S. S. (2014). Selection of most relevant input parameters using WEKA for artificial neural network based on solar radiation prediction models. Renewable and Sustainable Energy Review, 31, 509 – 519.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.