© The Institution of Engineering and Technology
Electricity price forecasting has become the focus of considerable interest in a deregulated energy market. In this study, regression tree-based models: classification and regression trees, Bagging and Random Forests have been built and used to identify the variables dominating the marginal price of the commodity as well as for short-term (one hour and day ahead) electricity price forecasting for the Spanish–Iberian market. Different prediction models are proposed including the main features of the market such as load, hydro and thermal generation and from available, wind energy production, of strategic interest in the Spanish market. In addition other explanatory variables are considered as lagged prices, as well as hour, day, month and year indicators. In the study, hourly data from 2000–2011 corresponding to 22 variables have been used. The results show the effectiveness of the proposed ensemble of tree-based models which emerge as an alternative and promising tool, competitive with other existing methods.
References
-
-
1)
-
23. García-Martos, C., Caro, E., Sánchez, M.J.: ‘Electricity prices forecasting accounting for renewable energies: optimal combined forecasts’. , Statistical Laboratory, Technical University of Madrid, 2012.
-
2)
-
18. Reston Filho, J.C., Alfonso, C.M., Oliveira, R.C.L.: ‘Pricing analysis in the Brazilian energy market: a decision tree approach’. Power Tech. IEEE, 2009, Bucharest, 28 June 2009–2 July 2009, .
-
3)
-
22. Zhao, J.H., Dong, Z.Y., Li, X.: ‘Electricity market price spike forecasting and decision making’, IET Gener. Transm. Distrib., 2007b, 1, (4), pp. 647–654 (doi: 10.1049/iet-gtd:20060217).
-
4)
-
39. Troncoso, A., Riquelme, J.M., Gómez, A., Martínez, J.L., Riquelme, J.C.: ‘Electricity market price forecasting based on weighted nearest neighbors techniques’, IEEE Trans. Power Syst., 2007, 22, pp. 1294–1301 (doi: 10.1109/TPWRS.2007.901670).
-
5)
-
28. Azzalini, A., Scarpa, B.: ‘Data analysis and data mining’ (Oxford, 2012).
-
6)
-
20. Amjady, N., Daraeepour, A.: ‘Design of input vector for day-ahead price forecasting of electricity markets’, Exp. Syst. Appl., 2009, 36, pp. 12281–12294 (doi: 10.1016/j.eswa.2009.04.059).
-
7)
-
S. Fan ,
C. Mao ,
L. Chen
.
Next-day electricity-price forecasting using a hybrid network.
IET Gener. Transm. Distrib.
,
1 ,
176 -
182
-
8)
-
N. Amjady ,
A. Daraeepour ,
F. Keynia
.
Day-ahead electricity price forecasting by modified relief algorithm and hybrid neural network.
IET Gener. Transm. Distrib.
,
3 ,
432 -
444
-
9)
-
7. García-Martos, C., Rodríguez, J., Sánchez, M.J.: ‘Forecasting electricity prices by extracting dynamic common factors: application to the Iberian Market’, IET Gener. Transm. Distrib., 2011, 1, pp. 1–10.
-
10)
-
29. Breimann, L.: ‘Bagging predictors’, Mach. Learn., 1996, 24, pp. 123–140.
-
11)
-
37. Shih, Y.S., Tsai, H.W.: ‘Variable selection bias in regression trees with constant fits’, Comp. Stat. Data Anal., 2004, 45, pp. 595–607 (doi: 10.1016/S0167-9473(03)00036-7).
-
12)
-
S.J. Koopman ,
M. Ooms ,
M.A. Carnero
.
Periodic seasonal reg-ARFIMA-GARCH models for daily electricity spot prices.
J. Am. Stat. Assoc.
,
477 ,
16 -
27
-
13)
-
35. Díaz-Uriarte, R., Álvarez de Andrés, S.: ‘Gene selection and classification of microarray data using random forests’, BMC Bioinf., 2006, 7, p. 3 (doi: 10.1186/1471-2105-7-3).
-
14)
-
17. Mori, H., Awata, A.: ‘Data mining of electricity price forecasting with regression tree and normalized radial basis function network’. Proc. of the IEEE Int. Conf. on Systems, Man and Cybernetics, 2007, .
-
15)
-
14. Neupane, B., Perera, K.S., Aung, Z., Woon, W.L.: ‘Artificial neural network-based electricity price forecasting for smart grid deployment’. Int. Conf. on Computer Systems and Industrial Informatics (ICCSII), 18–20 December, 2012, .
-
16)
-
32. Ishwaran, H.: ‘Variable importance in binary regression trees and forests’, Electr. J. Stats, 2007, 1, pp. 519–537 (doi: 10.1214/07-EJS039).
-
17)
-
31. Grömping, U.: ‘Variable importance assessment in regression: linear regression versus random forest’, Amer. Statistician, 2009, 63, (4), pp. 308–319 (doi: 10.1198/tast.2009.08199).
-
18)
-
A.M. Alonso ,
C. Garcı́a-Martos ,
J. Rodrı́guez ,
M.J. Sánchez
.
