An Adaptive Hybrid Model for Wind Power Prediction Based on the IVMD-FE-Ad-Informer

Entropy, Год журнала: 2023, Номер 25(4), С. 647 - 647

Опубликована: Апрель 12, 2023

Accurate wind power prediction can increase the utilization rate of generation and maintain stability system. At present, a large number studies are based on mean square error (MSE) loss function, which generates many errors when predicting original data with random fluctuation non-stationarity. Therefore, hybrid model for named IVMD-FE-Ad-Informer, is Informer an adaptive function combines improved variational mode decomposition (IVMD) fuzzy entropy (FE), proposed. Firstly, decomposed into K subsequences by IVMD, possess distinct frequency domain characteristics. Secondly, sub-series reconstructed new elements using FE. Then, robust Ad-Informer predicts predicted values each element superimposed to obtain final results power. Finally, analyzed evaluated two real datasets collected from farms in China Spain. The demonstrate that proposed superior other models performance accuracy different datasets, this effectively meet demand actual prediction.

Язык: Английский

---

A contrastive learning-based framework for wind power forecast

Expert Systems with Applications, Год журнала: 2023, Номер 230, С. 120619 - 120619

Опубликована: Июнь 5, 2023

Язык: Английский

---

Short-term wind speed forecasting based on a hybrid model of ICEEMDAN, MFE, LSTM and informer

PLoS ONE, Год журнала: 2023, Номер 18(9), С. e0289161 - e0289161

Опубликована: Сен. 8, 2023

Wind energy, as a kind of environmentally friendly renewable has attracted lot attention in recent decades. However, the security and stability power system is potentially affected by large-scale wind grid due to randomness intermittence speed. Therefore, accurate speed prediction conductive operation. A hybrid model based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), Multiscale Fuzzy Entropy (MFE), Long short-term memory (LSTM) INFORMER proposed this paper. Firstly, data are decomposed into multiple intrinsic mode functions (IMFs) ICEEMDAN. Then, MFE values each calculated, modes similar aggregated obtain new subsequences. Finally, subsequence predicted informer LSTM, sequence selects one better performance than two predictors, results superimposed final results. The also compared other seven related models four evaluation metrics under different periods verify its validity applicability. experimental indicate that ICEEMDAN, MFE, LSTM exhibits higher accuracy greater

Язык: Английский

---

A fuzzy time series forecasting model with both accuracy and interpretability is used to forecast wind power

Applied Energy, Год журнала: 2023, Номер 353, С. 122015 - 122015

Опубликована: Окт. 4, 2023

Язык: Английский

---

Forecasting of wind speed under wind-fire coupling scenarios by combining HS-VMD and AM-LSTM

Ecological Informatics, Год журнала: 2023, Номер 77, С. 102270 - 102270

Опубликована: Авг. 22, 2023

Язык: Английский

---