Spatial autocorrelation and entropy for renewable energy forecasting

Abstract

In renewable energy forecasting, data are typically collected by geographically distributed sensor networks, which poses several issues. (i) Data represent physical properties that are subject to concept drift, i.e., their characteristics could change over time. To address the concept drift phenomenon, adaptive online learning methods should be considered. (ii) The error distribution is typically non-Gaussian. Therefore, traditional quality performance criteria during training, like the mean-squared error, are less suitable. In the literature, entropy-based criteria have been proposed to deal with this problem. (iii) Spatially-located sensors introduce some form of autocorrelation, that is, values collected by sensors show a correlation strictly due to their relative spatial proximity. Although all these issues have already been investigated in the literature, they have not been investigated in combination. In this paper, we propose a new method which learns artificial neural networks by addressing all these issues. The method performs online adaptive training and enriches the entropy measures with spatial information of the data, in order to take into account spatial autocorrelation. Experimental results on two photovoltaic power production datasets are clearly favorable for entropy-based measures that take into account spatial autocorrelation, also when compared with state-of-the art methods.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Notes

  1. 1.

    http://re.jrc.ec.europa.eu/pvgis/.

  2. 2.

    In our formulation, the neighborhood N(p) includes the considered current plant p, i.e. \(p\in N(p)\).

  3. 3.

    http://www.nrel.gov/.

  4. 4.

    http://forecast.io/.

  5. 5.

    http://re.jrc.ec.europa.eu/pvgis/apps4/pvest.php.

  6. 6.

    https://github.com/sryza/spark-timeseries.

  7. 7.

    https://spark.apache.org/docs/latest/mllib-guide.html.

  8. 8.

    http://www.cs.waikato.ac.nz/ml/weka/.

References

  1. Aggarwal CC (2013) An introduction to sensor data analytics. In: Aggarwal CC (ed) Managing and mining sensor data. Springer, New York, pp 1–8

    Chapter  Google Scholar 

  2. Appice A, Ciampi A, Fumarola F, Malerba D (2014) Data mining techniques in sensor networks. SpringerBriefs in computer science. Springer, London

    Book  Google Scholar 

  3. Bacher P, Madsen H, Nielsen HA (2009) Online short-term solar power forecasting. Sol Energy 83(10):1772–1783

    Article  Google Scholar 

  4. Barbounis T, Theocharis JB (2007) Locally recurrent neural networks for wind speed prediction using spatial correlation. Inf Sci 177(24):5775–5797

    Article  Google Scholar 

  5. Barlow R, Brunk H (1972) The isotonic regression problem and its dual. J Am Stat Assoc 67(337):140–147

    MathSciNet  MATH  Article  Google Scholar 

  6. Bessa R, Miranda V, Gama J (2008) Wind power forecasting with entropy-based criteria algorithms. In: Proceedings of the 10th international conference on probabilistic methods applied to power systems, IEEE, PMAPS ’08, pp 1–7

  7. Bessa RJ, Miranda V, Gama J (2009) Entropy and correntropy against minimum square error in offline and online three-day ahead wind power forecasting. IEEE Trans Power Syst 24(4):1657–1666

    Article  Google Scholar 

  8. Bessa RJ, Trindade A, Miranda V (2015) Spatial-temporal solar power forecasting for smart grids. IEEE Trans Ind Inform 11(1):232–241

    Article  Google Scholar 

  9. Bishop CM (1995) Neural networks for pattern recognition. Oxford Univ. Press, Oxford, London

    MATH  Google Scholar 

  10. Bludszuweit H, Dominguez-Navarro JA, Llombart A (2008) Statistical analysis of wind power forecast error. IEEE Trans Power Syst 23(3):983–991

    Article  Google Scholar 

  11. Bofinger S, Heilscher G (2006) Solar electricity forecast—approaches and first results. In: 20th Europ. PV conf

  12. Bogorny V, Valiati J, Camargo S, Engel P, Kuijpers B, Alvares LO (2006) Mining maximal generalized frequent geographic patterns with knowledge constraints. In: Sixth international conference on data mining (ICDM’06), IEEE, pp 813–817

  13. Borcard D, Legendre P, Avois-Jacquet C, Tuomisto H (2004) Dissecting the spatial structure of ecological data at multiple scales. Ecology 85(7):1826–1832

    Article  Google Scholar 

  14. Box GE, Jenkins GM, Reinsel GC, Ljung GM (2015) Time series analysis: forecasting and control. Wiley, Hoboken

    MATH  Google Scholar 

  15. Buhan S, Cadirci I (2015) Multistage wind-electric power forecast by using a combination of advanced statistical methods. IEEE Trans Ind Inform 11(5):1231–1242

