Wind power forecasting with discrete wavelet transform and Xgboost

Yıl 2022, Cilt: 14 Sayı: 2, 58 - 65, 30.11.2022

Mehmet Ali Yelgeç , Okan Bingöl

https://doi.org/10.55974/utbd.1132336

Öz

Wind power forecasting is necessary for system operator and wind farm for voltage and frequency control, load dispatch, unit commitment, maintenance planning and electricity market actions. Wind power time series, which is a intermittent source, is not stationary and contains various outliers. This situation reduces the success of forecasting models. In order for the wind power forecasting model to give the best results, in this paper the wind power data was transformed with discrete wavelet transform. Transformed data were trained and forecested with Xgboost, a decision tree based, gradient boosting algorithm. Proposed model were designed separately for a selected month from each season. These models were compared with MAE, RMSE, R2 error metrics by the models designed with Xgboost without discrete wavelet transform. Discrete wavelet and Xgboost model gave more successful results than Xgboost model.

Anahtar Kelimeler

Wind power, Wind power forecasting, Discrete wavelet transform, Xgboost

Ayrık dalgacık dönüşümü ve Xgboost ile rüzgâr gücü tahmini

Öz

Rüzgâr gücü tahmini, sistem işletmecisi ve santraller için gerilim ve frekans kontrolü, yük kontrolü, ünite planlaması, bakım planlaması ve elektrik marketi hareketleri için gereklidir. Süreksiz bir kaynak olan rüzgârdan elde edilen güce ait zaman serisi durağan bir yapıda değildir. Rüzgâr gücü zaman serisi çeşitli sebeplerden dolayı aykırı veriler barındırmaktadır. Bu durum tahmin modellerinde başarıyı düşürmektedir. Bu çalışmada rüzgâr gücü tahmin modelinin en iyi sonucu vermesi için rüzgâr gücü verisi ayrık dalgacık dönüşümü ile dönüştürülmüştür. Dönüştürülen veriler, karar ağacı tabanlı, gradyan arttırmaya dayanan bir algoritma olan Xgboost ile eğitilmiştir. Test için ayrılan veriler tahmin edilmiştir. Ayrık dalgacık dönüşümü-Xgboost modeli her mevsimden seçilen dört ay için ayrı ayrı tasarlanmış, ayrık dalgacık dönüşümü olmadan sadece Xgboost ile tasarlanan model ile MAE, RMSE ve R2 hata metrikleriyle karşılaştırılmıştır. Ayrık dalgacık dönüşümü-Xgboost ile tasarlanan modeller daha başarılı sonuçlar vermiştir.