Seasonal dynamic factor analysis and bootstrap inference: application to electricity market forecasting.
Technometrics
,
2 ,
137 -
151
-
19)
-
20)
-
C. Garcı́a-Martos ,
J. Rodrı́guez ,
M.J. Sánchez
.
Mixed models for short-run forecasting of electricity prices: application to the spanish market case.
IEEE Trans. Power Syst.
,
2 ,
544 -
552
-
21)
-
22)
-
8. Carpio, J., Juan, J., López, D.: ‘Multivariate exponential smoothing and dynamic factor model applied to hourly electricity price analysis’, Technometrics, 2014, 56, pp. 494–503. (doi: 10.1080/00401706.2013.860920).
-
23)
-
27. Breimann, L., Friedman, J.H., Olshem, J.H., Stone, C.J.: ‘Classification and regression trees’ (Chapman and Hall/CRC, 1984).
-
24)
-
41. Amjady, N., Keynia, F.: ‘Day-ahead price forecasting of electricity markets by mutual information technique and cascaded neuro-evolutionary algorithm’, IEEE Trans. Power Syst., 2009, 24, pp. 306–318 (doi: 10.1109/TPWRS.2008.2006997).
-
25)
-
N. Amjady ,
A. Dareepour
.
Mixed price and load forecasting of electricity markets by a new iterative prediction method.
Electr. Power Syst. Res.
,
1329 -
1336
-
26)
-
33. Strobl, C., Boulesteix, A., Kneib, T., Augustin, T., Zeileis, A.: ‘Conditional variable importance for random forests’, BMC Bioinf., 2008, 9, pp. 307 (doi: 10.1186/1471-2105-9-307).
-
27)
-
L. Breiman
.
Random forests.
Mach. Learn.
,
1 ,
5 -
32
-
28)
-
A.J. Conejo ,
M.A. Plazas ,
R. Espínola ,
A.B. Molina
.
Day-ahead electricity price forecasting using the wavelet transform and ARIMA models.
IEEE Trans. Power Syst.
,
2 ,
1035 -
1042
-
29)
-
36. Genuer, R., Poggi, J.M., Tuleau, C.: ‘Random forest: some methodological insights’. , Institut National de Recherche en Informatique et en Automatique, Saclay, France, 2008, .
-
30)
-
2. García-Martos, C., Rodríguez, J., Sánchez, M.J.: ‘Forecasting electricity prices and their volatilities using unobserved components’, Energy Econ., 2011, 33, pp. 1227–1239 (doi: 10.1016/j.eneco.2011.07.005).
-
31)
-
39. Catalão, J.P.S., Pousinho, H.M.I., Mendes, V.M.F.: ‘Short-term electricity prices forecasting in a competitive market by a hybrid intelligent approach’, Energy Convers. Manage., 2011, 52, pp. 1061–1065 (doi: 10.1016/j.enconman.2010.08.035).
-
32)
-
F. Nogales ,
J. Contreras ,
A. Conejo ,
R. Espinola
.
Forecasting next-day electricity prices by time series models.
IEEE Trans. Power Syst.
,
2 ,
342 -
348
-
33)
-
16. Weron, R.: ‘Modeling and forecasting electricity load prices: a statistical approach’ (The Wiley Finance Series, 2006).
-
34)
-
24. Cruz, A., Muñoz, A., Zamora, J.L., Espínola, R.: ‘The effect of wind generation and weekday on Spanish electricity spot price forecasting’, Electr. Power Syst. Res., 2011, 81, pp. 1924–1935 (doi: 10.1016/j.epsr.2011.06.002).
-
35)
-
31. Zhao, J.H., Dong, Z.Y., Li, X., et al: ‘A framework for electricity price spike analysis with advanced data mining methods’, IEEE Trans. Power Syst., 2007, 22, pp. 376–385 (doi: 10.1109/TPWRS.2006.889139).
-
36)
-
19. R Development Core Team R: ‘A language and environment for statistical computing’ (R Foundation for Statistical Computing, Vienna, Austria, 2008), .
-
37)
-
J. Contreras ,
R. Espínola ,
F.J. Nogales ,
A.J. Conejo
.
ARIMA models to predict next-day electricity prices.
IEEE Trans. Power Syst.
,
3 ,
1014 -
1020
-
38)
-
29. Strobl, C., Boulesteix, A., Zeileis, L.A., Hothorn, T.: ‘Bias in random forest variable importance measures: illustrations, sources and a solution’, BMC Bioinformatics, 2007, 8, p. 25 (doi: 10.1186/1471-2105-8-25).
-
39)
-
21. Aggarwal, S., Saini, L., Kumar, A.: ‘Electricity price forecasting in deregulated markets: a review and evaluation’, International J. Electr. Power Energy Syst., 2009, 31, (1), pp. 13–22 (doi: 10.1016/j.ijepes.2008.09.003).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-gtd.2014.0655
Related content
content/journals/10.1049/iet-gtd.2014.0655
pub_keyword,iet_inspecKeyword,pub_concept
6
6