High and low frequency wind power prediction based on Transformer and BiGRU-Attention

Energy, Journal Year: 2023, Volume and Issue: 288, P. 129753 - 129753

Published: Dec. 1, 2023

Language: Английский

---

Spatio-temporal deep learning model for accurate streamflow prediction with multi-source data fusion

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 178, P. 106091 - 106091

Published: May 28, 2024

Language: Английский

---

Combined Ultra-Short-Term Photovoltaic Power Prediction Based on CEEMDAN Decomposition and RIME Optimized AM-TCN-BiLSTM

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 134847 - 134847

Published: Feb. 1, 2025

Language: Английский

---

Multistep short-term wind power forecasting model based on secondary decomposition, the kernel principal component analysis, an enhanced arithmetic optimization algorithm, and error correction

Energy, Journal Year: 2023, Volume and Issue: 286, P. 129640 - 129640

Published: Nov. 13, 2023

Language: Английский

---

Research on multi-digital twin and its application in wind power forecasting

Energy, Journal Year: 2024, Volume and Issue: 292, P. 130269 - 130269

Published: Jan. 5, 2024

Language: Английский

---

A Comprehensive Review of Wind Power Prediction Based on Machine Learning: Models, Applications, and Challenges

Energies, Journal Year: 2025, Volume and Issue: 18(2), P. 350 - 350

Published: Jan. 15, 2025

Wind power prediction is essential for ensuring the stability and efficient operation of modern systems, particularly as renewable energy integration continues to expand. This paper presents a comprehensive review machine learning techniques applied wind prediction, emphasizing their advantages over traditional physical statistical models. Machine methods, especially deep approaches such Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), ensemble like XGBoost, excel in addressing nonlinearity complexity data. The also explores critical aspects data preprocessing, feature selection strategies, model optimization techniques, which significantly enhance accuracy robustness. Challenges acquisition difficulties, complex terrain influences, sensor quality issues are examined depth, with proposed solutions discussed. Additionally, highlights future research directions, including potential multi-model fusion, emerging technologies Transformers, smart sensors IoT develop intelligent, automated, reliable systems. By existing challenges leveraging advanced this work provides valuable insights into current state offers strategic guidance enhancing applicability reliability models practical scenarios.

Language: Английский

---

An Ultra-Short-Term Wind Power Forecasting Model Based on EMD-EncoderForest-TCN

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 60058 - 60069

Published: Jan. 1, 2024

Accurate wind power prediction helps to stabilize the operation of system, improve utilization rate renewable energy, reduce dependence on traditional and achieve sustainable energy development. An ultra short-term method integrating EMD-EncoderForest-TCN is proposed address difficulty predicting due frequent changes in speed. Firstly, time-series input data model decomposed into high-frequency low-frequency components using Empirical Mode Decomposition. Then, based EncoderForest TCN model, differential information extraction performed components. The regularizes captures trend patterns data. models time series capture complex structures power. Finally, convolutional neural networks, output results each part are calculated accurate Based operational an actual farm, conduct a case study analysis. show that can power, with accuracy improvement 2.57%.

Language: Английский

---

Short-term wind power prediction based on improved variational modal decomposition, least absolute shrinkage and selection operator, and BiGRU networks

Energy, Journal Year: 2024, Volume and Issue: 303, P. 131951 - 131951

Published: June 7, 2024

Language: Английский

---

An Integrated Complete Ensemble Empirical Mode Decomposition with Adaptive Noise to Optimize LSTM for Significant Wave Height Forecasting

Journal of Marine Science and Engineering, Journal Year: 2023, Volume and Issue: 11(2), P. 435 - 435

Published: Feb. 16, 2023

In recent years, wave energy has gained attention for its sustainability and cleanliness. As one of the most important parameters energy, significant height (SWH) is difficult to accurately predict due complex ocean conditions ubiquitous chaotic phenomena in nature. Therefore, this paper proposes an integrated CEEMDAN-LSTM joint model. Traditional computational fluid dynamics (CFD) a long calculation period high capital consumption, but artificial intelligence methods have advantage accuracy fast convergence. CEEMDAN commonly used method digital signal processing mechanical engineering, not yet been SWH prediction. It better performance than EMD EEMD more suitable LSTM addition, also novel filter formulation outliers based on improved violin-box plot. The final empirical results show that significantly outperforms each forecast duration, improving prediction accuracy. particular, duration 1 h, improvement over LSTM, with 71.91% RMSE, 68.46% MAE 6.80% NSE, respectively. summary, our model can improve real-time scheduling capability marine engineering maintenance operations.

Language: Английский

---

A comprehensive wind power prediction system based on correct multiscale clustering ensemble, similarity matching, and improved whale optimization algorithm–A case study in China

Renewable Energy, Journal Year: 2025, Volume and Issue: unknown, P. 122529 - 122529

Published: Feb. 1, 2025

Language: Английский

---