A novel network training approach for solving sample imbalance problem in wind power prediction

Energy Conversion and Management, Journal Year: 2023, Volume and Issue: 283, P. 116935 - 116935

Published: March 22, 2023

Language: Английский

---

The ultra-short-term wind power point-interval forecasting model based on improved variational mode decomposition and bidirectional gated recurrent unit improved by improved sparrow search algorithm and attention mechanism

Energy, Journal Year: 2023, Volume and Issue: 288, P. 129714 - 129714

Published: Nov. 20, 2023

Language: Английский

---

A novel deep learning-based evolutionary model with potential attention and memory decay-enhancement strategy for short-term wind power point-interval forecasting

Applied Energy, Journal Year: 2024, Volume and Issue: 360, P. 122785 - 122785

Published: Feb. 6, 2024

Language: Английский

---

Probabilistic optimization based adaptive neural network for short-term wind power forecasting with climate uncertainty

International Journal of Electrical Power & Energy Systems, Journal Year: 2024, Volume and Issue: 157, P. 109897 - 109897

Published: Feb. 29, 2024

Advanced wind power prediction technique plays an essential role in the stable operation of grid with large-scale integration power. Most research focuses on distance-based static classification where subjective nature initial center selection increases uncertainty prediction. And data a daily basis neglects potentially significant climate changes at smaller time scales. To address these issues, improved snake optimization-long short-term memory (ISO-LSTM) model Gaussian mixture (GMM) clustering is proposed to forecast from adaptive perspective. By exploiting merits probabilistic classification, K-means optimized GMM enables appropriate feature modelling for substantial Then ISO algorithm exhibits higher search accuracy and better suited finding hyperparameter combinations LSTM neural networks. The National Aeronautics Space Administration (NASA) US used validate effectiveness method. Compared traditional clustering, has increased by 2.63 %. Simultaneously, adoption enhanced algorithm, further 7.27 Different existing models have also been tested; it shows that demonstrates accuracy.

Language: Английский

---

Probability Density Forecasting of Wind Power Based on Transformer Network with Expectile Regression and Kernel Density Estimation

Electronics, Journal Year: 2023, Volume and Issue: 12(5), P. 1187 - 1187

Published: March 1, 2023

A comprehensive and accurate wind power forecast assists in reducing the operational risk of generation, improves safety stability system, maintains balance generation. Herein, a hybrid probabilistic density forecasting approach based on transformer network combined with expectile regression kernel estimation (Transformer-ER-KDE) is methodically established. The prediction results various levels are exploited as input estimation, optimal bandwidth achieved by employing leave-one-out cross-validation to arrive at complete probability curve. In order more assess predicted results, two sets evaluation criteria constructed, including metrics for point interval prediction. generation dataset from official website Belgian grid company Elia employed validate proposed approach. experimental reveal that Transformer-ER-KDE method outperforms mainstream recurrent neural models terms error. Further, suggested capable accurately capturing uncertainty through construction intervals curves.

Language: Английский

---

An enhanced feature extraction based long short-term memory neural network for wind power forecasting via considering the missing data reconstruction

Energy Reports, Journal Year: 2023, Volume and Issue: 11, P. 97 - 114

Published: Nov. 27, 2023

Wind power forecasting plays a significant role in regulating the peak and frequency of system, which can improve wind receiving capacity. Despite plenty methods have been proposed to fortify accuracy forecasting, existing models do not consider reconstruction missing data extract spatiotemporal features from data. To address these issues, this study proposes an improved long short-term memory (LSTM) network based method reconstruct capture In order model, multiple imputation technique (MIT) is first developed fill up samples with reconstructed by analyzing correlation among variables raw Secondly, exploit spatial temporal reduce low computation complexity, new parallel convolutional involving dilated convolution causal established for extraction. Finally, further performance, LSTM applied long-term trends reveal internal relations derived features. The experimental results on benchmark dataset both demonstrate that obtain better performance.

Language: Английский

---

Advancements in wind power forecasting: A comprehensive review of artificial intelligence-based approaches

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: May 1, 2024

Language: Английский

---

An improved wind power uncertainty model for day-ahead robust scheduling considering spatio-temporal correlations of multiple wind farms

International Journal of Electrical Power & Energy Systems, Journal Year: 2022, Volume and Issue: 145, P. 108674 - 108674

Published: Oct. 2, 2022

Language: Английский

---

Two-stage correction prediction of wind power based on numerical weather prediction wind speed superposition correction and improved clustering

Energy, Journal Year: 2024, Volume and Issue: 302, P. 131797 - 131797

Published: May 27, 2024

Language: Английский

---

Grid-Friendly Integration of Wind Energy: A Review of Power Forecasting and Frequency Control Techniques

Sustainability, Journal Year: 2024, Volume and Issue: 16(21), P. 9535 - 9535

Published: Nov. 1, 2024

Integrating renewable energy sources into power systems is crucial for achieving global decarbonization goals, with wind experiencing the most growth due to technological advances and cost reductions. However, large-scale farm integration presents challenges in balancing generation demand, mainly variability reduced system inertia from conventional generators. This review offers a comprehensive analysis of current literature on forecasting frequency control techniques support grid-friendly integration. It covers strategies enhancing management, focusing models, systems, role storage (ESSs). Machine learning are widely used forecasting, supervised machine (SML) being effective short-term predictions. Approximately 33% studies utilize SML. Hybrid methods, combining various or without ESS, have emerged as promising high penetration. In conversion (WECSs), inertial combined primary prevalent, leveraging kinetic stored turbines. The highlights trend toward fast response control, focus methods regulation WECS. These findings emphasize ongoing need advanced ensure stability reliability future grids.

Language: Английский

---