A comprehensive country-based day-ahead wind power generation forecast model by coupling numerical weather prediction data and CatBoost with feature selection methods for Turkey
Restricted accessResearch articleFirst published online October, 2022
A comprehensive country-based day-ahead wind power generation forecast model by coupling numerical weather prediction data and CatBoost with feature selection methods for Turkey
A country-based day-ahead wind power generation forecast (WPGF) model with a grid selection algorithm and feature selection models was proposed in this study. Atmospheric variables extracted from 300, 500, 700 hPa pressure levels, and surface level of ERA5 reanalysis data with 2.5° spatial resolution were used to train/validate the categorical boosting (CatBoost) model. A special grid selection algorithm was proposed by considering Turkey’s spatial distribution of wind power plants. The day-ahead forecasts of ECMWF’s HRES (High-resolution) were used as the test subset, therefore, paving the way for the operational use of the model. The proposed model could be considered much as a specialized machine learning based downscaling method for country-based WPGF due to using numerical weather prediction model outputs as its input. Results showed that the proposed model that uses fewer features has outperformed the other models with a normalized root mean square error of 7.6% and coefficient of determination of 0.8989.
AhmadiMKhasheiM (2021) Current status of hybrid structures in wind forecasting. Engineering Applications of Artificial Intelligence99: 104133.
2.
AlbergelCZhengYBonanB, et al. (2020) Data assimilation for continuous global assessment of severe conditions over terrestrial surfaces. Hydrology and Earth System Sciences24(9): 4291–4316.
3.
AlizamirMKimSKisiO, et al. (2020) A comparative study of several machine learning based non-linear regression methods in estimating solar radiation: Case studies of the USA and Turkey regions. Energy197: 117239.
4.
ArayaIAValleCAllendeH (2020) A multi-scale model based on the long short-term memory for day ahead hourly wind speed forecasting. Pattern Recognition Letters136: 333–340.
5.
ArcomanoTSzunyoghIPathakJ, et al. (2020) A machine learning-based global atmospheric forecast model. Geophysical Research Letters47(9): e2020GL087776.
6.
BarqueMMartinSVianinJEN, et al. (2018) Improving wind power prediction with retraining machine learning algorithms. In: 2018 International workshop on big data and information security (IWBIS), Jakarta, Indonesia, 12–13 May, pp.43–48. New York, NY: IEEE. DOI: 10.1109/IWBIS.2018.8471713
7.
BitarEYRajagopalRKhargonekarPP, et al. (2012) Bringing wind energy to market. IEEE Transactions on Power Systems27(3): 1225–1235.
8.
BorboudakisGTsamardinosI (2019) Forward-backward selection with early dropping. Journal of Machine Learning Research20(1): 276–314.
9.
CadenasERiveraW (2007) Wind speed forecasting in the south coast of Oaxaca, México. Renewable Energy32(12): 2116–2128.
10.
CaoQEwingBTThompsonMA (2012) Forecasting wind speed with recurrent neural networks. European Journal of Operational Research221(1): 148–154.
11.
CarpinoneAGiorgioMLangellaR, et al. (2015) Markov chain modeling for very-short-term wind power forecasting. Electric Power Systems Research122: 152–158.
ClevelandWSGrosseEShyuWM (1992) Local regression models. Chapter 8. In: ChambersJMHastieTJ (eds) Statistical Models in S. Pacific Grove, CA: Wadsworth & Brooks/Cole, pp.309–376.
14.
da SilvaRGRibeiroMHDMMorenoSR, et al. (2021) A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting. Energy216: 119174.
15.
DemolliHDokuzASEcemisA, et al. (2019) Wind power forecasting based on daily wind speed data using machine learning algorithms. Energy Conversion and Management198: 111823.
16.
DemšarJ (2006) Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research7: 1–30.
17.
DieboldFXMarianoRS (1995) Comparing predictive accuracy. Journal of Business and Economic Statistics13: 253–263.
18.
DingYChenZLuW, et al. (2021) A CatBoost approach with wavelet decomposition to improve satellite-derived high-resolution PM2.5 estimates in Beijing-Tianjin-Hebei. Atmospheric Environment249: 118212.
19.
