An intelligent approach to short-term wind power prediction using deep neural networks

• Autorzy: Niksa-Rynkiewicz Tacjana , Stomma Piotr , Witkowska Anna , Rutkowska Danuta , Słowik Adam , Cpałka Krzysztof , Jaworek-Korjakowska Joanna , Kolendo Piotr

Identyfikatory

DOI

10.2478/jaiscr-2023-0015

• Języki publikacji: EN

Abstrakty

EN

In this paper, an intelligent approach to the Short-Term Wind Power Prediction (STWPP) problem is considered, with the use of various types of Deep Neural Networks (DNNs). The impact of the prediction time horizon length on accuracy, and the influence of temperature on prediction effectiveness have been analyzed. Three types of DNNs have been implemented and tested, including: CNN (Convolutional Neural Networks), GRU (Gated Recurrent Unit), and H-MLP (Hierarchical Multilayer Perceptron). The DNN architectures are part of the Deep Learning Prediction (DLP) framework that is applied in the Deep Learning Power Prediction System (DLPPS). The system is trained based on data that comes from a real wind farm. This is significant because the prediction results strongly depend on weather conditions in specific locations. The results obtained from the proposed system, for the real data, are presented and compared. The best result has been achieved for the GRU network. The key advantage of the system is a high effectiveness prediction using a minimal subset of parameters. The prediction of wind power in wind farms is very important as wind power capacity has shown a rapid increase, and has become a promising source of renewable energies.

Słowa kluczowe

EN

renewable energy; wind energy; wind power; wind turbine; short-term wind power prediction; deep learning; convolutional neural networks; gated recurrent unit; hierarchical multilayer perceptron; deep neural networks

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2023
• Tom: Vol. 13. No. 3
• Strony: 197--210
• Opis fizyczny: Bibliogr. 55 poz., rys.

Twórcy

autor

Niksa-Rynkiewicz Tacjana

• Gdańsk University of Technology, Faculty of Ocean Engineering and Ship Technology, 80-233 Gdańsk, Poland

• https://orcid.org/0000-0001-9202-8454

autor

Stomma Piotr

• University of Białystok, Institute of Computer Science, 15-328 Białystok, Poland

• https://orcid.org/0000-0002-2603-8205

autor

Witkowska Anna

• Gdańsk University of Technology, Faculty of Electrical and Control Engineering, 80-233 Gdańsk, Poland

• https://orcid.org/0000-0001-9594-6832

autor

Rutkowska Danuta

• University of Social Sciences, Information Technology Institute, 90-213 Łódź, Poland

• https://orcid.org/0000-0003-0217-2589

autor

Słowik Adam

• Koszalin University of Technology, Department of Electronics and Computer Science, 75-452 Koszalin, Poland

• https://orcid.org/0000-0003-2542-9842

autor

Cpałka Krzysztof

• Częstochowa University of Technology, Department of Intelligent Computer Systems, 42-200 Częstochowa, Poland

• https://orcid.org/0000-0001-9761-118X

autor

Jaworek-Korjakowska Joanna

• AGH University, Department of Automatic Control and Robotics, Center of Excellence in Artificial Intelligence 30-059 Kraków, Poland

• https://orcid.org/0000-0003-0146-8652

autor

Kolendo Piotr

• Institute of Power Engineering, Department of Power Automation, 80-870 Gdańsk, Poland

