FDNet: Frequency filter enhanced dual LSTM network for wind power forecasting

A CNN encoder decoder LSTM model for sustainable wind power predictive analytics

With the rising demand for environmental protection, wind energy has made considerable progress as a clean energy source. Due to the uncertainty of wind power generation, accurate forecasting of wind power is conducive to achieving stable grid-connected control of wind turbines. This paper proposes an ultra-short-term wind power forecasting model composed of variational modal decomposition (VMD) and long short-term memory (LSTM) networks. Obtain the recorded historical wind speed and historical power from the wind field data acquisition and monitoring control system (SCADA), and use VMD to decompose and reconstruct the historical wind speed of the wind field to form 5 training data sets. Using historical power, historical wind speed, and predicted wind speed as input, wind power forecasts for the next 4 hours (15 minutes apart) are made. In order to evaluate the prediction ability of the proposed model, two algorithms, LSTM and XGBoost, are used for prediction. Taking root mean square error (RMSE) and mean absolute error (MAE) as evaluation indicators, the results show that the prediction accuracy of wind power is significantly improved after VMD processing, and the performance of LSTM is better than XGBoost in the two evaluation indicators.

Accurate wind power prediction can reduce the negative impact of wind power on power grid and reduce the operation cost of power system. Wind power forecasting is of great significance in spot trading, but the instability of wind power series brings difficulties to forecasting. With the rapid development of deep learning technology, prediction algorithm based on deep learning has been widely used in wind power prediction. The long short-term memory (LSTM) network performs well in a variety of prediction scenarios, but there is still room for improvement. In order to improve the prediction accuracy of LSTM in wind power prediction, this paper adopts a new gating mechanism in LSTM network, which can improve the context information modeling ability of LSTM network. The experimental results based on real data show that the proposed improved LSTM prediction model can improve the prediction accuracy of LSTM prediction model in ultra-short term wind power prediction scenarios.

This study proposes a novel deep learning framework for gold futures price forecasting, combining Long ShortTerm Memory (LSTM) networks with a temporal attention mechanism and a comprehensive set of technical indicators. While traditional LSTMs struggle with temporal relevance in volatile markets, our attention-enhanced architecture dynamically reweights critical time steps in the input sequence, including momentum, volatility, and trend signals, to improve accuracy and interpretability. Empirical evaluation on gold futures data (2010-2025) demonstrates the model's superiority, achieving a Mean Absolute Percentage Error (MAPE) of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1. 1 3 \%}$</tex> and a coefficient of determination (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{2}$</tex>) of 0.991, with a 34.7 % reduction in Mean Absolute Error (MAE) after calibration. The attention mechanism further provides actionable insights by identifying dominant market regimes, while a lag-aware calibration module enhances directional forecasting. By bridging sequential modeling with dynamic temporal weighting, this work advances financial time-series forecasting, offering a robust tool for traders and policymakers navigating commodity market uncertainty.

Wind power forecasting based on a novel gated recurrent neural network model

The developed research includes an Long Short-Term Memory (LSTM) network with IoT sensor data for the management of rice crop irrigation. Optimizing the amount of water required for rice crops is very critical, based on real-time predictions of the actual environmental and soil parameters including moisture, temperature, humidity, and rainfall as well as all other possible related factors. IoT sensors installed in agricultural fields gathered data, which was transmitted to a controller and then uploaded to the cloud for further processing. The training dataset contained 5,600 records. In this research, 70% was used for training and the rest 30% for testing. Three LSTM models were used for analyzing sensor data and predicting the need for irrigation and controlling the irrigation pump accordingly. These were Vanilla LSTM, Stacked LSTM, and Bidirectional LSTM. It was evaluated the performance of the models developed using precision, recall, F1 score, accuracy, and other performance measures such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> Score. Bidirectional LSTM was determined to have the best performance, with MAE at 0.15, RMSE at 0.24, and an R2 score of 0.93, exhibiting high accuracy and predictive power. The Stacked LSTM and Vanilla LSTM also gave fair results, in terms of having R2 values of 0.89 and 0.84, respectively. The number of training and memory used for the computation were also given, with Vanilla LSTM taking least, followed by Stacked LSTM and Bidirectional LSTM. These results suggest that the LSTM networks can potentially be capable of improving the irrigation management such that more water is conserved and, subsequently, more suitable for agricultural productivity.

