Research Article
BibTex RIS Cite

LONG SHORT-TERM MEMORY FOR WIND POWER ESTIMATION: THE EFFECT OF DATA SAMPLING AND CLUSTERING

Year 2025, Volume: 28 Issue: 1, 202 - 215, 03.03.2025

Volkan Yamaçlı

Abstract

Wind energy is one of the most efficient substitutes for traditional power sources, which is clean, renewable and friendly to the environment. Nonetheless, there are some of obstacles to the security and dependability of power grid functioning due to the erratic nature of wind speed and power quality. In order to address scheduling problem through wind speed and power prediction, a long short-term memory (LSTM)-based prediction model, one of the most popular recurrent neural networks (RNN), is proposed. In this study, the dataset obtained from a wind turbine placed in Turkey is used. At first, the LSTM network is trained for different window size of data for wind speed and power sequences. Then, the outputs of these two LSTM networks are used as an input for another LSTM network ensuring a robust approach for lower amount of data with higher intervals. The final wind power forecasting data are obtained by using each sequences’ results. Four different case studies are carried out based on intervals of 30-minutes, 1-hour, 6-hours, and 1-day in order to the efficiency of the proposed algorithm is shown.

Keywords

Wind energy long short-term memory recurrent neural networks wind power forecasting

References

  • Abaci, K., Yetgin, Z., Yamacli, V., & Isiker, H. (2024). Modified effective butterfly optimizer for solving optimal power flow problem. Heliyon, 10(12), e32862. https://doi.org/10.1016/j.heliyon.2024.e32862
  • Ai, X., Li, S., & Xu, H. (2022). Short-term wind speed forecasting based on two-stage preprocessing method, sparrow search algorithm and long short-term memory neural network. Energy Reports, 8, 14997-15010. https://doi.org/10.1016/j.egyr.2022.11.051
  • Akçay, H., & Yıltas-Kaplan, D. (2024). Zaman serileri tahminleme algoritmaları ile kontör tüketim tahminlemesi ve karşılaştırmalı uygulaması. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(1), 166-189. https://doi.org/10.17780/ksujes.1369811
  • Al‐Shaikhi, A., Nuha, H., Mohandes, M., Rehman, S., & Adrian, M. (2022). Vertical wind speed extrapolation model using long short‐term memory and particle swarm optimization. Energy Science & Engineering, 10(12), 4580-4594. https://doi.org/10.1002/ese3.1291
  • Bokde, N., Feijóo, A., Villanueva, D., & Kulat, K. (2019). A Review on Hybrid Empirical Mode Decomposition Models for Wind Speed and Wind Power Prediction. Energies, 12(2), 254. https://doi.org/10.3390/en12020254
  • Chen, J., Guo, Z., Zhang, L., & Zhang, S. (2024). Short-term wind speed prediction based on improved Hilbert–Huang transform method coupled with NAR dynamic neural network model. Scientific Reports, 14(1), 617. https://doi.org/10.1038/s41598-024-51252-y
  • Erisen, B. (2018). Wind Turbine Scada Dataset. https://www.kaggle.com/datasets/berkerisen/wind-turbine-scada-dataset
  • Gan, Z., Li, C., Zhou, J., & Tang, G. (2021). Temporal convolutional networks interval prediction model for wind speed forecasting. Electric Power Systems Research, 191, 106865. https://doi.org/10.1016/j.epsr.2020.106865
  • Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to Forget: Continual Prediction with LSTM. Neural Computation, 12(10), 2451-2471. https://doi.org/10.1162/089976600300015015
  • Guan, S., Wang, Y., Liu, L., Gao, J., Xu, Z., & Kan, S. (2023). Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm. Heliyon, 9(6), e16938. https://doi.org/10.1016/j.heliyon.2023.e16938
  • Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  • Hou, X., Hu, W., & Luo, M. (2024). Short-term wind farm cluster power point-interval prediction based on graph spatio-temporal features and S-Stacking combined reconstruction. Heliyon, 10(14), e33945. https://doi.org/10.1016/j.heliyon.2024.e33945