DuanJZuoHBaiY, et al. (2021) Short-term wind speed forecasting using recurrent neural networks with error correction. Energy217: 119397.
FengCCuiMHodgeBM, et al. (2017) A data-driven multi-model methodology with deep feature selection for short-term wind forecasting. Applied Energy190: 1245–1257.
24.
FlomPLCassellDL (2007) Stopping stepwise: Why stepwise and similar selection methods are bad, and what you should use. In: NorthEast SAS Users Group Inc 20th annual conference, Baltimore, MD, 11–14 November, Vol. 11.
25.
FontiVBelitserE (2017) Feature selection using lasso. VU Amsterdam Research Paper in Business Analytics30: 1–25.
26.
ForbesKFZampelliEM (2020) Accuracy of wind energy forecasts in Great Britain and prospects for improvement. Utilities Policy67: 101111.
27.
FrazierPI (2018) A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811.
28.
FriedmanJHastieTTibshiraniR (2010) Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software33(1): 1–22.
29.
FriedmanM (1940) A comparison of alternative tests of significance for the problem of m rankings. The Annals of Mathematical Statistics11(1): 86–92.
30.
GarcíaIHuoSPradoR, et al. (2020) Dynamic Bayesian temporal modeling and forecasting of short-term wind measurements. Renewable Energy161: 55–64.
31.
HancockJTKhoshgoftaarTM (2020) CatBoost for big data: An interdisciplinary review. Journal of Big Data7(1): 94.
32.
HayesLStocksMBlakersA (2021) Accurate long-term power generation model for offshore wind farms in Europe using ERA5 reanalysis. Energy229: 120603.
33.
HuangGWuLMaX, et al. (2019) Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions. Journal of Hydrology574: 1029–1041.
34.
HyndmanRJAthanasopoulosG (2018) Forecasting: Principles and Practice. Melbourne: OTexts.
JacksonDA (1993) Stopping rules in principal components analysis: A comparison of heuristical and statistical approaches. Ecology74(8): 2204–2214.
37.
JiangYZhaoNPengL, et al. (2019) A new hybrid framework for probabilistic wind speed prediction using deep feature selection and multi-error modification. Energy Conversion and Management199: 111981.
38.
JungJBroadwaterRP (2014) Current status and future advances for wind speed and power forecasting. Renewable and Sustainable Energy Reviews31: 762–777.
39.
KassRERafteryAE (1995) Bayes factors. Journal of the American Statistical Association90(430): 773–795.
40.
KisvariALinZLiuX (2021) Wind power forecasting – A data-driven method along with gated recurrent neural network. Renewable Energy163: 1895–1909.
41.
LahouarABen Hadj SlamaJ (2017) Hour-ahead wind power forecast based on random forests. Renewable Energy109: 529–541.
LiuHDuanZChenC (2020a) Wind speed big data forecasting using time-variant multi-resolution ensemble model with clustering auto-encoder. Applied Energy280: 115975.
44.
LiuXZhangHKongX, et al. (2020b) Wind speed forecasting using deep neural network with feature selection. Neurocomputing397: 393–403.
45.
MalhanPMittalM (2022) A novel ensemble model for long-term forecasting of wind and hydro power generation. Energy Conversion and Management251: 114983.
46.
NatekinAKnollA (2013) Gradient boosting machines, a tutorial. Frontiers in Neurorobotics7: 21.
ÖzenCDinçUDenizA, et al. (2021) Wind power generation forecast by coupling numerical weather prediction model and gradient boosting machines in Yahyalı wind power plant. Wind Engineering45(5): 1256–1272.
49.
PedregosaFVaroquauxGGramfortA, et al. (2011) Scikit-learn: Machine learning in Python. Journal of Machine Learning Research12: 2825–2830.
50.
PoggiPMuselliMNottonG, et al. (2003) Forecasting and simulating wind speed in Corsica by using an autoregressive model. Energy Conversion and Management44(20): 3177–3196.
51.
ProkhorenkovaLGusevGVorobevA, et al. (2017) CatBoost: unbiased boosting with categorical features. arXiv preprint arXiv:1706.09516.
52.
PrósperMAOtero-CasalCFernándezFC, et al. (2019) Wind power forecasting for a real onshore wind farm on complex terrain using WRF high resolution simulations. Renewable Energy135: 674–686.
