Utilizing ANN for improving the WRF wind forecasts in Türkiye
Tóm tắt
The accurate estimation of wind speed is crucial for wind energy production, given the exponential relationship between wind and power. However, this is a challenging task due to the stochastic nature of meteorology. In this study, the Weather Research and Forecasting Model (WRF) with a 9 km spatial resolution was used to simulate hourly wind speed values for Türkiye, using Global Data Assimilation System (GDAS) 0.25° boundary data. Several statistical metrics, including Root Mean Squared Error (RMSE), Mean Bias Error (MB), Index of Agreement (IoA), and Pearson correlation, were used to evaluate the performance of the WRF model. The WRF model, which used CONUS parametrization and was supplied with GDAS boundary data every 6 h, operated for 17,520 h in a 1-month consecutive run. The ANN model, which has Hecht-Nielsen (2n + 1) topology, was used to perform hindcasting of the WRF model. The input layer of the ANN model used temperature, pressure, and wind speed values obtained from WRF. The analysis was done spatio-temporally for 2 years and presented with seasonal and annual performance values. After applying the ANN model to the WRF model, which had initial values of MB of 1.42, RMSE of 2.26, R of 0.51, and IOA value of 0.02, the new MB, RMSE, R, and IOA values were found to be 0.04, 0.96, 0.56, and 0.60, respectively. Therefore, it can be concluded that the ANN model improved the WRF model's wind speed prediction performance in Türkiye by 11% on average, relatively.
Tài liệu tham khảo
Akataş N (2015) Kısa Süreli Rüzgar Tahmini İçin Wrf Model Performansının Analizi Ve Rüzgar Gücü Uygulamaları [Masters Thesis, İstanbul Technical University Institute of Science and Technology]. Retrieved from http://hdl.handle.net/11527/15236. Accessed 06.01.2023
Andraju P, Kanth AL, Kumari KV et al (2019) Performance Optimization of Operational WRF Model Configured for Indian Monsoon Region. Earth Syst Environ 3:231–239. https://doi.org/10.1007/s41748-019-00092-2
Astsatryan H, Grigoryan H, Poghosyan A et al (2021) Air temperature forecasting using artificial neural network for Ararat valley. Earth Sci Inform 14:711–722. https://doi.org/10.1007/s12145-021-00583-9
Atalay M, Çelik E (2017) Büyük Veri Analizinde Yapay Zekâ Ve Makine Öğrenmesi Uygulamaları [Artificial Intelligence and Machine Learning Applications in Big Data Analysis]. Mehmet Akif Ersoy Üniversitesi Sosyal Bilimler Enstitüsü Dergisi 9(22):155–172. https://doi.org/10.20875/makusobed.309727
Ataseven B (2013) Yapay Sinir Ağları İle Öngörü Modellemesi. Öneri Dergisi 10(39):101–115. Retrieved from https://dergipark.org.tr/en/pub/maruoneri/issue/17900/187806. Accessed 13.10.2022
Bailey BH (2016) 3 - Wind resources for offshore wind farms: characteristics and assessment. In: Ng C, Ran L (eds) Offshore wind farms. Woodhead Publishing, pp 29–58. https://doi.org/10.1016/B978-0-08-100779-2.00003-9
Bakırcı M (2011) Avrupa Birliğine (Ab) Uyum Sürecinde Türkiye Ve Avrupa’da Dağlik Sahalarin Kullanimina Yönelik Perspektifler (Avrupa Dağlık Bölgeler Şartı’nın Esasları) [Perspectives Aimed at Usage of Mountainous Areas In Turkey and Europe During the Process of Adaptation to the European Union (EU) (Principles of European Charter of Mountain Regions)]. Doğu Coğrafya Dergisi 10(13):291–309. Retrieved from https://dergipark.org.tr/en/pub/ataunidcd/issue/2434/30932. Accessed 13.10.2022
