Assessment of Solar Energy Potential of Smart Cities of Tamil Nadu Using Machine Learning with Big Data

  • R. MeenalEmail author
  • A. Immanuel Selvakumar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 750)


Global Solar Radiation (GSR) prediction is important to forecast the output power of solar PV system in case of renewable energy integration into the existing grid. GSR can be predicted using commonly measured meteorological data like relative humidity, maximum, and minimum temperature as input. The input data is collected from India Meteorological Department (IMD), Pune. In this work, Waikato Environment for Knowledge Analysis (WEKA) software is employed for GSR prediction using Machine Learning (ML) techniques integrated with Big Data. Feature selection methodology is used to reduce the input data set which improves the prediction accuracy and helps the algorithm to run fast. Predicted GSR value is compared with measured value. Out of eight ML algorithms, Random Forest (RF) has minimum errors. Hence this work attempts in predicting the GSR in Tamil Nadu using RF algorithm. The predicted GSR values are in the range of 5–6 kWh/m2/day for various solar energy applications in Tamil Nadu.


Machine learning Big data Global solar radiation Random forest 



Authors would like to thank IMD, Pune for data support.


  1. 1.
    Prescott, J.A.: Evaporation from a water surface in relation to solar radiation. Trans. R. Soc. S. Aust. 64, 114–118 (1940)Google Scholar
  2. 2.
    Chen, R., Ersi, K., Yang, J., Lu, S., Zhau, W.: Validation of five global radiation models with measured daily data in China. Energ. Convers. Manage. 45, 1759–1769 (2004)CrossRefGoogle Scholar
  3. 3.
    Citakoglu, H.: Comparison of artificial intelligence techniques via empirical equations for prediction of solar radiation. Comput. Electron. Agric. 115, 28–37 (2015)CrossRefGoogle Scholar
  4. 4.
    Belaid, S., Mellit, A.: Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate. Energ. Convers. Manage. 118, 105–118 (2016)CrossRefGoogle Scholar
  5. 5.
    Meenal, R., Immanuel Selvakumar, A.: Assessment of SVM, Empirical and ANN based solar radiation prediction models with most influencing input parameters. Renewable Energy 121, 324–343 (2018)CrossRefGoogle Scholar
  6. 6.
    Voyant, C., Notton, G., Kalogirou, S., Nivet, M.-L., Paoli, C., Motte, F., Fouilloy, A.: Machine learning methods for solar radiation forecasting: a review. Renewable Energy 105, 569–582 (2017)CrossRefGoogle Scholar
  7. 7.
    NASA: Atmospheric Science Data Centre.
  8. 8.
    Salcedo-Sanz, S., Casanova-Mateo, C., Muñoz-Marí, J., Camps-Valls, G.: Prediction of daily global solar irradiation using temporal gaussian processes. IEEE Geosci. Remote Sens. Lett. 11(11) (November 2014).
  9. 9.
    Quinlan, J.R.: Learning with continuous classes. In: Adams and Sterling (eds.) Proceedings AI’92, pp. 343–348. World Scientific, Singapore (1992)Google Scholar
  10. 10.
    Pfahringer, B.: Random Model Trees: An Effective and Scalable Regression method. University of Waikato, New Zealand.
  11. 11.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)CrossRefGoogle Scholar
  12. 12.
    Breiman, L.: Random forests. J. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  13. 13.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Electrical SciencesKarunya Institute of Technology and SciencesCoimbatoreIndia

Personalised recommendations