A new distributed decomposition–reconstruction–ensemble learning paradigm for short-term wind power prediction

This study proposes an enhanced deep learning framework for accurately estimating the state of health (SOH) of lithium-ion batteries (LIBs), leveraging a refined Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM)-Attention architecture. To improve prediction accuracy and robustness, a novel Multi-Scale Adaptive Wasserstein-Huber Loss (MSAWH Loss) is introduced, which combines the strengths of Huber loss and multi-scale Wasserstein distance to effectively handle outliers and capture complex degradation patterns. Furthermore, an Uncertainty-Guided Adaptive Bayesian Optimization (UGABO) algorithm is employed to optimize model hyperparameters, achieving efficient convergence in high-dimensional and noisy parameter spaces while maintaining a balance between exploration and exploitation. To enhance generalization, four complementary data augmentation techniques—linear interpolation, data slicing, sequence flipping, and cross-sample mixing—are applied to the National Aeronautics and Space Administration (NASA) charge-discharge dataset, significantly enriching the training data. Additionally, a Model Predictive Control (MPC) mechanism is integrated to correct long-horizon prediction errors, dynamically refining outputs based on recent deviations and maintaining consistency with real-world battery constraints. Experimental results demonstrate that the proposed framework outperforms baseline models, achieving a 20.6% reduction in mean absolute error (MAE), an 18.6% reduction in root mean squared error (RMSE), and a 0.1% improvement in R-squared (R 2 ). These findings highlight the effectiveness of integrating adaptive loss design, automated hyperparameter optimization, strategic data augmentation, and feedback-based error correction in advancing SOH prediction performance for lithium-ion batteries.

Underwater wireless sensor network (UWSN) is highly vulnerable to packet loss due to varied features of underwater channels, including multipath fading, high latency, and environmental interference. Accurate prediction of packet loss is critical for improving data reliability and network performance. Our research presents a new approach to forecasting using a combination of autoregressive moving average (ARMA) and long short-term memory (LSTM) networks which are statistical models. A synthetic dataset was generated to facilitate model development and evaluation, simulating realistic UWSN conditions by varying key parameters such as signal-to-noise ratio (SNR), received signal strength indicator (RSSI), depth, distance, and temperature. The ARMA model captures linear temporal trends, while the LSTM network is trained on the ARMA residuals to learn nonlinear correction patterns. The findings indicate that the hybrid ARMA-LSTM model exhibits a marked superiority over the standalone ARMA model, achieving an approximate 87.5% reduction in mean absolute error (MAE), an 84% enhancement in root mean square error (RMSE),a significant boost in predictive accuracy as reflected by the R² score, which improved from -0.45 to nearly 0. The results highlight the hybrid method a strong and precise solution for predicting packet loss in UWSN, directly impacting the improvement of reliability in underwater communication.

With the in-depth implementation of China’s “National Strategy for Building a Strong Transportation Network,” the scale of expressway construction has continued to expand. As a result, the number of high-fill and deep-cut subgrade projects under complex geological conditions has increased significantly, leading to a surge in landslide-related issues. Consequently, accurate prediction of slope displacement is of critical importance for early warning and prevention of landslide disasters. This study proposes a hybrid prediction model, VMD-MPA-LSSVM-LSTM (VMLL), which integrates Variational Mode Decomposition (VMD), Marine Predators Algorithm (MPA), Least Squares Support Vector Machine (LSSVM), and Long Short-Term Memory (LSTM) networks. Using monitoring data from the high-fill embankment slope at Hongtuyao as the research subject, the VMLL model is employed to predict slope displacement based on small-sample data. The objective is to provide a more accurate method for early warning of slope displacement. Firstly, the original monitoring data are decomposed into trend displacement components and fluctuation displacement components using Variational Mode Decomposition (VMD). Subsequently, the trend component and the fluctuation component are predicted using Least Squares Support Vector Machine (LSSVM) and Long Short-Term Memory (LSTM) networks, respectively. Finally, the Marine Predators Algorithm (MPA) is employed to optimize the hyperparameters of the predictive models. Based on this framework, a VMLL-based slope displacement prediction model is constructed. To verify the superiority of the VMLL model, a comparative analysis was conducted against LSSVM, LSTM, and the VMD-LSSVM-LSTM models. The results demonstrate that the VMLL model achieves the highest prediction accuracy, with a Mean Absolute Percentage Error (MAPE) of 0.4022%, a Mean Absolute Error (MAE) of 0.016 mm, a Root Mean Square Error (RMSE) of 0.0206 mm, a coefficient of determination (R²) of 94.08%, and a Variance Accounted For (VAF) of 96.5%. Compared with the other three models, the VMLL model reduces the MAPE, MAE, and RMSE by 30.41–67.62%, 30.38–67.40%, and 27.32–71.00%, respectively. Meanwhile, it improves the R² and VAF by 5.95–217.51% and 0.38–11.48%, respectively. These improvements clearly demonstrate that the VMLL model outperforms the other models, indicating its significant advantage over single prediction models. Furthermore, three additional datasets were used to evaluate the model’s performance. The average values of the performance evaluation metrics for these datasets were 0.6207% (MAPE), 0.0238 mm(MAE), 0.0273 mm(RMSE), 90.33%(R²), and 96.81%(VAF), respectively. These results demonstrate the high accuracy and strong robustness of the proposed model in predicting both horizontal displacement and vertical settlement of slopes, providing a reliable methodological framework for slope stability assessment and landslide disaster early warning.