Barutçu B, Tanrıover S, Sakarya S, Incecik S, Sayınta FM, Çalışkan E, Kahraman A, Aksoy B, Kahya C, Aslan Z, Topcu S (2016) Postprocessing WRF short-term irradiance forecasts for Southeastern Anatolia Using Artificial Neural Networks (in Turkish). In: 10th International Clean Energy Symposium, UTES’16, İstanbul, Turkey. Retrieved from https://www.utes.itu.edu.tr/wp-content/uploads/2016/11/UTES16-BİLDİRİLER-KİTABI.pdf. Accessed 16.03.2022
Başakın EE, Ekmekcioğlu Ö, Çıtakoğlu H, Özger M (2022) A new insight to the wind speed forecasting: robust multi-stage ensemble soft computing approach based on pre-processing uncertainty assessment. Neural Comput Appl 34(1):783–812. https://doi.org/10.1007/s00521-021-06424-6
Carvalho D, Rocha A, Gómez-Gesteira M, Santos C (2012) A sensitivity study of the WRF model in wind simulation for an area of high wind energy. Environ Model Softw 33:23–34. https://doi.org/10.1016/j.envsoft.2012.01.019
Cilimkovic M (2015) Neural networks and back propagation algorithm. Inst Technol Blanchardstown, Blanchardstown Road North Dublin, Dublin, Ireland
Citakoglu H, Aydemir A (2019) Determination of Monthly Wind Speed of Kayseri Region With Gray Estimation Method. IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT) 2019:415–420. https://doi.org/10.1109/JEEIT.2019.8717421
De Giorgi MG, Ficarella A, Tarantino M (2011) Assessment of the benefits of numerical weather predictions in wind power forecasting based on statistical methods. Energy 36(7):3968–3978. https://doi.org/10.1016/j.energy.2011.05.006
DeepAI (2019a) Perceptron. Retrieved from https://deepai.org/machine-learning-glossary-and-terms/perceptron. Accessed 08.10.2022
DeepAI (2019b) What is ReLu? Retrieved from https://deepai.org/machine-learning-glossary-and-terms/relu. Accessed 08.10.2022
Giannakopoulou E-M, Nhili R (2014) WRF Model Methodology for Offshore Wind Energy Applications. Adv Meteorol 2014:319819. https://doi.org/10.1155/2014/319819
Google Maps (2023) Maxar Techonologies. Can be accesible from: https://www.google.com/maps/place/37°45’19.1”N+38°16’39.0”E/@37.7553,38.2753113,17z/data=3m1.4b1.4m4.3m3.8m2.3d37.75534d38.2775. Accessed 16.02.2023
Gültepe Y (2019) Makine Öğrenmesi Algoritmaları ile Hava Kirliliği Tahmini Üzerine Karşılaştırmalı Bir Değerlendirme [A Comparative Assessment on Air Pollution Estimation by Machine Learning Algorithms]. Avrupa Bilim ve Teknoloji Dergisi 16:8–15. https://doi.org/10.31590/ejosat.530347
Hahmann AN, Pena Diaz A (2010) Validation of Boundary Layer Winds from WRF Mesoscale Forecasts over Denmark. In: EWEC 2010 Proceedings online European Wind Energy Association (EWEA). Retrieved from https://backend.orbit.dtu.dk/ws/portalfiles/portal/4557241/Pena_paper_ewec_2010.pdf. Accessed 08.10.2022
Hoła J, Schabowicz K (2005) Application of artificial neural networks to determine concrete compressive strength based on non-destructive tests. J Civ Eng Manag 11(1):23–32. https://doi.org/10.3846/13923730.2005.9636329
Jain AK, Mao J, Mohiuddin KM (1996) Artificial neural networks: a tutorial. Computer 29(3):31–44. https://doi.org/10.1109/2.485891
Ji-Hang L, Zhen-Hai G, Hui-Jun W (2014) Analysis of Wind Power Assessment Based on the WRF Model. Atmospheric and Oceanic Science Letters 7(2):126–131. https://doi.org/10.3878/j.issn.1674-2834.13.0078