Anahtar Kelimeler

Rüzgâr gücü, Rüzgâr gücü tahmini, Ayrık dalgacık dönüşümü, Xgboost

Kaynakça

• [1] Türkiye Elektrik İlerim A.Ş. Kurulu Güç Raporu Mart 2022. https://www.teias.gov.tr/tr-TR/kurulu-guc-raporlari (Erişim Tarihi: 27.04.2022).
• [2] Foley AM, Leahy PG, Marvuglia A, McKeogh EJ. Current methods and advances in forecasting of wind power generation. Renewable Energy, 37(1), 1-8, 2012.
• [3] Monteiro C, Bessa R, Miranda V, Botterud A, Wang J, Conzelmann G. Wind power forecasting: state-of-the-art. Decision and Information Sciences, 2009.
• [4] Santhosh, M., Venkaiah, C., & Vinod Kumar, D. M. (2020). Current advances and approaches in wind speed and wind power forecasting for improved renewable energy integration: A review. Engineering Reports, 2(6), e12178.
• [5] Potter CW, Negnevitsky M. Very short-term wind forecasting for Tasmanian power generation. IEEE Transactions on Power Systems, 21, (2), 965-972, 2006.
• [6] Nor KM, Shaaban M, Rahman HA. Feasibility assessment of wind energy resources in Malaysia based on NWP models. Renewable Energy, 62, 147-154, 2014.
• [7] Focken U, Lange M, Waldl H.-P.H.-P. Previento-A Wind Power Prediction System with an Innovative Upscaling Algorithm. In Proceedings of the European Wind Energy Conference (EWEC), Copenhagen, Denmark, pp. 1–4, 2011.
• [8] Zhang Y, Li Y, Zhang G. Short-term wind power forecasting approach based on Seq2Seq model using NWP data. Energy, 213, 118371,2020.
• [9] Wang J, Zhou Q, Zhang X. Wind power forecasting based on time series ARMA model. In IOP Conference Series: Earth and Environmental Science Vol. 199, No. 2, p. 022015. IOP Publishing, 2018.
• [10] Yatiyana E, Rajakaruna S, Ghosh A. Wind speed and direction forecasting for wind power generation using ARIMA model. In 2017 Australasian Universities Power Engineering Conference (AUPEC) (pp. 1-6). IEEE, 2017.
• [11] Kusiak A, Zhang Z. Short-horizon prediction of wind power: A data-driven approach. IEEE Transactions on Energy Conversion, 25(4), 1112-1122, 2010.
• [12] Durán MJ, Cros D, Riquelme J. Short-term wind power forecast based on ARX models. J. Energy Eng. 133, 172–180, 2007.
• [13] Firat U, Engin SN, Sarcalar M, Ertuzum AB. Wind Speed Forecasting Based on Second Order Blind Identification and Autoregressive Model. In Proceedings of the 2010 Ninth International Conference on Machine Learning and Applications, Washington, DC, USA, 12–14, pp. 686–691, 2010.
• [14] Bilal B, Ndongo M, Adjallah KH, Sava A, Kebe CMF, Ndiaye PA, Sambou V. Wind turbine power output prediction model design based on artificial neural networks and climatic spatiotemporal data. In Proceedings of the IEEE International Conference on Industrial Technology 2018, Lyon, France, pp. 1085–1092, 2018.
• [15] Hong YY, Rioflorido CLPP. A hybrid deep learning-based neural network for 24-h ahead wind power forecasting. Appl. Energy, 250, 530–539,2019.
• [16] Shahid F, Zameer A, Muneeb M. A novel genetic LSTM model for wind power forecast. Energy, 223, 120069, 2021.
• [17] Du P, Wang J, Yang W, Niu T. A novel hybrid model for short-term wind power forecasting. Applied Soft Computing, 80, 93-106, 2019.
• [18] Hong YY, Rioflorido CLPP. A hybrid deep learning-based neural network for 24-h ahead wind power forecasting. Appl. Energy, 250, 530–539, 2019.
• [19] Lydia M, Kumar S, Selvakumar A. A comprehensive review on wind turbine power curve modeling techniques. Renewable and Sustainable Energy Reviews, 452-460, 2014.
• [20] Shepherd W, Zhang L. Electricity Generation Using Wind Power.World Scientific, 2011.
• [21] Liu Y, Guan L, Hou C, Han H, Liu Z, Sun Y, Zheng M. Wind power short-term prediction based on LSTM and discrete wavelet transform. Applied Sciences, 9(6), 1108, 2019.
• [22] Catalão JDS, Pousinho HMI, Mendes VMF. Short-term wind power forecasting in Portugal by neural networks and wavelet transform. Renewable energy, 36(4), 1245-1251, 2011.
• [23] Chaovalit P, Gangopadhyay A, Karabatis G, Chen Z. Discrete wavelet transform-based time series analysis and mining. ACM Computing Surveys (CSUR), 43(2), 1-37, 2011.
• [24] Wang W, Shi Y, Lyu G, Deng W. Electricity consumption prediction using Xgboost based on discrete wavelet transform. DEStech Trans. Comput. Sci. Eng., 2017.
• [25] Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794), 2016.
• [26] Demolli H, Dokuz AS, Ecemis A, Gokcek M. Wind power forecasting based on daily wind speed data using machine learning algorithms. Energy Conversion and Management, 198, 111823, 2019.