Sustainable development using integrated energy systems and solar, biomass, wind, and wave technology

Renewable Energy, Journal Year: 2024, Volume and Issue: unknown, P. 121359 - 121359

Published: Sept. 1, 2024

Language: Английский

---

Short-term wind power forecasting based on multi-scale receptive field-mixer and conditional mixture copula

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 164, P. 112007 - 112007

Published: July 17, 2024

Language: Английский

---

A novel hybrid BWO-BiLSTM-ATT framework for accurate offshore wind power prediction

Ocean Engineering, Journal Year: 2024, Volume and Issue: 312, P. 119227 - 119227

Published: Sept. 12, 2024

Language: Английский

---

1VMD-ATT-LSTM Electricity Price Prediction Based on Grey Wolf Optimization Algorithm in Electricity Markets Considering Renewable Energy

Renewable Energy, Journal Year: 2024, Volume and Issue: unknown, P. 121408 - 121408

Published: Sept. 1, 2024

Language: Английский

---

A novel multi-task fault detection model embedded with spatio-temporal feature fusion for wind turbine pitch and drive train systems

Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 65, P. 103194 - 103194

Published: Feb. 11, 2025

Language: Английский

---

Short-term wind speed prediction method based on prior wind direction knowledge and multi-period decoupling

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 153, P. 110596 - 110596

Published: April 22, 2025

Language: Английский

---

Predicting Oil Temperature in Electrical Transformers Using Neural Hierarchical Interpolation

Journal of Engineering, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

Effective electricity consumption planning is critical for power distribution. Ensuring the distribution network aligns with expected demand fluctuations a challenging task influenced by various time‐related and seasonal variables. This study focuses on improving transformer oil temperature forecasting, an indicator of health, using neural hierarchical interpolation time series (NHITS) model. The NHITS model’s architecture designed to handle long‐term forecasting efficiently, making it ideal capturing extended trends in temperature. It incorporates multirate signal sampling via MaxPool layers merge predictions across different scales. proposed methodology involves two key phases: data preparation model development. In phase, (ETT) datasets are used, normalized standard scaler, essential features such as external load selected. During development trained its hyperparameters optimized optimal performance. evaluates performance under conditions, including comparison multivariate univariate series, effects short horizons, impact temporal resolution. was validated ETT dataset, our results were benchmarked against previous that employed same dataset used Informer indicate outperforms model, showing average decrease 51.37% mean squared error (MSE) 37.83% absolute (MAE). These findings highlight ability capture both short‐term characteristics data, promising solution temperatures.

Language: Английский

---

WindDragon: automated deep learning for regional wind power forecasting

Environmental Data Science, Journal Year: 2025, Volume and Issue: 4

Published: Jan. 1, 2025

Abstract Achieving net-zero carbon emissions by 2050 necessitates the integration of substantial wind power capacity into national grids. However, inherent variability and uncertainty energy present significant challenges for grid operators, particularly in maintaining system stability balance. Accurate short-term forecasting is therefore essential. This article introduces an innovative framework regional over horizons (1–6 h), employing a novel Automated Deep Learning regression called WindDragon. Specifically designed to process speed maps, WindDragon automatically creates models leveraging Numerical Weather Prediction (NWP) data deliver state-of-the-art forecasts. We conduct extensive evaluations on from France year 2020, benchmarking against diverse set baselines, including both deep learning traditional methods. The results demonstrate that achieves improvements forecast accuracy considered highlighting its potential enhancing reliability face increased integration.

Language: Английский

---

A Novel Hybrid Deep Learning Model for Day-Ahead Wind Power Interval Forecasting

Sustainability, Journal Year: 2025, Volume and Issue: 17(7), P. 3239 - 3239

Published: April 5, 2025

Accurate interval forecasting of wind power is crucial for ensuring the safe, stable, and cost-effective operation grids. In this paper, we propose a hybrid deep learning model day-ahead forecasting. The begins by utilizing Gaussian mixture (GMM) to cluster daily data with similar distribution patterns. To optimize input features, feature selection (FS) method applied remove irrelevant data. empirical wavelet transform (EWT) then employed decompose both numerical weather prediction (NWP) into frequency components, effectively isolating high-frequency components that capture inherent randomness volatility A convolutional neural network (CNN) used extract spatial correlations meteorological while bidirectional gated recurrent unit (BiGRU) captures temporal dependencies within sequence. further enhance accuracy, multi-head self-attention mechanism (MHSAM) incorporated assign greater weight most influential elements. This leads development based on GMM-FS-EWT-CNN-BiGRU-MHSAM. proposed validated through comparison benchmark demonstrates superior performance. Furthermore, forecasts generated using NPKDE shows new achieves higher accuracy.

Language: Английский

---

Adaptive expert fusion model for online wind power prediction

Neural Networks, Journal Year: 2024, Volume and Issue: 184, P. 107022 - 107022

Published: Dec. 10, 2024

Wind power prediction is a challenging task due to the high variability and uncertainty of wind generation weather conditions. Accurate timely essential for optimal system operation planning. In this paper, we propose novel Adaptive Expert Fusion Model (EFM+) online prediction. EFM+ an innovative ensemble model that integrates strengths XGBoost self-attention LSTM models using dynamic weights. can adapt real-time changes in conditions data distribution by updating weights based on performance error recent similar samples. enables Bayesian inference updates with new data. We conduct extensive experiments real-world farm dataset evaluate EFM+. The results show outperforms existing accuracy error, demonstrates robustness stability across various scenarios. also sensitivity ablation analyses assess effects different components parameters promising technique handle nonstationarity generation.

Language: Английский

---