A Multi-Channel Spatiotemporal Segnet Model for Short Term Wind Power Prediction with Sequence Decomposition and Reconstruction

Published: Jan. 1, 2025

Language: Английский

---

Short-term wind power prediction with a new PCC-GWO-VMD and BiGRU hybrid model enhanced by attention mechanism

Journal of Renewable and Sustainable Energy, Journal Year: 2025, Volume and Issue: 17(3)

Published: May 1, 2025

The integration of wind power into the grid significantly depends on accuracy and reliability prediction. However, task prediction faces significant challenges due to stochastic nature speed. This study proposes a novel deep hybrid short-term model: PCC-GWO-VMD-BiGRU-Attention. model integrates Pearson correlation coefficient (PCC), variational mode decomposition (VMD), gray wolf optimization (GWO), attention mechanism optimized bidirectional gated recurrent unit (BiGRU-Attention) enhance robustness, while quantifying uncertainty through ensemble methods. First, PCC is used identify key factors affecting power, thereby improving model's computational performance. Second, GWO can dynamically adjust parameters [K, α] in VMD for optimal input time series, accuracy. Finally, BiGRU-Attention utilized extract global temporal features historical sequences, focuses information sequences further Experimental results show that, compared other learning models, this achieves highest with an root mean square error 0.2677 Megawatt (MW), absolute 0.1509 0.0717 determination (R2) 0.9605. method has practical value contributes ensuring safe operation farms.

Language: Английский

---

Solar irradiance forecasting using a novel hybrid deep ensemble reinforcement learning algorithm

Sustainable Energy Grids and Networks, Journal Year: 2022, Volume and Issue: 32, P. 100903 - 100903

Published: Aug. 9, 2022

Language: Английский

---

An Intelligent Approach to Short-Term Wind Power Prediction Using Deep Neural Networks

Journal of Artificial Intelligence and Soft Computing Research, Journal Year: 2023, Volume and Issue: 13(3), P. 197 - 210

Published: June 1, 2023

Abstract In this paper, an intelligent approach to the Short-Term Wind Power Prediction (STWPP) problem is considered, with use of various types Deep Neural Networks (DNNs). The impact prediction time horizon length on accuracy, and influence temperature effectiveness have been analyzed. Three DNNs implemented tested, including: CNN (Convolutional Networks), GRU (Gated Recurrent Unit), H-MLP (Hierarchical Multilayer Perceptron). DNN architectures are part Learning (DLP) framework that applied in System (DLPPS). system trained based data comes from a real wind farm. This significant because results strongly depend weather conditions specific locations. obtained proposed system, for data, presented compared. best result has achieved network. key advantage high using minimal subset parameters. power farms very important as capacity shown rapid increase, become promising source renewable energies.

Language: Английский

---

Wind power forecasting: A temporal domain generalization approach incorporating hybrid model and adversarial relationship-based training

Applied Energy, Journal Year: 2023, Volume and Issue: 355, P. 122266 - 122266

Published: Nov. 18, 2023

Language: Английский

---