Jiménez PA, Dudhia J (2012) Improving the representation of resolved and unresolved topographic effects on surface wind in the WRF model. J Appl Meteorol Climatol 51(2):300–316. https://doi.org/10.1175/JAMC-D-11-084.1
Kaastra I, Boyd M (1996) Designing a neural network for forecasting financial and economic time series. Neurocomputing 10(3):215–236. https://doi.org/10.1016/0925-2312(95)00039-9
Kara Y, Aydın S, Karanfil E, Özgür E (2022) Prediction of Wind Speed by Using Chaotic Approach: A Case Study in İstanbul. Int J Environ Geoinf 9(3):48–56. https://doi.org/10.30897/ijegeo.994011
Kyoto Protocol (1997) Kyoto Protocol to the United Nations Framework Convention on Climate Change, Dec. 10, 1997, 2303 U.N.T.S. 162
Lauber, V (2015) Political Economy of Renewable Energy. In J. D. Wright (Ed.), International Encyclopedia of the Social & Behavioral Sciences (Second Edition) (pp 367–373). Elsevier. https://doi.org/10.1016/B978-0-08-097086-8.91084-5
Lauret P, Diagne M, David M (2014) A Neural Network Post-processing Approach to Improving NWP Solar Radiation Forecasts. Energy Procedia 57:1044–1052. https://doi.org/10.1016/j.egypro.2014.10.089
Lerner J, Grundmeyer M, Garvert M (2009) The importance of wind forecasting. Renewable Energy Focus 10(2):64–66. https://doi.org/10.1016/S1755-0084(09)70092-4
Li G, Shi J (2010) On comparing three artificial neural networks for wind speed forecasting. Appl Energy 87(7):2313–2320. https://doi.org/10.1016/j.apenergy.2009.12.013
Li S, Sun X, Zhang S, Zhao S, Zhang R (2019) A Study on Microscale Wind Simulations with a Coupled WRF–CFD Model in the Chongli Mountain Region of Hebei Province. China Atmos 10(12):731. https://doi.org/10.3390/atmos10120731
Lorenz E, Heinemann D (2012) 1.13 - Prediction of Solar Irradiance and Photovoltaic Power. In A. Sayigh (Ed.), Comprehensive Renewable Energy (pp 239–292). Elsevier. https://doi.org/10.1016/B978-0-08-087872-0.00114-1
Masters T (1993) 10 - Designing Feedforward Network Architectures. In T. Masters (Ed.), Practical Neural Network Recipies in C++ (pp 173–185). Morgan Kaufmann. https://doi.org/10.1016/B978-0-08-051433-8.50015-X
Mattar C, Borvarán D (2016) Offshore wind power simulation by using WRF in the central coast of Chile. Renewable Energy 94:22–31. https://doi.org/10.1016/j.renene.2016.03.005
Miyamoto M, Takeuchi K (2019) Climate agreement and technology diffusion: Impact of the Kyoto Protocol on international patent applications for renewable energy technologies. Energy Policy. https://doi.org/10.1016/j.enpol.2019.02.053
National Oceanic and Atmospheric Administration (2018) Global data assimilation system (GDAS). Retrieved from https://www.ncei.noaa.gov/access/metadata/landing-page/bin/iso?id=gov.noaa.ncdc:C00379. Accessed 08.08.2022
Nielsen RH (1987) Kolmogorov's mapping neural network existence theorem. In: Proceedings of the IEEE First International Conference on Neural Networks rm (San Diego, CA). IEEE, Piscataway, NJ, pp 11–13 Retrieved from: https://cs.uwaterloo.ca/~y328yu/classics/Hecht-Nielsen.pdf. Accessed 08.08.2022
Nwankpa C, Ijomah WL, Gachagan A, Marshall S (2018) Activation Functions: Comparison of trends in Practice and Research for Deep Learning. https://doi.org/10.48550/arXiv.1811.03378
Özen C, Korkmaz E, Bağış S, Toros H (2017) Performance test of weather research and forecasting (WRF) model for central anatolia and black sea regions of turkey. In: 8th Atmospheric Sciences Symposium, İstanbul, Turkey. Retrieved from https://www.atmosfer.itu.edu.tr/eproceedings/ATMOS2017.pdf. Accessed 15.09.2022
