Accurate one step and multistep forecasting of very short-term PV power using LSTM-TCN model

Renewable Energy, Journal Year: 2023, Volume and Issue: 205, P. 1010 - 1024

Published: Feb. 7, 2023

Language: Английский

---

Short-term wind power prediction based on two-layer decomposition and BiTCN-BiLSTM-attention model

Energy, Journal Year: 2023, Volume and Issue: 285, P. 128762 - 128762

Published: Aug. 14, 2023

Language: Английский

---

Thermal fault prognosis of lithium-ion batteries in real-world electric vehicles using self-attention mechanism networks

Applied Thermal Engineering, Journal Year: 2023, Volume and Issue: 226, P. 120304 - 120304

Published: March 3, 2023

Language: Английский

---

Learning based short term wind speed forecasting models for smart grid applications: An extensive review and case study

Electric Power Systems Research, Journal Year: 2023, Volume and Issue: 222, P. 109502 - 109502

Published: June 1, 2023

Language: Английский

---

Wind power forecasting based on hybrid CEEMDAN-EWT deep learning method

Renewable Energy, Journal Year: 2023, Volume and Issue: 218, P. 119357 - 119357

Published: Sept. 22, 2023

Language: Английский

---

Elman neural network considering dynamic time delay estimation for short-term forecasting of offshore wind power

Applied Energy, Journal Year: 2024, Volume and Issue: 358, P. 122671 - 122671

Published: Jan. 21, 2024

Language: Английский

---

A short-term forecasting method for photovoltaic power generation based on the TCN-ECANet-GRU hybrid model

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: March 21, 2024

Abstract Due to the uncertainty of weather conditions and nonlinearity high-dimensional data, as well need for a continuous stable power supply system, traditional regression analysis time series forecasting methods are no longer able meet high accuracy requirements today's PV forecasting. To significantly improve prediction short-term output power, this paper proposes method based on hybrid model temporal convolutional networks gated recurrent units with an efficient channel attention network (TCN-ECANet-GRU) using generated data Australian station research object. First, (TCNs) used spatial feature extraction layers, (ECANet) is embedded enhance capture capability network. Then, GRU extract timing information final prediction. Finally, experimental validation, TCN-ECANet-GRU generally outperformed other baseline models in all four seasons year according three performance assessment metrics: normalized root mean square error (RMSE), absolute (MAE) coefficient determination (R 2 ). The best RMSE, MAE R reached 0.0195, 0.0128 99.72%, respectively, maximum improvements 11.32%, 8.57% 0.38%, over those suboptimal model. Therefore, proposed effective at improving accuracy. Using method, concludes multistep predictions 3, 6, 9 steps, which also indicates that outperforms models.

Language: Английский

---

A novel model for ultra-short term wind power prediction based on Vision Transformer

Energy, Journal Year: 2024, Volume and Issue: 294, P. 130854 - 130854

Published: March 2, 2024

Language: Английский

---

Ultra-short-term wind farm cluster power prediction based on FC-GCN and trend-aware switching mechanism

Energy, Journal Year: 2024, Volume and Issue: 290, P. 130238 - 130238

Published: Jan. 2, 2024

Language: Английский

---

Ensemble models of TCN-LSTM-LightGBM based on ensemble learning methods for short-term electrical load forecasting

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 134757 - 134757

Published: Jan. 1, 2025

Language: Английский

---