    Article  Google Scholar 

  16. Cavalcante L, Bessa RJ, Reis M, Browell J (2017) Lasso vector autoregression structures for very short-term wind power forecasting. Wind Energy 20(4):657–675

    Article  Google Scholar 

  17. Ceci M, Appice A (2006) Spatial associative classification: propositional vs structural approach. J Intell Inf Syst 27(3):191–213

    Article  Google Scholar 

  18. Ceci M, Corizzo R, Fumarola F, Malerba D, Rashkovska A (2017) Predictive modeling of PV energy production: How to set up the learning task for a better prediction? IEEE Trans Ind Inform 13(3):956–966. https://doi.org/10.1109/TII.2016.2604758

    Article  Google Scholar 

  19. Ceci M, Corizzo R, Malerba D, Rashkovska A (2018) Spatial autocorrelation and entropy for renewable energy forecasting (Dataset). 1:1. https://doi.org/10.5281/zenodo.1242854

    Article  Google Scholar 

  20. Chakraborty P, Marwah M, Arlitt MF, Ramakrishnan N (2012) Fine-grained photovoltaic output prediction using a bayesian ensemble. In: AAAI

  21. Chu Y, Pedro H, Coimbra C (2013) Hybrid intra-hour dni forecasts with sky image processing enhanced by stochastic learning. Sol Energy 98(PC):592–603. https://doi.org/10.1016/j.solener.2013.10.020

    Article  Google Scholar 

  22. Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30

    MathSciNet  MATH  Google Scholar 

  23. Dowell J, Pinson P (2016) Very-short-term probabilistic wind power forecasts by sparse vector autoregression. IEEE Trans Smart Grid 7(2):763–770

    Google Scholar 

  24. Erdogmus D, Principe JC (2002) Generalized information potential criterion for adaptive system training. IEEE Trans Neural Netw 13(5):1035–1044

    Article  Google Scholar 

  25. Erdogmus D, Principe JC, Kim SP, Sanchez JC (2002) A recursive renyi’s entropy estimator. In: Neural networks for signal processing, 2002. Proceedings of the 2002 12th IEEE workshop on, IEEE, pp 209–217

  26. European Photovoltaic Industry Association E (2014) Global market outlook for photovoltaics 2014–2018

  27. Fabbri A, Gomezsanroman T, Rivierabbad J, Mendezquezada VH (2005) Assessment of the cost associated with wind generation prediction errors in a liberalized electricity market. IEEE Trans Power Syst 20(3):1440–1446

    Article  Google Scholar 

  28. Fotheringham AS, Brunsdon C, Charlton M (2003) Geographically weighted regression: the analysis of spatially varying relationships. Wiley, Hoboken

    MATH  Google Scholar 

  29. Gaber MM, Zaslavsky A, Krishnaswamy S (2005) Mining data streams: a review. SIGMOD Rec 34(2):18–26

    MATH  Article  Google Scholar 

  30. Gneiting T, Larson K, Westrick K, Genton MG, Aldrich E (2006) Calibrated probabilistic forecasting at the stateline wind energy center: the regime-switching space-time method. J Am Stat Assoc 101(475):968–979

    MathSciNet  MATH  Article  Google Scholar 

  31. He M, Yang L, Zhang J, Vittal V (2014) A spatio-temporal analysis approach for short-term forecast of wind farm generation. IEEE Trans Power Syst 29(4):1611–1622

    Article  Google Scholar 

  32. Heaton J (2015) Encog: library of interchangeable machine learning models for java and c#. J Mach Learn Res 16(1):1243–1247

    MathSciNet  MATH  Google Scholar 

  33. Hong T, Pinson P, Fan S, Zareipour H, Troccoli A, Hyndman R (2016) Probabilistic energy forecasting: global energy forecasting competition 2014 and beyond. Int J Forecast 32(3):896–913. https://doi.org/10.1016/j.ijforecast.2016.02.001

    Article  Google Scholar 

  34. Hyndman RJ, Khandakar Y et al (2007) Automatic time series for forecasting: the forecast package for r. Tech. rep., Monash University, Department of Econometrics and Business Statistics

  35. Inman R, Pedro H, Coimbra C (2013) Solar forecasting methods for renewable energy integration. Prog Energy Combust Sci 39(6):535–576. https://doi.org/10.1016/j.pecs.2013.06.002

    Article  Google Scholar 

  36. Jayasumana AP (2009) Sensor networks—technologies, protocols and algorithms. In: Industrial electronics, IEEE international symposium on, IEEE, ISIE 2009