• https://orcid.org/0000-0001-9292-5980

Bibliografia

• [1] Alzubaidi L., Zhang J., Humaidi A.J. et al.(2021) Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data 8(53), doi.org/10.1186/s40537-021-00444-8
• [2] Benítez-Buelga A., Fernández-Blanco P., and Usaola J. (2019). Wind power short-term prediction using LSTM recurrent neural networks. Energies, 12(17), 3338.
• [3] Brunner C., Ko A., and Fodor S. (2022). An autoencoder-enhanced stacking neural network model for increasing the performance of intrusion detection. J. of Artificial Intelligence and Soft Computing Research, 12(2) 149-163.
• [4] Chaudhary A., Sharma A., Kumar A., Dikshit K., & Kumar N. (2020). Short term wind power forecasting using machine learning techniques. J. of Statistics and Management Systems, 23, 145-156.
• [5] Cheng Y., Zhang Z., and Zhou Y. (2018). A population-based wind power short-term prediction approach using hybrid least squares suport vector regression with artificial bee colony algorithm. Energy Procedia, 152, 697-703.
• [6] Chung J., Gulcehre C., Cho K., and Bengio Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.
• [7] Colak I., Sagiroglu S., Yesilbudak M., Kabalci E., and Bulbul H.I. (2015). Multi-time series andtime scale modeling for wind speed and wind power forecasting part I: Statistical methods, very short-term and short-term applications. In 2015 Int. Conf. on Renewable Energy Research and Applications (ICRERA) (pp. 209-214). IEEE.
• [8] Colak I., Sagiroglu S., Yesilbudak M., Kabalci E., and Bulbul H.I. (2015). Multi-time series and-time scale modeling for wind speed and wind power forecasting part II: Medium-term and long-term applications. In 2015 Int. Conf. on Renewable Energy Research and Applications (ICRERA) (pp. 215-220). IEEE.
• [9] Emmert-Streib F., Yang Z., Feng H., Tripathi S., and Dehmer M. (2020) An introductory review of deep learning for prediction models with big data. Frontiers in Artificial Intelligence. Sec. Machine Learning and Artificial Intelligence, vol.3, doi.org/10.3389/frai.2020.00004
• [10] Gabryel M., Cpałka K., and Rutkowski L. (2005). Evolutionary strategies for learning of neuro-fuzzy systems. Proc. of the I Workshop on Genetic Fuzzy Systems, 119-123.
• [11] Gabryel M., Lada D., Filutowicz Z., PatoraWysocka Z., Kisiel-Dorohinicki M., and Chen G. (2022). Detecting anomalies in advertising web traffic with the use of the variational autoencoder. J. of Artificial Intelligence and Soft Computing Research, 12 (4) 255-256.
• [12] Giebel G., Brownsword R., Kariniotakis G., Denhard M., and Draxl C. (2011). The state-of-the-art. in short-term prediction of wind power: A literature overview, 2nd edition. ANEMOS.plus.
• [13] Guo Z., Song J., and Liu Y. (2018). Wind power short-term prediction based on convolutional neural network. Energies, 11(10), 2634.
• [14] Harbola S., and Coors V. (2019). One dimensional convolutional neural network architectures for wind prediction. Energy Conversion and Management, 195, 70-75.
• [15] Jalali S.M.J., Ahmmadian S., Khodayar M., Khosravi et.al. (2022). An advanced short-term wind power forecasting framework based on the optimized deep neural network models. Int. J. of Electrical Power and Energy Systems, vol.141, 108143.
• [16] Javadi M., Malyscheff A.M., Wu D., Kang C., and Jiang J.N. (2018). An algorithm for practical power curve estimation of wind turbines. CSEE J. of Power and Energy Systems, 4(1), 93-102.
• [17] Jia W., Wang H., Sun P., and Li J. (2019). Wind power prediction based on stacked autoencoder and LSTM. Energy Conversion and Management, 194, 78-87.
• [18] Karam C., Zini J., Awad M., Saade C., Naffaa L., and Amina M. (2021). A Progressive and crossdomain deep transfer learning framework for wrist fracture detection. J. of Artificial Intelligence and Soft Computing Research, 12(2) 101-120.