  • Jun Zhang, & Man, K. F. (1998). Time series prediction using RNN in multi-dimension embedding phase space. SMC’98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218), 1868-1873. https://doi.org/10.1109/ICSMC.1998.728168
  • Jung, J., & Broadwater, R. P. (2014). Current status and future advances for wind speed and power forecasting. Renewable and Sustainable Energy Reviews, 31, 762-777. https://doi.org/10.1016/j.rser.2013.12.054
  • Lawal, A., Rehman, S., Alhems, L. M., & Alam, Md. M. (2021). Wind Speed Prediction Using Hybrid 1D CNN and BLSTM Network. IEEE Access, 9, 156672-156679. https://doi.org/10.1109/ACCESS.2021.3129883
  • Li, M., Zhang, Z., Ji, T., & Qu, Q. H. (2020). Ultra-short term wind speed prediction using mathematical morphology decomposition and long short-term memory. CSEE Journal of Power and Energy Systems. https://doi.org/10.17775/CSEEJPES.2019.02070
  • Lopez, L., Oliveros, I., Torres, L., Ripoll, L., Soto, J., Salazar, G., & Cantillo, S. (2020). Prediction of Wind Speed Using Hybrid Techniques. Energies, 13(23), 6284. https://doi.org/10.3390/en13236284
  • Memarzadeh, G., & Keynia, F. (2021). Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm. Electric Power Systems Research, 192, 106995. https://doi.org/10.1016/j.epsr.2020.106995
  • Pavlov-Kagadejev, M., Jovanovic, L., Bacanin, N., Deveci, M., Zivkovic, M., Tuba, M., Strumberger, I., & Pedrycz, W. (2024). Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting. Artificial Intelligence Review, 57(3), 45. https://doi.org/10.1007/s10462-023-10678-y
  • Shao, B., Song, D., Bian, G., & Zhao, Y. (2021). Wind Speed Forecast Based on the LSTM Neural Network Optimized by the Firework Algorithm. Advances in Materials Science and Engineering, 2021, 1-13. https://doi.org/10.1155/2021/4874757
  • Shi, Z., Yao, W., Li, Z., Zeng, L., Zhao, Y., Zhang, R., Tang, Y., & Wen, J. (2020). Artificial intelligence techniques for stability analysis and control in smart grids: Methodologies, applications, challenges and future directions. Applied Energy, 278, 115733. https://doi.org/10.1016/j.apenergy.2020.115733
  • Sun, W., & Wang, Y. (2018). Short-term wind speed forecasting based on fast ensemble empirical mode decomposition, phase space reconstruction, sample entropy and improved back-propagation neural network. Energy Conversion and Management, 157, 1-12. https://doi.org/10.1016/j.enconman.2017.11.067
  • Wang, C., Han, D., Liu, Q., & Luo, S. (2019). A Deep Learning Approach for Credit Scoring of Peer-to-Peer Lending Using Attention Mechanism LSTM. IEEE Access, 7, 2161-2168. https://doi.org/10.1109/ACCESS.2018.2887138
  • Wang, J., Sun, J., & Zhang, H. (2013). Short-term wind power forecasting based on support vector machine. 2013 5th International Conference on Power Electronics Systems and Applications(PESA), 1-5. https://doi.org/10.1109/PESA.2013.6828211
  • Wang, J., Wang, Y., Li, Z., Li, H., & Yang, H. (2020). A combined framework based on data preprocessing, neural networks and multi-tracker optimizer for wind speed prediction. Sustainable Energy Technologies and Assessments, 40, 100757. https://doi.org/10.1016/j.seta.2020.100757
  • Xie, Y., Li, C., Tang, G., & Liu, F. (2021). A novel deep interval prediction model with adaptive interval construction strategy and automatic hyperparameter tuning for wind speed forecasting. Energy, 216, 119179. https://doi.org/10.1016/j.energy.2020.119179
  • Yamaçli, V., Işiker, H., Yetgín, Z., & Abaci, K. (2024). Solving Optimal Power Flow Control Problem Using Honey Formation Optimization Algorithm. IEEE Access, 12, 109293-109322. https://doi.org/10.1109/ACCESS.2024.3439021