  37. Jebaraj S, Iniyan S (2006) A review of energy models. Renew Sustain Energy Rev 10(4):281–311. https://doi.org/10.1016/j.rser.2004.09.004

    Article  Google Scholar 

  38. Kalogirou S (2000) Artificial neural networks in renewable energy systems applications: a review. Renew Sustain Energy Rev 5(4):373–401. https://doi.org/10.1016/S1364-0321(01)00006-5

    Article  Google Scholar 

  39. Kleissl J (2013) Solar energy forecasting and resource assessment. https://doi.org/10.1016/C2011-0-07022-9

  40. Lange M (2005) On the uncertainty of wind power predictionsanalysis of the forecast accuracy and statistical distribution of errors. J Sol Energy Eng 127(2):177–194

    Article  Google Scholar 

  41. Lauret P, Voyant C, Soubdhan T, David M, Poggi P (2015) A benchmarking of machine learning techniques for solar radiation forecasting in an insular context. Sol Energy 112:446–457. https://doi.org/10.1016/j.solener.2014.12.014

    Article  Google Scholar 

  42. Li X, Claramunt C (2006) A spatial entropy-based decision tree for classification of geographical information. Trans GIS 10(3):451–467

    Article  Google Scholar 

  43. Liu W, Pokharel PP, Príncipe JC (2007) Correntropy: properties and applications in non-gaussian signal processing. IEEE Trans Signal Process 55(11):5286–5298

    MathSciNet  MATH  Article  Google Scholar 

  44. Lorenz E, Hurka J, Karampela G, Heinemann D, Beyer HG, Schneider M (2008) Qualified forecast of ensemble power production by spatially dispersed grid-connected pv systems. In: Proceedings of the 23rd European photovoltaic solar energy conference and exhibition, pp 3285–3291

  45. Malerba D, Ceci M, Appice A (2005) Mining model trees from spatial data. In: European conference on principles of data mining and knowledge discovery, Springer, pp 169–180

  46. Marquez R, Coimbra C (2013) Intra-hour dni forecasting based on cloud tracking image analysis. Sol Energy 91:327–336. https://doi.org/10.1016/j.solener.2012.09.018

    Article  Google Scholar 

  47. Mathiesen P, Kleissl J (2011) Evaluation of numerical weather prediction for intra-day solar forecasting in the continental united states. Sol Energy 85(5):967–977. https://doi.org/10.1016/j.solener.2011.02.013

    Article  Google Scholar 

  48. Morejon RA, Principe JC (2004) Advanced search algorithms for information-theoretic learning with kernel-based estimators. IEEE Trans Neural Netw 15(4):874–884

    Article  Google Scholar 

  49. Nanni M, Kuijpers B, Korner C, May M, Pedreschi D (2008) Spatiotemporal data mining. In: Giannotti F, Pedreschi D (eds) Mobility, data mining and privacy: geographic knowledge discovery. Springer, Berlin, pp 267–296

    Chapter  Google Scholar 

  50. Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33(3):1065–1076

    MathSciNet  MATH  Article  Google Scholar 

  51. Pedro H, Coimbra C (2012) Assessment of forecasting techniques for solar power production with no exogenous inputs. Sol Energy 86(7):2017–2028. https://doi.org/10.1016/j.solener.2012.04.004

    Article  Google Scholar 

  52. Pelland S, Galanis G, Kallos G (2013) Solar and photovoltaic forecasting through post-processing of the global environmental multiscale numerical weather prediction model. Prog Photovolt Res Appl 21(3):284–296

    Article  Google Scholar 

  53. Principe JC (2010) Information theoretic learning: Renyi’s entropy and kernel perspectives, chap 5. Springer, Berlin, pp 181–218

    Book  Google Scholar 

  54. Principe JC, Xu D (1999a) Information-theoretic learning using renyi’s quadratic entropy. In: Jutten C, Loubaton P, Cardoso JF (eds) Proceedings of the first international workshop on independent component analysis and signal separation, Aussois, pp 407–412

  55. Principe JC, Xu D (1999b) An introduction to information theoretic learning. In: Neural networks, international joint conference on, IEEE, IJCNN ’99, vol 3, pp 1783–1787

  56. Rashkovska A, Novljan J, Smolnikar M, Mohorčič M, Fortuna C (2015) Online short-term forecasting of photovoltaic energy production. In: Innovative smart grid technologies conference (ISGT), 2015 IEEE power and energy society, IEEE, ISGT 2015

