Advertisement

Scalable Gaussian Process Models for Solar Power Forecasting

  • Astrid Dahl
  • Edwin Bonilla
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10691)

Abstract

Distributed residential solar power forecasting is motivated by multiple applications including local grid and storage management. Forecasting challenges in this area include data nonstationarity, incomplete site information, and noisy or sparse site history. Gaussian process models provide a flexible, nonparametric approach that allows probabilistic forecasting. We develop fully scalable multi-site forecast models using recent advances in approximate Gaussian process methods to (probabilistically) forecast power at 37 residential sites in Adelaide (South Australia) using only historical power data. Our approach captures diurnal cycles in an integrated model without requiring prior data detrending. Further, multi-site methods show some advantage over single-site methods in variable weather conditions.

Notes

Acknowledgements

This work was supported by Solar Analytics Pty Ltd. and performed on behalf of the Cooperative Research Centre for Low-Carbon Living (University of New South Wales and Solar Analytics Pty Ltd.).

References

  1. 1.
    Alvarez, M.A., Rosasco, L., Lawrence, N.D., et al.: Kernels for vector-valued functions: a review. Found. Trends® Mach. Learn. 4(3), 195–266 (2012)CrossRefzbMATHGoogle Scholar
  2. 2.
    Aryaputera, A.W., Yang, D., Zhao, L., Walsh, W.M.: Very short-term irradiance forecasting at unobserved locations using spatio-temporal kriging. Sol. Energy 122, 1266–1278 (2015). http://www.sciencedirect.com/science/article/pii/S0038092X15005745 CrossRefGoogle Scholar
  3. 3.
    Bessa, R., Trindade, A., Silva, C.S., Miranda, V.: Probabilistic solar power forecasting in smart grids using distributed information. Int. J. Electr. Power Energy Syst. 72, 16–23 (2015). http://www.sciencedirect.com/science/article/pii/S0142061515000897, the Special Issue for 18th Power Systems Computation ConferenceCrossRefGoogle Scholar
  4. 4.
    Bilionis, I., Constantinescu, E.M., Anitescu, M.: Data-driven model for solar irradiation based on satellite observations. Sol. Energy 110, 22–38 (2014). http://www.sciencedirect.com/science/article/pii/S0038092X14004393 CrossRefGoogle Scholar
  5. 5.
    Boland, J.: Spatial-temporal forecasting of solar radiation. Renew. Energy 75, 607–616 (2015). http://www.sciencedirect.com/science/article/pii/S0960148114006624 CrossRefGoogle Scholar
  6. 6.
    Bonilla, E.V., Krauth, K., Dezfouli, A.: Generic inference in latent Gaussian process models (2016). arXiv preprint: arXiv:1609.00577
  7. 7.
    Copper, J., Sproul, A., Jarnason, S.: Photovoltaic (pv) performance modelling in the absence of onsite measured plane of array irradiance (poa) and module temperature. Renew. Energy 86, 760–769 (2016)CrossRefGoogle Scholar
  8. 8.
    Cressie, N., Wikle, C.K.: Statistics for Spatio-Temporal Data. John Wiley & Sons, Hoboken (2011)zbMATHGoogle Scholar
  9. 9.
    David, M., Ramahatana, F., Trombe, P., Lauret, P.: Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models. Sol. Energy 133, 55–72 (2016). http://www.sciencedirect.com/science/article/pii/S0038092X16300172 CrossRefGoogle Scholar
  10. 10.
    Diagne, M., David, M., Lauret, P., Boland, J., Schmutz, N.: Review of solar irradiance forecasting methods and a proposition for small-scale insular grids. Renew. Sustain. Energy Rev. 27, 65–76 (2013). http://www.sciencedirect.com/science/article/pii/S1364032113004334 CrossRefGoogle Scholar
  11. 11.
    Domke, J., Engerer, N., Menon, A., Webers, C.: Distributed solar prediction with wind velocity (2016)Google Scholar