53.
PutzDGumhalterMAuerH (2021) A novel approach to multi-horizon wind power forecasting based on deep neural architecture. Renewable Energy178: 494–505.
54.
QinLXiongYLiuK (2019) Weather division-based wind power forecasting model with feature selection. IET Renewable Power Generation13(16): 3050–3060.
55.
Republic of Turkey Ministry of Energy and Natural Resources (2020) Energy investments. Available at: https://enerji.gov.tr/eigm-raporlari (accessed 20 December 2020).
56.
RibeiroMHDMda SilvaRGMorenoSR, et al. (2022) Efficient bootstrap stacking ensemble learning model applied to wind power generation forecasting. International Journal of Electrical Power & Energy Systems136: 107712.
57.
RingnérM (2008) What is principal component analysis?Nature Biotechnology26(3): 303–304.
58.
RodriguesEROliveiraICunhaR, et al. (2018) DeepDownscale: a deep learning strategy for high-resolution weather forecast. In: 2018 IEEE 14th International conference on e-Science (e-Science), Amsterdam, The Netherlands, 29 October–1 November 2018, pp.415–422. New York, NY: IEEE. DOI: 10.1109/eScience.2018.00130
59.
Salcedo-SanzSCornejo-BuenoLPrietoL, et al. (2018) Feature selection in machine learning prediction systems for renewable energy applications. Renewable and Sustainable Energy Reviews90: 728–741.
60.
ShapiroSSWilkMB (1965) An analysis of variance test for normality (complete samples). Biometrika52(3/4): 591–611.
61.
SirinSMYilmazBN (2021) The impact of variable renewable energy technologies on electricity markets: An analysis of the Turkish balancing market. Energy Policy151: 112093.
62.
StaffellIPfenningerS (2016) Using bias-corrected reanalysis to simulate current and future wind power output. Energy114: 1224–1239.
63.
TianZ (2021) A state-of-the-art review on wind power deterministic prediction. Wind Engineering45(5): 1374–1392.
64.
TianZWangGLiS, et al. (2019) Artificial bee colony algorithm–optimized error minimized extreme learning machine and its application in short-term wind speed prediction. Wind Engineering43(3): 263–276.
65.
TibshiraniR (1996) Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological)58(1): 267–288.
66.
TikhonovAN (1943) On the stability of inverse problems. Doklady Akademii Nauk SSSR39: 195–198.
67.
TsagrisMPapadovasilakisZLakiotakiK, et al. (2020) A generalised OMP algorithm for feature selection with application to gene expression data. arXiv preprint arXiv:2004.00281.
68.
Turkish Wind Energy Association (2020) WPP database. Available at: https://tureb.com.tr (accessed 25 December 2020).
69.
VoudouriAKhainPCarmonaI, et al. (2017) Objective calibration of numerical weather prediction models. Atmospheric Research190: 128–140.
70.
WangHHanSLiuY, et al. (2019) Sequence transfer correction algorithm for numerical weather prediction wind speed and its application in a wind power forecasting system. Applied Energy237: 1–10.
71.
WangJSongYLiuF, et al. (2016) Analysis and application of forecasting models in wind power integration: A review of multi-step-ahead wind speed forecasting models. Renewable and Sustainable Energy Reviews60: 960–981.
72.
WilcoxonF (1945) Individual comparisons by ranking methods. Biometrics Bulletin1: 80–83.
73.
YangCZhuXQiaoJ, et al. (2020) Forward and backward input variable selection for polynomial echo state networks. Neurocomputing398: 83–94.
74.
YoungMTHinkleJDKannanR, et al. (2020) Distributed Bayesian optimization of deep reinforcement learning algorithms. Journal of Parallel and Distributed Computing139: 43–52.
75.
ZhaoJGuoZHSuZY, et al. (2016) An improved multi-step forecasting model based on WRF ensembles and creative fuzzy systems for wind speed. Applied Energy162: 808–826.
76.
ZhaoJWangJGuoZ, et al. (2019) Multi-step wind speed forecasting based on numerical simulations and an optimized stochastic ensemble method. Applied Energy255: 113833.
