IE interfaces (산업공학)

Korean Institute of Industrial Engineers (대한산업공학회)
권호 표지
DOI QR코드

DOI QR Code

Electricity Demand Forecasting based on Support Vector Regression

Support Vector Regression에 기반한 전력 수요 예측

  • 이형로 (아주대학교 산업공학과) ;
  • 신현정 (아주대학교 산업공학과)
  • Received : 2011.08.31
  • Accepted : 2011.11.02
  • Published : 2011.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Forecasting of electricity demand have difficulty in adapting to abrupt weather changes along with a radical shift in major regional and global climates. This has lead to increasing attention to research on the immediate and accurate forecasting model. Technically, this implies that a model requires only a few input variables all of which are easily obtainable, and its predictive performance is comparable with other competing models. To meet the ends, this paper presents an energy demand forecasting model that uses the variable selection or extraction methods of data mining to select only relevant input variables, and employs support vector regression method for accurate prediction. Also, it proposes a novel performance measure for time-series prediction, shift index, followed by description on preprocessing procedure. A comparative evaluation of the proposed method with other representative data mining models such as an auto-regression model, an artificial neural network model, an ordinary support vector regression model was carried out for obtaining the forecast of monthly electricity demand from 2000 to 2008 based on data provided by Korea Energy Economics Institute. Among the models tested, the proposed method was shown promising results than others.