  12. 12.
    Gutierrez-Corea, F.V., Manso-Callejo, M.A., Moreno-Regidor, M.P., Manrique-Sancho, M.T.: Forecasting short-term solar irradiance based on artificial neural networks and data from neighboring meteorological stations. Sol. Energy 134, 119–131 (2016). http://www.sciencedirect.com/science/article/pii/S0038092X16300536 CrossRefGoogle Scholar
  13. 13.
    Hensman, J., Fusi, N., Lawrence, N.D.: Gaussian processes for big data. In: Uncertainty in Artificial Intelligence (2013)Google Scholar
  14. 14.
    Inman, R.H., Pedro, H.T., Coimbra, C.F.: Solar forecasting methods for renewable energy integration. Prog. Energy Combust. Sci. 39(6), 535–576 (2013)CrossRefGoogle Scholar
  15. 15.
    Lauret, P., Voyant, C., Soubdhan, T., David, M., Poggi, P.: A benchmarking of machine learning techniques for solar radiation forecasting in an insular context. Sol. Energy 112, 446–457 (2015)CrossRefGoogle Scholar
  16. 16.
    Li, J., Ward, J.K., Tong, J., Collins, L., Platt, G.: Machine learning for solar irradiance forecasting of photovoltaic system. Renew. Energy 90, 542–553 (2016). http://www.sciencedirect.com/science/article/pii/S0960148115305747 CrossRefGoogle Scholar
  17. 17.
    Lonij, V.P., Brooks, A.E., Cronin, A.D., Leuthold, M., Koch, K.: Intra-hour forecasts of solar power production using measurements from a network of irradiance sensors. Sol. Energy 97, 58–66 (2013)CrossRefGoogle Scholar
  18. 18.
    Pelland, S., Remund, J., Kleissl, J., Oozeki, T., De Brabandere, K.: Photovoltaic and solar forecasting: state of the art. iea pvps task 14, subtask 3.1. report iea-pvps t14–01: 2013. Technical report (2013). ISBN: 978-3-906042-13-8Google Scholar
  19. 19.
    Quiñonero-Candela, J., Rasmussen, C.E.: A unifying view of sparse approximate Gaussian process regression. J. Mach. Learn. Res. 6, 1939–1959 (2005)zbMATHMathSciNetGoogle Scholar
  20. 20.
    Rana, M., Koprinska, I., Agelidis, V.G.: Univariate and multivariate methods for very short-term solar photovoltaic power forecasting. Energy Convers. Manag. 121, 380–390 (2016)CrossRefGoogle Scholar
  21. 21.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press, Cambridge (2006)zbMATHGoogle Scholar
  22. 22.
    Sampson, P.D., Guttorp, P.: Nonparametric estimation of nonstationary spatial covariance structure. J. Am. Stat. Assoc. 87(417), 108–119 (1992)CrossRefGoogle Scholar
  23. 23.
    Shinozaki, K., Yamakawa, N., Sasaki, T., Inoue, T.: Areal solar irradiance estimated by sparsely distributed observations of solar radiation. IEEE Trans. Power Syst. 31(1), 35–42 (2016)CrossRefGoogle Scholar
  24. 24.
    Titsias, M.: Variational learning of inducing variables in sparse Gaussian processes. In: Artificial Intelligence and Statistics (2009)Google Scholar
  25. 25.
    Voyant, C., Notton, G., Kalogirou, S., Nivet, M.L., Paoli, C., Motte, F., Fouilloy, A.: Machine learning methods for solar radiation forecasting: a review. Renew. Energy 105, 569–582 (2017). http://www.sciencedirect.com/science/article/pii/S0960148116311648 CrossRefGoogle Scholar
  26. 26.
    Yang, D., Gu, C., Dong, Z., Jirutitijaroen, P., Chen, N., Walsh, W.M.: Solar irradiance forecasting using spatial-temporal covariance structures and time-forward kriging. Renew. Energy 60, 235–245 (2013). http://www.sciencedirect.com/science/article/pii/S0960148113002759 CrossRefGoogle Scholar
  27. 27.
    Yang, D., Ye, Z., Lim, L.H.I., Dong, Z.: Very short term irradiance forecasting using the lasso. Sol. Energy 114, 314–326 (2015). http://www.sciencedirect.com/science/article/pii/S0038092X15000304 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.University of New South WalesSydneyAustralia

Personalised recommendations