• [19] Kingma D.P., and Ba J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
• [20] Li X., Jia H., and Zhang Y. (2020). Short-term wind power prediction based on a novel hybrid algorithm combining the convolutional neural network and the improved differential evolution algorithm. Applied Energy, 275, 115373.
• [21] LeCun Y., Bengio Y., and Hinton G. (2015). Deep learning. Nature, 521(7553), 436-444.
• [22] Li Y., Cui Y., Li Y., Liu J., and Cao Y. (2020). Wind power forecasting based on EMD-LSTM neural network. Applied Energy, 261, 114441.
• [23] Imseng D., Doss M.M., Bourlard H. (2010). Hierarchical multilayer perceptron based language identification. Proc. Interspeech 2010, 2722-2725, doi: 10.21437/Interspeech.2010-721
• [24] Lin C.Y., Huang S.M., and Liao Y.C. (2018). A review of wind power point forecasting models: Current status and future perspectives. Renewable and Sustainable Energy Reviews, 82(Pt.1), 1-18.
• [25] Lin J., Li Y., Li C., Li J., Li S., and Lin L. (2019). A novel approach for short-term wind power prediction based on improved KNN algorithm and particle swarm optimization. Applied Energy, 236, 350-365.
• [26] Lipu M.S.H., et al. (2021). Artificial intelligence based hybrid forecasting approaches for wind power generation: progress challenges and prospects. IEEE Access. vol. 9, pp. 102460-102489.
• [27] Liu T., Huang Z., Tian L., Zhu Y., Wang H., and Feng S. (2021). Enhancing wind turbine power forecast via convolutional neural network. Electronics, 10(3), 261.
• [28] Ludwig S. (2022). Performance Analysis of data fusion methods applied to epileptic seizure recognition. J. of Artificial Intelligence and Soft Computing Research, 12 (1) 5-17.
• [29] McTigue M.F., Ju P., and Krause P.C. (1997). Doubly fed induction generator using back-to-back PWM converters and its application to variablespeed wind-energy generation. IEEE Transactions on Industry Applications, 33(2), 461-468.
• [30] Niksa-Rynkiewicz T., Szewczuk-Krypa N., Witkowska A., Cpałka K., Zalasinski M. and Cader, A. (2021). Monitoring regenerative heat exchanger in steam power plant by making use of the recurrent neural network. J. of Artificial Intelligence and Soft Computing Research,11(2) 143-155.
• [31] Niksa-Rynkiewicz T., Witkowska A., Głuch J., and Adamowicz M. (2022). Monitoring the gas turbine start-up phase on the platform using a hierarchical model based on Multi-Layer Perceptron networks. Polish Maritime Research, 29, 123-131.
• [32] Nguyen H., Nguyen T., Nowak J., Byrski A., Siwocha A. and Le V. (2022). Combined YOLOv5 and HRNet for high accuracy 2D keypoint and human pose estimation. J. of Artificial Intelligence and Soft Computing Research, 12(4) 281-298.
• [33] Prasad D.K., Islam M.R., Tabassum-Abbasi, et al. (2018). Wind power prediction using machine learning techniques: A comprehensive review. Renewable and Sustainable Energy Reviews. [34] Qing K., and Zhang R. (2021). Position-Encoding Convolutional Network to solving connected text Captcha. J. of Artificial Intelligence and Soft Computing Research, 12(2) 121-133.
• [35] Rutkowska D. (2002). Neuro-Fuzzy Architectures and Hybrid Learning. Physica-Verlag. A SpringerVerlag Company.
• [36] Rutkowski L., and Cpałka K. (2000). Flexible structures of neuro-fuzzy systems. Quo Vadis Computational Intelligence, Studies in Fuzziness and Soft Computing, 54, 479-484.
• [37] Singh U., and Rizwan M. (2022). SCADA system dataset exploration and machine learning based forecast for wind turbines. Results in Engineering, vol.16, 100640.
• [38] Shan Y., Xiong T., Zhang Z., and Wei X. (2018). A hybrid intelligent approach for short-term wind power prediction. Renewable Energy, 125, 62-72.