  57. Rényi A (1976) Selected papers of alfred renyi, vol. 2akademia kiado

  58. Rinzivillo S, Turini F (2007) Knowledge discovery from spatial transactions. J Intell Inf Syst 28(1):1–22

    Article  Google Scholar 

  59. Sharma N, Sharma P, Irwin DE, Shenoy PJ (2011) Predicting solar generation from weather forecasts using machine learning. In: SmartGridComm, IEEE, pp 528–533

  60. Sheela KG, Deepa S (2013) Review on methods to fix number of hidden neurons in neural networks. Math Probl Eng 2013:425740. https://doi.org/10.1155/2013/425740

    Article  Google Scholar 

  61. Stojanova D, Ceci M, Appice A, Dzeroski S (2012) Network regression with predictive clustering trees. Data Min Knowl Discov 25(2):378–413

    MathSciNet  MATH  Article  Google Scholar 

  62. Stojanova D, Ceci M, Appice A, Malerba D, Dzeroski S (2013) Dealing with spatial autocorrelation when learning predictive clustering trees. Ecol Inform 13:22–39. https://doi.org/10.1016/j.ecoinf.2012.10.006

    Article  Google Scholar 

  63. Tastu J, Pinson P, Trombe PJ, Madsen H (2014) Probabilistic forecasts of wind power generation accounting for geographically dispersed information. IEEE Trans Smart Grid 5(1):480–489

    Article  Google Scholar 

  64. Thompson SK (1990) Adaptive cluster sampling. J Am Stat Assoc 85(412):1050–1059

    MathSciNet  MATH  Article  Google Scholar 

  65. Usaola J, Ravelo O, Gonzlez G, Soto F, DvilaMC Daz-Guerra B (2004) Benefits for wind energy in electricitymarkets from using short term wind power prediction tools; asimulation study. Wind Eng 28(1):119–127

    Article  Google Scholar 

  66. Yang H, Kurtz B, Nguyen D, Urquhart B, Chow C, Ghonima M, Kleissl J (2014) Solar irradiance forecasting using a ground-based sky imager developed at uc san diego. Sol Energy 103:502–524. https://doi.org/10.1016/j.solener.2014.02.044

    Article  Google Scholar 

  67. Zhang J, Florita A, Hodge BM, Lu S, Hamann H, Banunarayanan V, Brockway A (2015a) A suite of metrics for assessing the performance of solar power forecasting. Sol Energy 111:157–175. https://doi.org/10.1016/j.solener.2014.10.016

    Article  Google Scholar 

  68. Zhang J, Hodge BM, Lu S, Hamann H, Lehman B, Simmons J, Campos E, Banunarayanan V, Black J, Tedesco J (2015b) Baseline and target values for regional and point pv power forecasts: toward improved solar forecasting. Sol Energy 122:804–819. https://doi.org/10.1016/j.solener.2015.09.047

    Article  Google Scholar 

  69. Zhao M, Li X (2011) An application of spatial decision tree for classification of air pollution index. In: Geoinformatics, 2011 19th international conference on, IEEE, pp 1–6

  70. Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J R Stat Soc Ser B (Stat Methodol) 67(2):301–320

    MathSciNet  MATH  Article  Google Scholar 

Download references

Acknowledgements

The research described in this paper has been funded by the Ministry of Education, Universities and Research (MIUR) through the projects “ComESto - Community Energy Storage: Gestione Aggregata di Sistemi d’Accumulo dell’Energia in Power Cloud” (Grant No. ARS01_01259) and “Vi-POC: Virtual Power Operation Center” (Grant PAC02L1_00269). We also acknowledge the support of the European commission through the projects MAESTRA - Learning from Massive, Incompletely annotated, and Structured Data (Grant ICT-2013-612944) and “TOREADOR - TrustwOrthy model-awaRE Analytics Data platform” (Grant 988797). The computational work has been carried out on the resources provided by the projects ReCaS (PONa3_00052) and PRISMA (PON04a2_A). The authors also wish to thank Lynn Rudd for her help in reading the manuscript.

Author information

Affiliations

Authors

Corresponding authors

Correspondence to Michelangelo Ceci or Roberto Corizzo.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Responsible editor: Alípio Jorge, Rui L. Lopes, German Larrazabal.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ceci, M., Corizzo, R., Malerba, D. et al. Spatial autocorrelation and entropy for renewable energy forecasting. Data Min Knowl Disc 33, 698–729 (2019). https://doi.org/10.1007/s10618-018-0605-7

Download citation

Keywords

  • Entropy
  • Spatial autocorrelation
  • Artificial neural networks
  • Photovoltaic power
  • Forecasting