Skip to main content
SpringerLink
Log in

Mean shift densification of scarce data sets in short-term electric power load forecasting for special days

  • Original Paper
  • Published:
Electrical Engineering Aims and scope Submit manuscript

Abstract

Short-term load forecasting plays an important role to the operation of electric systems, as a key parameter for planning maintenances and to support the decision making process on the purchase and sale of electric power. A particular case in this respect is the consumption forecasting on special days, which can be a complex task as it presents unusual load behavior, when compared to regular working days. Moreover, its reduced number of samples makes it hard to properly train and validate more complex and nonlinear prediction algorithms. This paper tackles this problem by proposing a new approach to improve the accuracy of the predictions amidst existing special days, employing an Information Theoretic Learning Mean Shift algorithm for pattern discovery, classifying and densifying the available scarce consumption data. The paper describes how this methodology was applied to an electrical load forecasting problem in the northern region of Brazil, improving the previously obtained accuracy held by the power company.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

References

  1. Shao Z et al (2015) Multivariate statistical and similarity measure based semiparametric modeling of the probability distribution: A novel approach to the case study of mid-long term electricity consumption forecasting in China. Appl Energy 156:502–518

    Article  Google Scholar 

  2. Quilumba FL et al (2015) Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities. IEEE Trans Smart Grid 6(2):911–918

  3. Paparoditis E, Sapatinas T (2013) Short-term load forecasting: the similar shape functional time-series predictor. IEEE Trans Power Syst 28(4):3818–3825

    Article  Google Scholar 

  4. Hong T, Fan S (2016) Probabilistic electric load forecasting: a tutorial review. Int J Forecast

  5. Ko CN, Lee CM (2013) Short-term load forecasting using SVR (support vector regression)-based radial basis function neural network with dual extended Kalman filter. Energy 49:413–422

    Article  Google Scholar 

  6. Friedrich L, Afshari A (2015) Short-term forecasting of the Abu Dhabi electricity load using multiple weather variables. Energy Proc 75:3014–3026

    Article  Google Scholar 

  7. Fidalgo JN, Lopes J (2005) Load forecasting performance enhancement when facing anomalous events. IEEE Trans Power Syst 20(1):408–415

    Article  Google Scholar 

  8. Zhao Y et al (2009)Short-term load forecasting: multi-level wavelet neural networks with holiday corrections. Power and Energy Society General Meeting (2009) PES’09. IEEE, IEEE 2009

  9. Arora S, Taylor JW (2013) Short-term forecasting of anomalous load using rule-based triple seasonal methods. IEEE Trans Power Syst 28(3):3235–3242

    Article  Google Scholar 

  10. Chakhchoukh Y, Panciatici P, Mili L (2011) Electric load forecasting based on statistical robust methods. IEEE Trans Power Syst 26(3):982–991

    Article  Google Scholar 

  11. Fernandes RSS et al (2011) Day ahead load forecasting models for holidays in Indian context. In: 2011 International Conference on Power and Energy Systems (ICPS). IEEE

  12. Mu Q et al (2010) Short-term load forecasting using improved similar days method. In: Power and Energy Engineering Conference (APPEEC), 2010 Asia-Pacific. IEEE

  13. Jiang A, Liang N (2014) Short-term load forecasting using support vector machine optimized by the improved fruit fly algorithm and the similar day method. In: Electricity Distribution (CICED), 2014 China International Conference on. IEEE

  14. Wi YM, Joo SK, Song KB (2012) Holiday load forecasting using fuzzy polynomial regression with weather feature selection and adjustment. IEEE Trans Power Syst 27(2):596–603

    Article  Google Scholar 

  15. Rao S et al (2006) Information theoretic mean shift algorithm. Machine Learning for Signal Processing, 2006. In: Proceedings of the 2006 16th IEEE Signal Processing Society Workshop on. IEEE

  16. Rao S, Allan de Medeiros M, Príncipe J (2009) Mean shift: an information theoretic perspective. Patt Recognit Lett 30(3):222–230

    Article  Google Scholar 

  17. Miranda V, Castro ARG, Lima S (2012) Diagnosing faults in power transformers with autoassociative neural networks and mean shift. IEEE Trans Power Delivery 27(3):1350–1357

  18. Motlagh O, Grozev G, Papageorgiou EI (2016) A neural approach to electricity demand forecasting. Artificial neural network modelling. Springer International Publishing, pp 281–306

  19. Dilhani MS, Jeenanunta C (2016) Daily electric load forecasting: case of Thailand. In: 2016 7th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES). IEEE

  20. Mulyadi Y et al (2015) Anomalous STLF for Indonesia power system using Artificial Neural Network. In: 2015 International Conference on Science and Technology (TICST). IEEE

  21. Cho H et al (2015) Modelling and forecasting daily electricity load via curve linear regression. Modeling and stochastic learning for forecasting in high dimensions. Springer International Publishing, pp 35–54

  22. Raza MQ, Baharudin Z, Nallagownden P (2014) A comparative analysis of PSO and LM based NN short term load forecast with exogenous variables for smart power generation. In: 2014 5th International Conference on Intelligent and Advanced Systems (ICIAS). IEEE

  23. Cevik HH, Cunkas M (2014) A comparative study of artificial neural network and ANFIS for short term load forecasting. In: 2014 6th International Conference on Electronics, Computers and Artificial Intelligence (ECAI). IEEE

  24. Mirhosseini M, Marzband M, Oloomi M (2009) Short term load forecasting by using neural network structure. In: Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2009. ECTI-CON 2009. 6th International Conference on, vol. 1. IEEE

