Predicting wind power using LSTM, Transformer, and other techniques

Arun Kumar M; Rithick Joshua K; Sahana Rajesh; Caroline Dorathy Esther J; Kavitha Devi MK; Arun Kumar M; Rithick Joshua K; Sahana Rajesh; Caroline Dorathy Esther J; Kavitha Devi MK

doi:10.3934/ctr.2024007

Clean Technologies and Recycling

2024, Volume 4, Issue 2: 125-145. doi: 10.3934/ctr.2024007

Previous Article Next Article

Research article

Predicting wind power using LSTM, Transformer, and other techniques

1.
Department of Computer Science and Engineering, Thiagarjar College of Engineering, Madurai-625015, Tamil Nadu, India
2.
Department of Biotechnology, School of Bio Sciences and Technology, Vellore Institute of Technology, Vellore - 632014, Tamil Nadu, India
3.
Faculty of Computer Science and Engineering, Thiagarjar College of Engineering, Madurai-625015, Tamil Nadu, India

Received: 05 May 2024 Revised: 22 November 2024 Accepted: 26 November 2024 Published: 11 December 2024

Predicting wind turbine energy is essential for optimizing renewable energy utilization and ensuring grid stability. Accurate forecasts enable effective resource planning, minimizing reliance on non-renewable energy sources and reducing carbon emissions. Additionally, precise predictions support efficient grid management, allowing utilities to balance supply and demand in real time, ultimately enhancing energy reliability and sustainability. In this study, we bridge the gap by exploring various machine learning (ML) and deep learning (DL) methodologies to enhance wind power forecasts. We emphasize the importance of accuracy in these predictions, aiming to overcome current standards. Our approach utilized these models to predict wind power generation for the next 15 days, utilizing the SCADA Turkey dataset and Tata Power Poolavadi Data collected. We used R² scores alongside traditional metrics like mean absolute error (MAE) and root mean square error (RMSE) to evaluate model performance. By employing these methodologies, we aim to enhance wind power forecasting, thereby enabling more efficient utilization of renewable energy resources.
- temporal dependencies,
- feature engineering,
- ensemble methods,
- grid integration,
- hyperparameter tuning
Citation: Arun Kumar M, Rithick Joshua K, Sahana Rajesh, Caroline Dorathy Esther J, Kavitha Devi MK. Predicting wind power using LSTM, Transformer, and other techniques[J]. Clean Technologies and Recycling, 2024, 4(2): 125-145. doi: 10.3934/ctr.2024007

Related Papers:

Abstract

Predicting wind turbine energy is essential for optimizing renewable energy utilization and ensuring grid stability. Accurate forecasts enable effective resource planning, minimizing reliance on non-renewable energy sources and reducing carbon emissions. Additionally, precise predictions support efficient grid management, allowing utilities to balance supply and demand in real time, ultimately enhancing energy reliability and sustainability. In this study, we bridge the gap by exploring various machine learning (ML) and deep learning (DL) methodologies to enhance wind power forecasts. We emphasize the importance of accuracy in these predictions, aiming to overcome current standards. Our approach utilized these models to predict wind power generation for the next 15 days, utilizing the SCADA Turkey dataset and Tata Power Poolavadi Data collected. We used R² scores alongside traditional metrics like mean absolute error (MAE) and root mean square error (RMSE) to evaluate model performance. By employing these methodologies, we aim to enhance wind power forecasting, thereby enabling more efficient utilization of renewable energy resources.

References

[1]	Tarek Z, Shams MY, Elshewey AM, et al. (2023) Wind power prediction based on machine learning and deep learning models. Comput Mater Continua 74: 715–732. https://doi.org/10.32604/cmc.2023.032533 doi: 10.32604/cmc.2023.032533
[2]	Hu C, Zhao Y, Jiang H, et al. (2022) Prediction of ultra-short-term wind power based on CEEMDAN-LSTM-TCN. Energy Rep 8: 483–492. https://doi.org/10.1016/j.egyr.2022.09.171 doi: 10.1016/j.egyr.2022.09.171
[3]	Shen Z, Fan X, Zhang L, et al. (2022) Wind speed prediction of unmanned sailboat based on CNN and LSTM hybrid neural network. Ocean Eng 254: 111352. https://doi.org/10.1016/j.oceaneng.2022.111352 doi: 10.1016/j.oceaneng.2022.111352
[4]	Huang Q, Wang Y, Yang X, et al. (2023) Research on wind power prediction based on a gated transformer. Appl Sci 13: 8350. https://doi.org/10.3390/app13148350 doi: 10.3390/app13148350
[5]	Wu H, Meng K, Fan D, et al. (2022) Multistep short-term wind speed forecasting using transformer. Energy 261: 125231. https://doi.org/10.1016/j.energy.2022.125231 doi: 10.1016/j.energy.2022.125231
[6]	Wu H, Wang P, Chao KM, et al. (2021) Wind power forecasting with deep learning networks: Time-series forecasting. Appl Sci 11: 10335. https://doi.org/10.3390/app112110335. doi: 10.3390/app112110335
[7]	Eryilmaz S, Devrim Y (2018) Theoretical derivation of wind plant power distribution with the consideration of wind turbine reliability. Reliab Eng Syst Saf 185: 44–50. https://doi.org/10.1016/j.ress.2018.12.018 doi: 10.1016/j.ress.2018.12.018
[8]	Ho CY, Cheng KS, Ang CH (2023) Utilizing the random forest method for short-term wind speed forecasting in the coastal area of central Taiwan. Energies 16: 1374. https://doi.org/10.3390/en16031374 doi: 10.3390/en16031374
[9]	Phan QT, Wu YK, Phan QD (2021) A hybrid wind power forecasting model with XGBoost, data preprocessing considering different NWPs. Appl Sci 11: 1100. https://doi.org/10.3390/app11031100 doi: 10.3390/app11031100
[10]	Ponkumar G, Jayaprakash S, Kanagarathinam K (2023). Advanced machine learning techniques for accurate very short-term wind power forecasting in wind energy systems using historical data analysis. Energies 16: 5459. https://doi.org/10.3390/en16145459 doi: 10.3390/en16145459
[11]	Bai W, Jin M, Li W, et al. (2024). Multi-step prediction of wind power based on hybrid model with improved variational mode decomposition and sequence-to-sequence network. Processes 12: 191. https://doi.org/10.3390/pr12010191 doi: 10.3390/pr12010191
[12]	Yuan C, Li J, Xie Y, et al. (2022) Investigation on the effect of the baseline control system on dynamic and fatigue characteristics of modern wind turbines. Appl Sci 12: 2968. https://doi.org/10.3390/app12062968 doi: 10.3390/app12062968
[13]	Elsaraiti M, Merabet A (2021) Application of long-short-term-memory recurrent neural networks to forecast wind speed. Appl Sci 11: 2387. https://doi.org/10.3390/app11052387 doi: 10.3390/app11052387
[14]	Huang C, Liu C, Zhong M, et al. (2024). Research on wind turbine location and wind energy resource evaluation methodology in port scenarios. Sustainability 16: 1074. https://doi.org/10.3390/su16031074 doi: 10.3390/su16031074
[15]	Piotrowski P, Rutyna I, Baczyński D, et al. (2022). Evaluation metrics for wind power forecasts: A comprehensive review and statistical analysis of errors. Energies 15: 9657. https://doi.org/10.3390/en15249657 doi: 10.3390/en15249657

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)