• [39] Słowik A. (2011). Application of evolutionary algorithm to design minimal phase digital filters with non-standard amplitude characteristics and finite bit word length. Bulletin of the Polish Academy of Sciences-Technical Sciences, 59(2), 125-135.
• [40] Słowik A., and Białko M. (2004). Design and optimization of combinational digital circuits using modified evolutionary algorithm. Proc. of 7th Int. onf. on Artificial Intelligence and Soft Computing, ICAISC 2004, Lecture Notes in Artificial Intelligence. vol. 3070, pp. 468-473.
• [41] Słowik A., and Białko M. (2008). Design and Optimization of IIR Digital filters with non-standard characteristics using continuous ant colony optimization algorithm. Proc. of 5th Hellenic Conference on Artificial Intelligence, SETN 2008, Lecture Notes in Artificial Intelligence. vol. 5138, pp. 395-400.
• [42] Słowik A., and Białko M. (2007). Design of IIR digital filters with non-standard characteristics using differential evolution algorithm. Bulletin of the Polish Academy of Sciences-Technical Sciences. 55(4), 359-363.
• [43] Słowik A., and Białko M. (2006). Partitioning of VLSI circuits on subcircuits with minimal numer of connections using evolutionary algorithm. Proc. of 8th Int. Conf. on Artificial Intelligence and Soft Computing, ICAISC 2006, Lecture Notes in Computer Science. vol. 4029, pp. 470-478.
• [44] Szczypta J., Przybył A., and Cpałka K. (2013). Some aspects of evolutionary designing optimal controllers. Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, 7895, 91-100.
• [45] Szewczuk-Krypa N., Kolendo P., Głuszek J., Drop M., and Aronowski J. (2022). A new method of wind farm active power curve estimation based on statistical approach. Przegl ˛ad Elektrotechniczny, 98(1), 19-26.
• [46] Tang J., Ma Z., Chen H., and Yang F. (2019). Probabilistic forecasting of wind power generation using extreme learning machine and cloud model. Applied Energy, 254, 113654.
• [47] Tsai W., Hong C., Lin W., Tu C., and Chen C. (2023). A review of modern wind power generation forecasting technologies. Preprints.org 2023, 2023040917.
• [48] Wang X., Guo P., and Huang X. (2011). A Review of wind power forecasting models. Energy Procedia, 12, 770-778.
• [49] Wang Y., Hu Q., Srinivasan D., and Wang Z. (2019). Wind power curve modeling and wind power forecasting with inconsistent data. IEEE Transactions on Sustainable Energy, 10(1), 16-25.
• [50] Yang S., Yu X., and Zhou Y. (2020). LSTM and GRU neural network performance comparison study: Taking Yelp Review Dataset as an example. 2020 International Workshop on Electronic Communication and Artificial Intelligence (IWECAI), Shanghai, China, 2020, pp. 98-101, doi: 10.1109/IWECAI50956.2020.00027.
• [51] Yuan X., Zou W., and Zhang H. (2020). Short-term wind speed forecasting using deep learning: An empirical comparison of long short-term memory, convolutional neural network, and deep belief network. Renewable Energy.
• [52] Zalasinski M., Cpałka K., and Hayashi Y. (2015). New fast algorithm for the dynamic signature verification using global features values. Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, 9120, 175-188.
• [53] Zhang H., Wu S., Zhang X., et al. (2021). A novel short-term wind power prediction approach based on wavelet transform and extreme learning machine optimized by firefly algorithm. Energy Conversion and Management.
• [54] Zhang X., Li Y., Wang Q., and Wang G. (2019). Short-term wind power prediction using an artificial neural network ensemble based on principal component analysis and fuzzy c-means clustering. Renewable Energy.
• [55] Zhang Y., Zhang W., Shi D., and Lu Y. (2018). A hybrid method of wind speed and wind power prediction based on fuzzy clustering analysis and support vector regression. Energy Conversion and Management, 157, 203-212.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).