SavedAdd your journal

Journals / Fırat Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 38 Sayı: 1

Analysis and Forecasting of the Wave Energy Dynamics via LSTM Deep Learning Network

LSTM Derin Öğrenme Ağı ile Dalga Enerjisi Dinamiklerinin Analizi ve Tahmini

Ali Rıza Alan(BAHÇEŞEHİR ÜNİVERSİTESİ)0000-0002-0243-9493
Pages
37–46
Publication Date
2026-03-28
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

According to our research, LSTM-based deep learning or comparable techniques can be used for these kinds of forecasts, which could be helpful in maximizing power conversion, anticipating resonance dynamics, and preventing excessive loading and converter structural damage.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:One of the most advantageous sources of renewable energy is the currents and waves of the ocean.
📊
Key Findings & Data:Predicting how well ocean wave and tidal energy converting equipment will operate in a marine setting is less frequently researched compared to other topics.
💡
Conclusion & Impact:According to our research, LSTM-based deep learning or comparable techniques can be used for these kinds of forecasts, which could be helpful in maximizing power conversion, anticipating resonance dynamics, and preventing excessive loading and converter structural damage.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Okyanus dalgaları · dalga enerjisi · LSTM

Abstract

One of the most advantageous sources of renewable energy is the currents and waves of the ocean. Predicting the energy availability in the maritime environment is a topic that has been extensively addressed by researchers. Various weather forecasting approaches, numerical models, and even artificial intelligence systems are examined in the literature. Predicting how well ocean wave and tidal energy converting equipment will operate in a marine setting is less frequently researched compared to other topics. For this reason, modeling the temporal dynamics of a buoy-type power take-off (PTO) device in a random marine environment is carried out as the initial step. A spectrum technique is used to represent the random sea environment, and FFT routines are used to efficiently simulate the multi-spectral ocean wave field. The transfer function approach is used to model the dynamics of a PTO device in this multi-spectral environment. As the second step, the Long Short Term Memory (LSTM) deep learning network is used to predict the heave velocities and converter power time series. It is demonstrated that the instantaneous converter power and device dynamics can be predicted by the LSTM. According to our research, LSTM-based deep learning or comparable techniques can be used for these kinds of forecasts, which could be helpful in maximizing power conversion, anticipating resonance dynamics, and preventing excessive loading and converter structural damage.

Özet

Yenilenebilir enerjinin en avantajlı kaynaklarından biri okyanus akıntıları ve dalgalarıdır. Deniz ortamındaki enerji bulunabilirliğinin tahmini araştırmacılar tarafından kapsamlı bir şekilde ele alınan bir konudur. Literatürde çeşitli hava durumu tahmin yaklaşımları, sayısal modeller ve hatta yapay zekâ sistemleri incelenmektedir. Okyanus dalgası ve gelgit enerjisi dönüştürme ekipmanlarının deniz ortamında ne kadar iyi çalışacağının tahmin edilmesi, diğer konulara kıyasla daha az araştırılan bir konudur. Bu nedenle, ilk adım olarak şamandıra tipi bir güç alma (power take-off, PTO) cihazının rastgele bir deniz ortamındaki zamansal dinamiklerinin modellenmesi gerçekleştirilmiştir. Rastgele deniz ortamını temsil etmek için bir spektrum tekniği kullanılmış ve çok spektrumlu okyanus dalgası alanını verimli bir şekilde simüle etmek için FFT rutinleri kullanılmıştır. Transfer fonksiyonu yaklaşımı bu çok spektrumlu ortamda PTO cihazının dinamiklerini modellemek için kullanılmıştır. İkinci adım olarak, Uzun Kısa Dönemli Hafıza (Long Short Term Memory, LSTM) derin öğrenme ağı, düşey hızları ve dönüştürücü güç zaman serilerini tahmin etmek için kullanılmıştır. Anlık dönüştürücü gücü ve cihaz dinamiklerinin LSTM tarafından tahmin edilebileceği gösterilmiştir. Araştırmamıza göre, bu tür tahminler için LSTM tabanlı derin öğrenme veya benzeri teknikler kullanılabilir; bu da güç dönüşümünü en üst düzeye çıkarmada, rezonans dinamiklerini öngörmede, aşırı yükleme ve dönüştürücü yapısal hasarını önlemede yardımcı olabilir.

🔖

Cite This Article

Alan, A. R. (2026). Analysis and Forecasting of the Wave Energy Dynamics via LSTM Deep Learning Network. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 38 Sayı: 1, 37–46. https://doi.org/10.35234/fumbd.1595758

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (29)

