LSTM Deep Learning Techniques for Wind Power Generation Forecasting

Year 2024, Volume: 5 Issue: 1, 41 - 47

Ahmed Babiker Abdalla Ibrahim Kenan Altun

https://doi.org/10.55195/jscai.1471257

Abstract

Wind power generation forecasting is crucial for the optimal integration of renewable energy sources into power systems. Traditional forecasting methods often struggle to accurately predict wind energy production due to the complex and nonlinear relationships between wind speed, weather parameters, and power output. In recent years, deep learning techniques have emerged as promising alternatives for wind power forecasting. This conference paper provides a comprehensive review of deep learning techniques, with a specific focus on Long Short-Term Memory (LSTM) networks, for short-term wind power generation forecasting. Leveraging insights from recent research and empirical evaluations, this paper explores the effectiveness of LSTM networks in capturing temporal dependencies in wind data and improving prediction accuracy. The review highlights the potential of LSTM-based models to enhance the integration of wind energy into power systems and provides guidance for future research in this area.

Keywords

Energy Forecast Wind Energy, Deep Learning, LSTM

References

• Ahmed SD, Al-Ismail FSM, Shafiullah M, et al. (2020) Grid integration challenges of wind energy: A review. IEEE Access 8: 10857–10878.
• Khan M, He C, Liu T, et al. (2021) A new hybrid approach of clustering based probabilistic decision tree to forecast wind power on large scales. Journal of Electrical Engineering and Technology 16: 697–710.
• Niu W, Huang J, Yang H, et al. (2022) Wind turbine power prediction based on wind energy utilization coefficient and multivariate polynomial regression. Journal of Renewable and Sustainable Energy 14: 013306.
• Xu H-Y, Chang Y-Q, Wang F-L, et al. (2021) Univariate and multivariable forecasting models for ultra-short-term wind power prediction based on the similar day and LSTM network. Journal of Renewable and Sustainable Energy 13(6): 063307.
• Singh U, Rizwan M, Alaraj M, et al. (2021) A machine learning-based gradient boosting regression approach for wind power production forecasting: A step towards Smart Grid Environments. Energies 14: 5196.
• Chen H, Birkelund Y, Anfinsen SN, et al. (2021) Comparative study of data-driven short-term wind power forecasting approaches for the Norwegian Arctic region. Journal of Renewable and Sustainable Energy 13(2): 023314.
• Zhao, H., et al. "A hybrid forecasting model for wind power based on an extreme learning machine and a genetic algorithm." International Journal of Electrical Power & Energy Systems 34.1 (2012): 178-186.
• Li, S., et al. "An attention-based LSTM model for forecasting short-term wind power generation." Applied Soft Computing 90 (2020): 106190. M. E. Yüksel ve Ş. D. Odabaşı, “SMTP Protokolü ve Spam Mail Problemi”, Akad. Bilişim, 2010.
• Sørensen, P., et al. "Linking model complexity and data availability for wind speed prediction." Renewable Energy 34.8 (2009): 1839-1847.
• Liu, H., et al. "Investigating the relationship between wind speed forecast errors and wind farm power output forecast errors." Renewable Energy 130 (2019): 1034-1045. Y. Gedik, “E-Posta Pazarlama: Teorik Bir Bakış”, Uluslar. Önetim Akad. Derg., c. 3, sy 2, ss. 476-490, 2020.
• Jain, A., et al. "A review on machine learning models for wind speed prediction." Renewable and Sustainable Energy Reviews 99 (2019): 1011-1022.
• Pan, Y., et al. "A survey on forecast error correction methods for wind power generation." Renewable Energy 140 (2019): 1142-1150.
• Feng, Z., et al. "Explainable artificial intelligence for short-term wind power forecasting: A review." Renewable and Sustainable Energy Reviews 114 (2020): 111411.
• Staffell, T., et al. "The role of storage in the energy transition." Renewable Energy and Environmental Sustainability 1.1 (2019): 32.
• Denholm, P., et al. "Limits to solar and wind power deployment." Joule 3.6 (2019): 1075-1089.
• Taylor, J. W., & McSharry, P. E. (2007). Short-term wind speed forecasting for wind power applications using Bayesian model averaging. Journal of the Royal Statistical Society: Series A (Statistics in Society), 170(5), 935-950.
• Liu, C. et al. (2018). "Long Short-Term Memory Networks for Wind Speed and Power Prediction: A Comparative Study." Energy Conversion and Management, 78(3), 456-472.
• Chen, H. et al. (2020). "Forecasting Wind Energy Generation Using Recurrent Neural Networks: A Case Study in Onshore Wind Farms." Journal of Applied Energy, 33(1), 210-225.
• Gneiting, T., Raftery, A. E., Westveld, A. H., & Goldman, T. (2005). Calibrated probabilistic forecasting using ensemble model output statistics and minimum CRPS estimation. Monthly Weather Review, 133(5), 1098-1118.
• Pinson, P., Madsen, H., Nielsen, H. A., & Papaefthymiou, G. (2007). From probabilistic forecasts to statistical scenarios of short-term wind power production. Wind Energy, 10(6), 497-514.
• Ali Abdulrhman Salihi, Merdin Danismaz. (November 2023). "A Comparative Study on Wind Power Forecasting Models Based on the Use of LSTM." Department of Mechanical Engineering, Kirsehir Ahi Evran University, Turkey.