  25. Kelman J (2005) Atlas de Energia Elétrica do Brasil/Agência Nacional de Energia Elétrica. ANEEL, Technical report, Brasília

  26. de Geração, BIG-Banco de Informações (2015) Capacidade de Geração do Brasil. ANEEL. http://www.aneel.gov.br. Accessed 20 May 2016

  27. Limberger MAC, Souza RC, Calili RF (2014) Estudo da tarifa branca para classe residencial pela medição de consumo de energia e de pesquisas de posse e hábitos. Diss. Dissertação de Mestrado. Pós-graduação em Metrologia. Pontifícia Universidade Católica do Rio de Janeiro. Rio de Janeiro

  28. ANEEL (2012) Resolução Normativa No. 499

  29. ANEEL (2010) Resolução Normativa No. 414

  30. Muñoz F et al (2014) Tarifa Horária Branca: 2015 é um horizonte factível?. Fundação Getúlio Vargas. http://bibliotecadigital.fgv.br/ojs/index.php/bc/article/view/53895. Accessed 19 May 2016

  31. Kang H, Lee SH, Lee J (2010) Image segmentation based on fuzzy flood fill mean shift algorihm. In: Fuzzy Information Processing Society (NAFIPS), 2010 Annual Meeting of the North American. IEEE

  32. Khan ZH, Gu IYH, Backhouse A (2009) Joint particle filters and multi-mode anisotropic mean shift for robust tracking of video objects with partitioned areas. In: 2009 16th IEEE International Conference on Image Processing (ICIP). IEEE

  33. Sumaili J et al (2011) Finding representative wind power scenarios and their probabilities for stochastic models. In: 2011 16th International Conference on Intelligent System Application to Power Systems (ISAP). IEEE

  34. Sumaili J et al (2011) On the use of information theoretic mean shift for electricity load patterns clustering. In: 2011 IEEE Trondheim on PowerTech. IEEE

  35. Yuan XT, Li SZ (2009) Stochastic gradient kernel density mode-seeking. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE

  36. Fukunaga K, Hostetler LD (1975) The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans Inf Theory 21(1):32–40

    Article  MathSciNet  MATH  Google Scholar 

  37. Friedman J, Hastie T, Tibshirani R (2001) The elements of statistical learning, vol. 1. Springer, Berlin: Springer series in statistics

  38. de Santana AL et al (2007) Strategies for improving the modeling and interpretability of Bayesian networks. Data Knowl Eng 63(1):91–107

  39. Carević S, Capuder T, Delimar M (2010) Applications of clustering algorithms in long-term load forecasting. In: Energy Conference and Exhibition (EnergyCon), 2010 IEEE International. IEEE

  40. Dillon WR, Goldstein M (1984) Multivariate analysis: methods and applications

  41. De Livera AM, Hyndman RJ, Snyder RD (2011) Forecasting time series with complex seasonal patterns using exponential smoothing. J Am Stat Assoc 106(496):1513–1527

  42. Rocha CA et al (2006) Decision support in power systems based on load forecasting models and influence analysis of climatic and socio-economic factors. In: Optics East 2006. International Society for Optics and Photonics

  43. Kohonen T (1988) The ‘neural’ phonetic typewriter. Computer 21(3):11–22

    Article  Google Scholar 

  44. Sammon JW (1969) A nonlinear mapping for data structure analysis. IEEE Trans Compu 5:401–409

  45. Webberley A, Gao DW (2013) Study of artificial neural network based short term load forecasting. In: Power and Energy Society General Meeting (PES), 2013 IEEE. IEEE

  46. Perdas na distribuição: baixa tensão, altos prejuízos—Reportagem Especial Canal Energia (2013) Associação Brasileira de Distribuidores de Energia Elétrica (ABRADEE). http://www.abradee.com.br/imprensa/artigos-e-releases/1018-perdas-na-distribuicao-baixa-tensao-altos-prejuizos-reportagem-especial-canal-energia. Accessed 22 May 2016

Download references

Acknowledgments

The authors gratefully acknowledge the utility that supplied the data for this work, whose identification is not disclosed for reasons of confidentiality, and the contributions of their staff as domain experts. The conditions for development of the cooperation of the authors from INESC TEC (Portugal) were supported by the ERDF – European Regional Development Fund, through the Operational Programme for Competitiveness and Internationalization – COMPETE 2020 within action POCI-01-0145-FEDER-006961 and by FCT (Portuguese Foundation for Science and Technology) as part of the strategic project UID/EEA/50014/2013.

Author information

Authors and Affiliations

  1. Laboratory of High Performance Networks Planning, Federal University of Pará, Augusto Correa Street, 01, CO 479, Belém, PA, Brazil

    Liviane Rego, Carlos Francês, Marcelino Silva & Ádamo Santana

  2. INESC Technology and Science, Porto, Portugal

    Jean Sumaili & Vladimiro Miranda

  3. Universidade do Porto, Porto, Portugal

    Vladimiro Miranda

Authors
  1. Liviane Rego
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jean Sumaili
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Vladimiro Miranda
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Carlos Francês
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Marcelino Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ádamo Santana
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Liviane Rego.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rego, L., Sumaili, J., Miranda, V. et al. Mean shift densification of scarce data sets in short-term electric power load forecasting for special days. Electr Eng 99, 881–898 (2017). https://doi.org/10.1007/s00202-016-0424-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00202-016-0424-z

Keywords

Search

Navigation