Keywords

References

  1. Bishop, C. M. (2006), Pattern recognition and machine learning, Springer.
  2. Choi, N. H., Son, K. M., and Lee, T. G. (2001), Daily peak load forecasting considering the load trend and temperature, Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, 6(6), 35-42.
  3. Cristianini, N. and Taylor, J. S. (2000), An Introduction to support vector machines and other kernel based learning methods, Cambridge University Press.
  4. Hall, M. A. (1999), Correlation-based Feature Selection for Machine Learning, The University of Waikato Press.
  5. Han, C. H., Lee, J. W., and Lee, K. K. (2009), Analyzing Information Value of Temperature Forecast for the Electricity Demand Forecasts, The Korean Operations Research and Management Science Society, 26(1), 79-91.
  6. Han, S. M. (2009), A study on the development of the generation expansion planning system using multi-criteria decision making rule, Ph.D diss, Hongik University.
  7. Harvey, A. C. and Koopmand, S. J. (1993), Forecasting Hourly Electricity Demand using Time-varying splines, Journal of the American Statistical Association, 88(424), 1228-1236. https://doi.org/10.1080/01621459.1993.10476402
  8. Haykin, S. (1999), Neural networks: a comprehensive foundation, Prentice-Hall, Inc.
  9. Hong, W. C. (2009), Electric Load Forecasting by Support Vector Model, Applied Mathematical Modelling, 33(5), 2444-2454. https://doi.org/10.1016/j.apm.2008.07.010
  10. Khotanzad, A., Davis, M. H., Abaye, A., and Maratukulam, D. J. (1996), An Artificial Neural Network Hourly Temperature Forecaster with Applications in Load Forecasting, Journal of Power Systems, 11(2), 870-876. https://doi.org/10.1109/59.496168
  11. Kim, J. H., Lee, J. G., and Cha, J. M. (2009), Load forecasting and demand management considering with renewable energy, The Korean Institute of Electrical Engineers, 2260-2261.
  12. Kitagawa, G. and Gersch, W. (1996), Smoothness Priors Analysis o] Time Series, Lecture Notes in Statistics, Springer-Verlag.
  13. Kong, D. S., Kwak, Y. H., and Huh, J. H. (2010), Artificial Neural Network Based Energy Demand Prediction for the Urban District Energy Planning, Journal of the Architectural Institute of Korea, 26(2), 221-230.
  14. Kwon, S. K. (2004), The Present Situation of District Heating in Korea and Foreign Countries, The Society of Air-conditioning and Refrigerating Engineers of Korea, 1217-1222.
  15. Mirasgedis, S., Sarafidis, Y., Georgo Poulou, E., Lalas, D. P., Moschovits, M. Karagiannis, F., and Papakonstantinou, D. (2006), Models for mid-term electricity demand forecasting incorporating weather influences, Energy, 31(2-3), 208-227. https://doi.org/10.1016/j.energy.2005.02.016
  16. Nam, B. W., Song, K. B., Kim, K. H., and Cha, J. M. (2008), The Spatial Electric Load Forecasting Algorithm using the Multiple Regression Analysis Method, Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, 22(2), 63-70. https://doi.org/10.5207/JIEIE.2008.22.2.063
  17. Nrgaard, M. and Norgaard, P. M. (2006), Neural Networks for Modelling and Control of Dynamic Systems : A Practitioner's Handbook(Advanced Textbooks in Control and Signal Processing), Springer.
  18. Pai, P. F. and Hong, W. C. (2005), Support vector machines with simulated annealing algorithms in electricity load forecasting, Energy Conversion and Management, 46(17), 2669-2688. https://doi.org/10.1016/j.enconman.2005.02.004
  19. Pappas, S. Sp., Ekonomou, L., Karampelas, P., Karamousantas, D. C., Katsikas, S. K., Chatzarakis, G. E., and Skafidas, P. D. (2010), Electricity demand load forecasting of the Hellenic power system using an ARMA model, Electric Power Systems Research, 80(3), 256-264. https://doi.org/10.1016/j.epsr.2009.09.006
  20. Park, C. K. (2006), Estimating Software Development Cost USING Support Vector Regression, The Korean Operations Research and Management Science Society, 23(1), 75-91.
  21. Park, K., Hou, T., and Shin, H. (2011), Oil Price Forecasting Based on Machine Learning Techniques, Journal of the Korean Institute of Industrial Engineers, 37(1), 64-73. https://doi.org/10.7232/JKIIE.2011.37.1.064
  22. Romera, E. G., Moran, M. A. J., and Fernandez, D. C. (2008), Monthly electric energy demand forecasting with neural networks and Fourier series, Energy Conversion and Management, 49(11), 3135-3142. https://doi.org/10.1016/j.enconman.2008.06.004
  23. Shin, J. H. and Hong, Y. C. (2006), GMDH Algorithm with Data Weighting Performance and Its Application to Power Demand Forecasting, Journal of Control Automation and Systems Engineering, 12(7).
  24. Sholkopf, B. and Smola, A. (2002), Learning with Kernels, MIT Press, Cambridge MA.
  25. Srinivasan, D. (2008), Energy Demand Prediction using GMDH networks, Nuerocomputing, 72(1-3), 625-629. https://doi.org/10.1016/j.neucom.2008.08.006
  26. Thissen, U., van Brakel, R., de Weijer A. P., Melssen, W. J., and Buydens, L. M. C. (2003), Using Support Vector Machines for time series prediction, Chemometrics and Intelligent Laboratory Systems, 69(1-2), 35-49. https://doi.org/10.1016/S0169-7439(03)00111-4
  27. Wenwu, H., Zhizhong, W., and Hui, J. (2008), Model Optimizing and Feature Selection for Support Vector Regression in time series forecasting, Neurocomputing, 72(1-3), 600-611. https://doi.org/10.1016/j.neucom.2007.11.010
  28. Wi, Y. M., Moon, G. H., Lee, J. H., Joo, S. K., and Song, K. B. (2007), Load Forecasting for the Holidays using a Polynomial Regression Incorporating Temperature Effect, The Korean Institute of Electrical Engineers, 29-30.
  29. Yang, J., Rivard, H., and Zmeureanu, R. (2005), On-line building energy prediction using adaptive artificial neural networks, Energy and Buildings, 37(12), 1250-1259. https://doi.org/10.1016/j.enbuild.2005.02.005

Cited by

  1. Electricity Price Prediction Based on Semi-Supervised Learning and Neural Network Algorithms vol.39, pp.1, 2013, https://doi.org/10.7232/JKIIE.2013.39.1.030
  2. Development of Daily Peak Power Demand Forecasting Algorithm using ELM vol.62, pp.4, 2013, https://doi.org/10.5370/KIEEP.2013.62.4.169
  3. Development of Daily Peak Power Demand Forecasting Algorithm with Hybrid Type composed of AR and Neuro-Fuzzy Model vol.63, pp.3, 2014, https://doi.org/10.5370/KIEEP.2014.63.3.189
  4. Development of Daily Peak Power Demand Forecasting Algorithm Considering of Characteristics of Day of Week vol.63, pp.4, 2014, https://doi.org/10.5370/KIEEP.2014.63.4.307
  5. Development of Peak Power Demand Forecasting Model for Special-Day using ELM vol.64, pp.2, 2015, https://doi.org/10.5370/KIEEP.2015.64.2.074
  6. The Prediction and Analysis of the Power Energy Time Series by Using the Elman Recurrent Neural Network vol.41, pp.1, 2018, https://doi.org/10.11627/jkise.2018.41.1.084