RÜZGÂR GÜCÜ TAHMİNİNDE UZUN KISA-SÜRELİ BELLEK: VERİ ÖRNEKLEME VE KÜMELEMENİN ETKİSİ

Year 2025, Volume: 28 Issue: 1, 202 - 215, 03.03.2025

Volkan Yamaçlı

Abstract

Rüzgâr enerjisi, temiz, yenilenebilir ve çevre dostu olarak geleneksel güç kaynaklarının en verimli alternatiflerinden biridir. Bununla birlikte, rüzgâr hızının ve dolayısıyla güç kalitesinin değişken doğasından dolayı, elektrik şebekesinin güvenliği ve güvenilirliğinin önünde bazı engeller oluşabilmektedir. Rüzgâr hızı ve gücü tahmini aracılığı ile güç planlaması sorununu çözebilmek için, en popüler yinelemeli sinir ağlarından (YNSA) biri olan uzun kısa-süreli bellek (UKSB) tabanlı bir tahmin modeli önerilmektedir. Bu çalışmada Türkiye’de mevcut olan bir rüzgâr türbininden elde edilen ve yayımlanan bir veri seti kullanılmıştır. İlk olarak UKSB ağı, rüzgâr hızı ve rüzgâr gücü zaman-dizilerine ilişkin farklı pencere boyutundaki veriler için eğitilmiştir. Daha sonra bu iki UKSB ağının çıktıları başka bir UKSB ağı için girdi olarak kullanılarak daha yüksek aralıklarla daha az miktarda veri için sağlam bir yaklaşım sağlanması hedeflenmiştir. Nihai rüzgâr gücü tahmin verileri, her bir dizinin sonuçları kullanılarak elde edilir. 30-dakikalık, 1-saatik, 6-saatlik ve 1-günlük aralıklarla 4 farklı durum çalışması yapılarak önerilen algoritmanın etkinliği gösterilmiştir.

Keywords

Rüzgâr enerjisi uzun kısa-süreli bellek yinelemeli sinir ağları rüzgâr güç tahmini