Wind power is one of the most large-scale new energy sources. But wind power instability will affect power grid safety, which is in a great need for wind power forecasting algorithms. To accurately predict wind power and reduce power grid fluctuations, it proposes a new wind power forecasting (WPF) algorithm based on long short-term memory (LSTM) neural network using wind farm real operation data. First, the wind farm power data are de-averaged and divided into two different sets in order to meet the requirements of the algorithm. Then, structure of the LSTM neural network is designed and hyper-parameters are adjusted to improve accuracy of forecasting. Finally, the definite LSTM neural network is used for forecasting the power data in time series to derive the power forecasting value, which is reduced and evaluated according to the original size. The results show that compared with other forecasting methods, in short-term WPF at different time scales, this algorithm has smaller errors in power forecasting results, which is also suitable for long-term WPF.

The prediction of wind energy generation is important to enhance the performance and dependability of renewable energy systems due to the rising demand for wind-generated electricity and advancements in wind energy technology competitiveness. This study leverages advanced machine learning (ML) and some other statistical and deep learning based time series forecasting models to enhance the accuracy of wind energy predictions. This comprehensive analysis includes nine ML models—Linear Regression, Random Forests (RF), Gradient Boosting Machines (GBM), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), AdaBoost, XGBoost, Support Vector Regression (SVR), and Neural Networks—as well as Four time-series forecasting models—ARIMA, Temporal Convolutional Networks (TCNs), Long Short-Term Memory (LSTM) networks and GRU. Each ML model underwent rigorous cross-validation to ensure optimal performance. The assessment criteria utilized here comprised the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² Score. It was found that among the nine ML models, Random Forests, GBM and KNN consistently provided superior accuracy and robustness, making them the top choices for wind energy prediction whereas the performance of linear regression, SVM and SVR were very poor for the considered dataset. From the experiment, Random Forest, GBM, and KNN showed the best performance with low MSE values of 0.77, 1.95, and 1.51 respectively, while other models had MSEs above 7.5, with AdaBoost reaching 30. Their RMSEs (0.88, 1.40, 1.23) and MAEs (0.093, 0.73, 0.10) also indicate strong predictive accuracy compared to the rest.In this paper, time series forecasting, TCNs, LSTM and GRU networks showed strong capabilities in capturing temporal dependencies and trends within the wind energy data. Visualization techniques were employed to compare model performances comprehensively, providing clear insights into their predictive power. Therefore, this present study offers a robust framework for researchers and practitioners aiming to leverage machine learning and time series forecasting in the realm of renewable energy prediction.

Deep learning approaches for bias correction in WRF model outputs for enhanced solar and wind energy estimation: A case study in East and West Malaysia

Offshore wind turbines (OWTs) have complex operating conditions and are prone to accidents. Timely and accurate vibration prediction can reduce the probability of failure of OWTs. To address this issue, this study proposed a vibration prediction model based on long short-term memory (LSTM) network. The proposed prediction model was applied to an OWT in an offshore wind farm in China, and three evaluation indicators, i.e. mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE), were used to verify the vibration prediction performance of LSTM. The results demonstrated that the prediction accuracy of LSTM was better than that of back propagation (BP) neural network, and LSTM had optimum engineering practicability. The prediction accuracy of LSTM and BP neural networks decreased with an increase in prediction durations. However, the prediction accuracy of LSTM was higher. This study improves the online safety monitoring of OWTs.

Wind power is one of the most efficient renewable resources without emissions. Nonetheless, it is difficult to exactly forecast wind power generation given historical power and wind speed information, the failure of which may cost the risk of large-scale outages. This article takes a close look at the artificial recurrent neural network framework in the application of wind power forecasting. More intelligent mechanisms using attention to capture spatial-temporal patterns within historical data are emphasized in this work and are shown to be state-of-the-art for short-term wind power forecasting. Our experiments at a wind farm in southeast Australia using only the historical wind power generation and wind speed records from ambient weather stations show that, e.g., 7.4750% in mean absolute error (MAE) and 0.3345 in the coefficient of variation in the root mean squared error (CV-RMSE) for half-hour-ahead prediction. To interpret how the three models under consideration—the long- and short-term time-series network (LSTNet), the temporal pattern attention-based long short-term memory (TPA-LSTM) and the dual-stage attention-based recurrent neural network (DA-RNN)—work, we visualize and analyze the details of the models so that further improvement can be made by combining the advantageous components of the models.