Ramírez L, Vindel JM (2017) 13 - Forecasting and nowcasting of DNI for concentrating solar thermal systems. In M. J. Blanco & L. R. Santigosa (Eds.), Advances in Concentrating Solar Thermal Research and Technology (pp 293–310). Woodhead Publishing. https://doi.org/10.1016/B978-0-08-100516-3.00013-7
Ripley BD (1993) Statistical aspects of neural networks. In: Jensen JL, Kendall WS (eds) Barndoff-Neilsen OE networks and chaos-statistical and probabilistic aspects. Chapman & Hall, London, pp 40–123
Ritchie H, Roser M (2020) Renewable energy. Published online at OurWorldInData.org. Retrieved from: https://ourworldindata.org/renewable-energy. Accessed 15.03.2022
Rozumalski R (2014) “The UEMS Simulation Time Step Configuration File”. UwBe International. Available at https://weather.uwbeinternational.org/wrf/runs/it4km/conf/ems_run/run_timestep.conf. Accessed 18.01.2023
Şenel MC, Koç E (2015) Dünyada Ve Türkiye’de Rüzgâr Enerjisi Durumu-Genel Değerlendirme [The State Of Wind Energy in The World and Turkey General Evaluation]. Mühendis ve Makina 56(663):46–56. Retrieved from https://dergipark.org.tr/en/pub/muhendismakina/issue/54195/733672. Accessed 04.03.2022
Sensoy S, Demircan M, Ulupinar Y, Balta İ (2008) Türkiye İklimi [Climate of Turkey]. Turkish State Meteorological Service Article. Retrieved from https://www.mgm.gov.tr/FILES/genel/makale/13_Türkiye_iklimi.pdf
Skamarock WC, Klemp JB, Dudhia J, Gill DO, Barker D, Duda MG, Powers JG (2008) A Description of the advanced research WRF version 3 (No. NCAR/TN-475+STR). University Corporation for Atmospheric Research. https://doi.org/10.5065/D68S4MVH
Tan E, Mentes SS, Unal E, Unal Y, Efe B, Barutcu B, Onol B, Topcu HS, Incecik S (2021) Short term wind energy resource prediction using WRF model for a location in western part of Turkey. J Renew Sustain Energ 13(1):013303. https://doi.org/10.1063/5.0026391
Teneler G (2020) Türkiye’de Rüzgar Enerjisi [Wind energy in Turkey]. In Türkiye’nin Enerji Görünümü. TMMOB Makina Mühendisleri Odası, Ankara, pp 283–296
Wang SC (2003) Interdisciplinary computing in java programming: artificial neural network. In: The Springer international series in engineering and computer science, vol. 743. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0377-4_5
Wang C, Venkatesh SS (1994) A theory of generalization in learning machines with neural network applications [University of Pennsylvania]. In ProQuest Dissertations and Theses. https://www.proquest.com/dissertations-theses/theory-generalization-learning-machines-with/docview/304099739/se-2?accountid=11638. Accessed 25.08.2022
Westra J (2007) Evolutionary neural networks applied in first person shooters [Master’s Thesis, University Utrecht]. Retrieved from https://www.ai.rug.nl/~mwiering/thesis_westra.pdf. Accessed 15.09.2022
Willmott CJ, Robeson SM, Matsuura K (2012) A refined index of model performance. Int J Climatol 32:2088–2094. https://doi.org/10.1002/joc.2419
Yılmaz Ulu E, Dombaycı OA (2018) Wind energy in Turkey: potential and development. The Eurasia Proceedings of Science Technology Engineering and Mathematics (4):132–136. Retrieved from http://www.epstem.net/tr/pub/issue/40805/496377. Accessed 04.04.2022
Zhang W, Wu J, Jiang A (2022) Numerical study on aerodynamic roughness of forest. Earth Sci Inf 15(1):465–472. https://doi.org/10.1007/s12145-021-00735-x