References

  • Abaci, K., Yetgin, Z., Yamacli, V., & Isiker, H. (2024). Modified effective butterfly optimizer for solving optimal power flow problem. Heliyon, 10(12), e32862. https://doi.org/10.1016/j.heliyon.2024.e32862
  • Ai, X., Li, S., & Xu, H. (2022). Short-term wind speed forecasting based on two-stage preprocessing method, sparrow search algorithm and long short-term memory neural network. Energy Reports, 8, 14997-15010. https://doi.org/10.1016/j.egyr.2022.11.051
  • Akçay, H., & Yıltas-Kaplan, D. (2024). Zaman serileri tahminleme algoritmaları ile kontör tüketim tahminlemesi ve karşılaştırmalı uygulaması. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(1), 166-189. https://doi.org/10.17780/ksujes.1369811
  • Al‐Shaikhi, A., Nuha, H., Mohandes, M., Rehman, S., & Adrian, M. (2022). Vertical wind speed extrapolation model using long short‐term memory and particle swarm optimization. Energy Science & Engineering, 10(12), 4580-4594. https://doi.org/10.1002/ese3.1291
  • Bokde, N., Feijóo, A., Villanueva, D., & Kulat, K. (2019). A Review on Hybrid Empirical Mode Decomposition Models for Wind Speed and Wind Power Prediction. Energies, 12(2), 254. https://doi.org/10.3390/en12020254
  • Chen, J., Guo, Z., Zhang, L., & Zhang, S. (2024). Short-term wind speed prediction based on improved Hilbert–Huang transform method coupled with NAR dynamic neural network model. Scientific Reports, 14(1), 617. https://doi.org/10.1038/s41598-024-51252-y
  • Erisen, B. (2018). Wind Turbine Scada Dataset. https://www.kaggle.com/datasets/berkerisen/wind-turbine-scada-dataset
  • Gan, Z., Li, C., Zhou, J., & Tang, G. (2021). Temporal convolutional networks interval prediction model for wind speed forecasting. Electric Power Systems Research, 191, 106865. https://doi.org/10.1016/j.epsr.2020.106865
  • Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to Forget: Continual Prediction with LSTM. Neural Computation, 12(10), 2451-2471. https://doi.org/10.1162/089976600300015015
  • Guan, S., Wang, Y., Liu, L., Gao, J., Xu, Z., & Kan, S. (2023). Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm. Heliyon, 9(6), e16938. https://doi.org/10.1016/j.heliyon.2023.e16938
  • Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  • Hou, X., Hu, W., & Luo, M. (2024). Short-term wind farm cluster power point-interval prediction based on graph spatio-temporal features and S-Stacking combined reconstruction. Heliyon, 10(14), e33945. https://doi.org/10.1016/j.heliyon.2024.e33945
  • Jun Zhang, & Man, K. F. (1998). Time series prediction using RNN in multi-dimension embedding phase space. SMC’98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218), 1868-1873. https://doi.org/10.1109/ICSMC.1998.728168
  • Jung, J., & Broadwater, R. P. (2014). Current status and future advances for wind speed and power forecasting. Renewable and Sustainable Energy Reviews, 31, 762-777. https://doi.org/10.1016/j.rser.2013.12.054
  • Lawal, A., Rehman, S., Alhems, L. M., & Alam, Md. M. (2021). Wind Speed Prediction Using Hybrid 1D CNN and BLSTM Network. IEEE Access, 9, 156672-156679. https://doi.org/10.1109/ACCESS.2021.3129883
  • Li, M., Zhang, Z., Ji, T., & Qu, Q. H. (2020). Ultra-short term wind speed prediction using mathematical morphology decomposition and long short-term memory. CSEE Journal of Power and Energy Systems. https://doi.org/10.17775/CSEEJPES.2019.02070
  • Lopez, L., Oliveros, I., Torres, L., Ripoll, L., Soto, J., Salazar, G., & Cantillo, S. (2020). Prediction of Wind Speed Using Hybrid Techniques. Energies, 13(23), 6284. https://doi.org/10.3390/en13236284
  • Memarzadeh, G., & Keynia, F. (2021). Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm. Electric Power Systems Research, 192, 106995. https://doi.org/10.1016/j.epsr.2020.106995
  • Pavlov-Kagadejev, M., Jovanovic, L., Bacanin, N., Deveci, M., Zivkovic, M., Tuba, M., Strumberger, I., & Pedrycz, W. (2024). Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting. Artificial Intelligence Review, 57(3), 45. https://doi.org/10.1007/s10462-023-10678-y
  • Shao, B., Song, D., Bian, G., & Zhao, Y. (2021). Wind Speed Forecast Based on the LSTM Neural Network Optimized by the Firework Algorithm. Advances in Materials Science and Engineering, 2021, 1-13. https://doi.org/10.1155/2021/4874757
  • Shi, Z., Yao, W., Li, Z., Zeng, L., Zhao, Y., Zhang, R., Tang, Y., & Wen, J. (2020). Artificial intelligence techniques for stability analysis and control in smart grids: Methodologies, applications, challenges and future directions. Applied Energy, 278, 115733. https://doi.org/10.1016/j.apenergy.2020.115733
  • Sun, W., & Wang, Y. (2018). Short-term wind speed forecasting based on fast ensemble empirical mode decomposition, phase space reconstruction, sample entropy and improved back-propagation neural network. Energy Conversion and Management, 157, 1-12. https://doi.org/10.1016/j.enconman.2017.11.067
  • Wang, C., Han, D., Liu, Q., & Luo, S. (2019). A Deep Learning Approach for Credit Scoring of Peer-to-Peer Lending Using Attention Mechanism LSTM. IEEE Access, 7, 2161-2168. https://doi.org/10.1109/ACCESS.2018.2887138
  • Wang, J., Sun, J., & Zhang, H. (2013). Short-term wind power forecasting based on support vector machine. 2013 5th International Conference on Power Electronics Systems and Applications(PESA), 1-5. https://doi.org/10.1109/PESA.2013.6828211
  • Wang, J., Wang, Y., Li, Z., Li, H., & Yang, H. (2020). A combined framework based on data preprocessing, neural networks and multi-tracker optimizer for wind speed prediction. Sustainable Energy Technologies and Assessments, 40, 100757. https://doi.org/10.1016/j.seta.2020.100757
  • Xie, Y., Li, C., Tang, G., & Liu, F. (2021). A novel deep interval prediction model with adaptive interval construction strategy and automatic hyperparameter tuning for wind speed forecasting. Energy, 216, 119179. https://doi.org/10.1016/j.energy.2020.119179
  • Yamaçli, V., Işiker, H., Yetgín, Z., & Abaci, K. (2024). Solving Optimal Power Flow Control Problem Using Honey Formation Optimization Algorithm. IEEE Access, 12, 109293-109322. https://doi.org/10.1109/ACCESS.2024.3439021
There are 27 citations in total.

Details

Primary Language Turkish
Subjects Deep Learning, Electrical Energy Generation (Incl. Renewables, Excl. Photovoltaics)
Journal Section Computer Engineering
Authors

Volkan Yamaçlı 0000-0003-0331-8818

Publication Date March 3, 2025
Submission Date August 19, 2024
Acceptance Date September 13, 2024
Published in Issue Year 2025Volume: 28 Issue: 1

Cite

APA Yamaçlı, V. (2025). RÜZGÂR GÜCÜ TAHMİNİNDE UZUN KISA-SÜRELİ BELLEK: VERİ ÖRNEKLEME VE KÜMELEMENİN ETKİSİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 202-215.
 Download Cover Image