  1. Clément A, McCullen P, Falcão A, Fiorentino A, Gardner F, Hammarlund K, Lemonis G, Lewis T et.al. Wave energy in Europe: current status and perspectives. Renewable Sustainable Energy Rev. 2002; 6(5): 405-431.
  2. Ruellan M, BenAhmed H, Multon B, Josset C, Babarit A, Clemen, A. Design methodology for a SEAREV wave energy converter. IEEE Trans. Energy Convers. 2010; 25(3): 760-767.
  3. Moretti G, Rosati Papini GP, Daniele L, Forehand D, Ingram D, Vertechy R, Fontana M. Modelling and testing of a wave energy converter based on dielectric elastomer generators. Proc. R. Soc. A. 2019; 475(2222): 20180566.
  4. Tsai CP, Ko CH, Chen YC. Investigation on performance of a modified breakwater-integrated OWC wave energy converter. Sustainability. 2018; 10(3): 643.
  5. Parker RPM, Harrison GP, Chick JP. Energy and carbon audit of an offshore wave energy converter. Proc. Inst. Mech. Eng., Part A: J. Power Energy. 2007; 221(8): 1119-1130.
  6. Ahn KK, Truong DQ, Tien HH, Yoon JI. An innovative design of wave energy converter. Renewable Energy. 2012; 42: 186-194.
  7. Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J. LSTM: A search space odyssey. IEEE Trans. Neural Networks Learn. Syst. 2016; 28(10): 2222-2232.
  8. Jozefowicz R, Zaremba W, Sutskever I. An empirical exploration of recurrent network architectures. In: International Conference on Machine Learning; 2015; Lille, France. pp. 2342-2350.
  9. MacKay DJC. Information Theory, Inference, and Learning Algorithms. Cambridge University Press, 2003.
  10. Mousavi SM, Ghasemi M, Dehghan Manshadi M, Mosavi A. Deep learning for wave energy converter modeling using long short-term memory. Mathematics. 2021; 9(8): 871.
  11. Ni C, Ma X, Wang J. Integrated deep learning model for predicting electrical power generation from wave energy converter. In: 25th International Conference on Automation and Computing (ICAC); 5-7 September 2019; Lancaster, UK. pp. 1-6.
  12. Zhang J, Luo F, Quan X, Wang Y, Shi J, Shen C, Zhang C. Improving wave height prediction accuracy with deep learning. Ocean Modell. 2024; 188: 102312.
  13. Kang J, Zhu X, Shen L, Li M. Fault diagnosis of a wave energy converter gearbox based on an Adam optimized CNN-LSTM algorithm. Renewable Energy. 2024; 231: 121022.
  14. Zhang M, Yuan ZM, Dai SS, Chen ML, Incecik A. LSTM RNN-based excitation force prediction for the real-time control of wave energy converters. Ocean Eng. 2024; 306: 118023.
  15. Sareen K, Panigrahi BK, Shikhola T, Nagdeve R. An integrated decomposition algorithm based bidirectional LSTM neural network approach for predicting ocean wave height and ocean wave energy. Ocean Eng. 2023; 281: 114852.
  16. Lei Y. A wave forecasting method based on probabilistic diffusion LSTM network for model predictive control of wave energy converters. Appl. Soft Comput. 2024; 164: 112006.
  17. Yang Y, Han L, Qiu C, Zhao Y. A short-term wave energy forecasting model using two-layer decomposition and LSTM-attention. Ocean Eng. 2024; 299: 117279.
  18. Wang J, Zhang D, Huang Q, Cui Z. Multiple-step accurate prediction of wave energy: A hybrid model based on quadratic decomposition, SSA and LSTM. Int. J. Green Energy. 2025; 22(1): 100-123.
  19. Goda Y. Random Seas and Design of Maritime Structures. World Scientific Publishing Company, 2010.
  20. Bayındır C. Implementation of a computational model for random directional seas and underwater acoustics. M.S. Thesis, University of Delaware, Newark, Delaware, USA, 2009.
  21. Mérigaud A, Ringwood JV. Free-surface time-series generation for wave energy applications. IEEE J. Oceanic Eng. 2017; 43(1): 19-35.
  22. Alan AR, Bayındır C. Predicting ocean energy harvesting dynamics using LSTM deep learning network. In: The 34th Asian-Pacific Technical Exchange and Advisory Meeting on Marine Structures (TEAM 2020/21); 6-8 December 2021; İstanbul, Turkey.
  23. Saulnier J-B, Ricci P, Clément AH, Falcão AFde O. Mean power output estimation of WECs in simulated sea. In: Proceedings of the 8th European Wave and Tidal Energy Conference; 2009; Uppsala, Sweden.
  24. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997; 9(8): 1735-1780.
  25. Olah C. Understanding LSTM Networks. 2015. https://colah.github.io/posts/2015-08-Understanding-LSTMs/ (Erişim tarihi: 25 Ekim 2024).
  26. Bayındır C. Self-localized solutions of the Kundu-Eckhaus equation in nonlinear waveguides. Results Phys. 2019; 14: 102362.
  27. Bayındır C. Shapes and statistics of the rogue waves generated by chaotic ocean current. In: Proceedings of the 26th International Ocean and Polar Engineering Conference; 26 June-2 July 2016; Rhodes, Greece. pp. ISOPE—I.
  28. Bayındır C. Analytical and numerical aspects of the dissipative nonlinear Schrödinger equation. TWMS J. App. Eng. Math. 2016; 6(1): 135-142.
  29. Bayındır C. Rogue wavefunctions due to noisy quantum tunneling potentials. TWMS J. App. Eng. Math. 2017; 7(2): 236-247.