Comparison of Solar Irradiance between WRF simulation and Deep Learning: Case study in Nishi Akisawa, Japan


Comparison of Solar Irradiance between WRF simulation and Deep Learning: Case study in Nishi Akisawa, Japan


Jose Manuel Soares de Araujo

Gifu University Faculty Of Engineering and Graduate School Of Engineering 1-1 Yanagido, Gifu City 501-1193, Japan


American Journal of Engineering Research and Reviews

A This paper presents a study of evaluation for the reliability of seven-days direct normal irradiance (DNI) and diffuse irradiance (DIF) forecasts which provided by Weather Research and Forecasting (WRF) mesoscale model using six-hourly interval 0.5°x0.5° input dataset obtained from National Oceanic and Atmospheric Administration – National Operational Model Archive and Distribution System (NOMADS) website. 3 km spatial resolution was used to estimate seven-days simulation starting from 1st to 7th January 2017 for comparison purpose. Long short-term memory (LSTM) algorithm has been applied to make future prediction. The one-hourly values input dataset of LSTM obtained from Nishi Akisawa mega solar website is consist of one-year data of solar irradiance starting from 1st January to 31st December 2016. This dataset divided into training datasets (89%) and testing datasets(11%) where the testing datasets values was used to make future prediction of solar irradiance. The result shows the error of root mean square of LSTM algorithm is 129 W/m2 higher compare to 101 W/m2 from the WRF model for seven-days prediction but the result of this study proposed using LSTM algorithm for future prediction of solar irradiance or others parameter of weather.

Highlights
• Comparison of future prediction of solar irradiance has done in Nishi Akisawa-Japan; • This study applied NOAA-NOMADS dataset as input dataset of WRF; • Input data of LSTM algorithm obtained from Nishi Akisawa mega solar weather station; • LSTM algorithm shows error of RMSE is higher compared to WRF model.


Keywords: environmental impact, recession, water supply, lake, and hygiene


Free Full-text PDF


How to cite this article:
Jose Manuel Soares de Araujo.Comparison of Solar Irradiance between WRF simulation and Deep Learning: Case study in Nishi Akisawa, Japan. American Journal of Engineering Research and Reviews, 2018, x:xx (Accepted Article, Online first)


References:

1. Xiangyun Qing, Yugang Niu. Hourly day-ahead solar irradiance prediction using weather forecast. Volume 148, 1 April 2018, Pages 461-468 https://doi.org/10.1016/j.energy.2018.01.177
2. Solar energy prediction using linear and non-liner regularization models: A study on AMS (American Meteorological Society) 2013-2014 Solar Prediction Contests. Volume 78, 15 December 2014, Pages 247-256 DOI: 10.1016/j.energy.2014.10.012
3. Richard Perez, Sergey Kivalov, James Schlemmer, Karl Hemker Jr., David Renné, Thomas E.Hoff. Volume 84, Issue 12, December 2010, Pages 2161-2172 Validation of short and mediumterm operational solar radiation forecasts in the US http://dx.doi.org/10.1016/j.solener.2010.08.014
4. V.Lara-Fanego, J.A.Ruiz-Arias, D.Pozo-Vázquez, F.J.Santos-Alamillos, J.Tovar-Pescador Evaluation of the WRF model solar irradiance in Andalusia (Southern Spain). Volume 86, Issue 8, August 2012, Pages 2200-2217. https://doi.org/10.1016/j.solener.2011.02.014
5. Yashwant Kashyap Ankit Bansal Anil K.SaoSolar radiation forecasting with multiple parameters neural networks Volume 49, September 2015, Pages 825-835  ttps://doi.org/10.1016/j.rser.2015.04.077
6. Nishi Akisawa-Gifu. https://www.japanpostalcode.net/cp27707/zip-code-501-1184 nishiakisawa-gifu-shi-gifu.
7. W. Skamarock, J. Klemp, J. Dudhia, D. Gill, D. Barker, M. Duda, et al. A Description of the Advanced Research WRF Version 3. Technical Report NCAR/TN– 475+STR, NCAR 2008. (2008) Available: http://www2.mmm.ucar.edu/wrf/users/docs/arw_v3.pdf (accessed 24.09.15).
8. Mlawer, E. J., Taubman, J., Brown, P. D., Iacono, M. J., & Clough, S. A. (1997). Radiative transfer for inhomogeneous atmospheres: RRTM, a validated correlated model for the longwave. Journal of Geophysical Research, 102(D14), 16663–16682. http://dx.doi.org/10.1029/97JD00237.
9. Iacono, M.J., Mlawer, E.J., Clough, S.A., Morcrette, J.-J., 2000. Impact of an improved longwave radiation model, RRTM, on the energy budget and thermodynamic properties of the NCAR community climate mode, CCM3. J. Geophys. Res. 105,14873–14890.
10. Laura Bianco, ATOC 7500: Mesoscale Meteorological Modeling Spring 2008 http://cires1.colorado.edu/.
11. S.Y. Hong, Y. Noh, J. Dudhia. Mon Weather Rev, 134 (2006), pp. 2318–2341 A new vertical diffusion package with an explicit treatment of entrainment processes.
12. NCL, 2017. The NCAR Command Language (version 6.4.0). http://dx.doi.org/10.5065/D6WD3XH5.
13. Fischer T, Krauss C. Deep learning with long-term memory networks for financial market predictions. Eur J Oper Res 2018. FAU Discussion Papers in Economics, No.11/2017.
14. https://keras.io/.
15. Jitendra Kumar, Rimsha Goomer, Ashutosh Kumar Singh. Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters.Volume 125, 2018, Pages 676-682 https://doi.org/10.1016/j.procs.2017.12.087
16. https://machinelearningmastery.com
17. https://towardsdatascience.com/using-lstms-to-forecast-time-series-4ab688386b1f
18. David, M., Diagne, M., Lauret, P., 2012. Outputs and error indicators for solar forecasting models. In: Proceedings of the World Renewable Energy Forum 2012 (WREF 2012), Denver, USA.
19. Hadrien Verbois, Robert Huva, Andrivo Rusydi, Wilfred Walsh Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning. Volume 162, 1 March 2018, Pages 265-277 https://doi.org/10.1016/j.solener.2018.01.007
20. Notes for running WRF with the Aerosol-aware Thompson Scheme (mp_physics = 28) http://www2.mmm.ucar.edu/wrf/users/wrfv3.9/mp28_updated.html