On-line quantile regression in the RKHS (Reproducing Kernel Hilbert Space) for operational probabilistic forecasting of wind power
作者： Cristobal Gallego-Castillo , Ricardo Bessa , Laura Cavalcante , Oscar Lopez-Garcia
DOI: 10.1016/J.ENERGY.2016.07.055
关键词:
摘要: Abstract Wind power probabilistic forecast is being used as input in several decision-making problems, such stochastic unit commitment, operating reserve setting and electricity market bidding. This work introduces a new on-line quantile regression model based on the Reproducing Kernel Hilbert Space (RKHS) framework. Its application to field of wind forecasting involves discussion choice bias term models, consideration operational framework order mimic real conditions. Benchmark against linear splines models was performed for case study during 18 months period. Model parameter selection k -fold crossvalidation. Results showed noticeable improvement terms calibration, key criterion industry. Modest improvements Continuous Ranked Probability Score (CRPS) were also observed prediction horizons between 6 20 h ahead.
sci-hub.se 参考文章(45)
Cristobal Gallego-Castillo, Alvaro Cuerva-Tejero, Ricardo J. Bessa, Laura Cavalcante, Wind power probabilistic forecast in the Reproducing Kernel Hilbert Space power systems computation conference. pp. 1- 7 ,(2016) , 10.1109/PSCC.2016.7540830
R. A. Brown, T. J. Hastie, R. J. Tibshirani, Generalized Additive Models. Biometrics. ,vol. 47, pp. 785- ,(1991) , 10.2307/2532174
G Giebel, C Draxl, G Kariniotakis, R Brownsword, M Denhard, The state-of-the-art in short-term prediction of wind power. A literature overview ,(2011)
Emil B Iversen, Juan M Morales, Jan K Møller, Henrik Madsen, None, Short-term probabilistic forecasting of wind speed using stochastic differential equations International Journal of Forecasting. ,vol. 32, pp. 981- 990 ,(2016) , 10.1016/J.IJFORECAST.2015.03.001
Cristobal Gallego-Castillo, Alvaro Cuerva-Tejero, Oscar Lopez-Garcia, A review on the recent history of wind power ramp forecasting Renewable & Sustainable Energy Reviews. ,vol. 52, pp. 1148- 1157 ,(2015) , 10.1016/J.RSER.2015.07.154
Claudio Monteiro, Ricardo Bessa, V Miranda, Audun Botterud, Jianhui Wang, G Conzelmann, None, Wind power forecasting : state-of-the-art 2009. Argonne National Laboratory. ,(2009) , 10.2172/968212
Ginés Rubio, Héctor Pomares, Luis J. Herrera, Ignacio Rojas, Kernel methods applied to time series forecasting international work-conference on artificial and natural neural networks. pp. 782- 789 ,(2007) , 10.1007/978-3-540-73007-1_94
Ricardo Bessa, Carlos Moreira, Bernardo Silva, Manuel Matos, Handling renewable energy variability and uncertainty in power systems operation Wiley Interdisciplinary Reviews: Energy and Environment. ,vol. 3, pp. 156- 178 ,(2014) , 10.1002/WENE.76
P. Pinson, Very-short-term probabilistic forecasting of wind power with generalized logit-normal distributions Journal of the Royal Statistical Society: Series C (Applied Statistics). ,vol. 61, pp. 555- 576 ,(2012) , 10.1111/J.1467-9876.2011.01026.X
Alex J. Smola, Bernhard Schölkopf, A tutorial on support vector regression Statistics and Computing. ,vol. 14, pp. 199- 222 ,(2004) , 10.1023/B:STCO.0000035301.49549.88