Short-term multi-hour ahead country-wide wind power prediction for Germany using gated recurrent unit deep learning

Renewable and Sustainable Energy Reviews, Journal Year: 2022, Volume and Issue: 167, P. 112700 - 112700

Published: June 24, 2022

Language: Английский

---

Data-driven interpretable ensemble learning methods for the prediction of wind turbine power incorporating SHAP analysis

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 237, P. 121464 - 121464

Published: Sept. 7, 2023

Language: Английский

---

A short-term power prediction method based on numerical weather prediction correction and the fusion of adaptive spatiotemporal graph feature information for wind farm cluster

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 274, P. 126979 - 126979

Published: Feb. 21, 2025

Language: Английский

---

Prediction of Photovoltaic Power by the Informer Model Based on Convolutional Neural Network

Sustainability, Journal Year: 2022, Volume and Issue: 14(20), P. 13022 - 13022

Published: Oct. 12, 2022

Accurate prediction of photovoltaic power is great significance to the safe operation grids. In order improve accuracy, a similar day clustering convolutional neural network (CNN)–informer model was proposed predict power. Based on correlation analysis, it determined that global horizontal radiation meteorological factor had greatest impact power, and dataset divided into four categories according between factors fluctuation characteristics; then, CNN used extract feature information trends different subsets, features output by were fused input informer model. The establish temporal relationship historical data, final generation result obtained. experimental results show CNN–informer method has high accuracy stability in outperforms other deep learning methods.

Language: Английский

---

SCADA system dataset exploration and machine learning based forecast for wind turbines

Results in Engineering, Journal Year: 2022, Volume and Issue: 16, P. 100640 - 100640

Published: Sept. 13, 2022

Language: Английский

---

A Novel Bio-Inspired Optimization Algorithm Design for Wind Power Engineering Applications Time-Series Forecasting

Biomimetics, Journal Year: 2023, Volume and Issue: 8(3), P. 321 - 321

Published: July 20, 2023

Wind patterns can change due to climate change, causing more storms, hurricanes, and quiet spells. These changes dramatically affect wind power system performance predictability. Researchers practitioners are creating advanced forecasting algorithms that combine parameters data sources. Advanced numerical weather prediction models, machine learning techniques, real-time meteorological sensor satellite used. This paper proposes a Recurrent Neural Network (RNN) model incorporating Dynamic Fitness Al-Biruni Earth Radius (DFBER) algorithm predict patterns. The of this is compared with several other popular including BER, Jaya Algorithm (JAYA), Fire Hawk Optimizer (FHO), Whale Optimization (WOA), Grey Wolf (GWO), Particle Swarm (PSO)-based models. evaluation done using various metrics such as relative root mean squared error (RRMSE), Nash Sutcliffe Efficiency (NSE), absolute (MAE), bias (MBE), Pearson’s correlation coefficient (r), determination (R2), agreement (WI). According the analysis presented in study, proposed RNN-DFBER-based outperforms models considered. suggests RNN model, combined DFBER algorithm, predicts effectively than alternative To support findings, visualizations provided demonstrate effectiveness RNN-DFBER model. Additionally, statistical analyses, ANOVA test Wilcoxon Signed-Rank test, conducted assess significance reliability results.

Language: Английский

---

A Review for Green Energy Machine Learning and AI Services

Energies, Journal Year: 2023, Volume and Issue: 16(15), P. 5718 - 5718

Published: July 31, 2023

There is a growing demand for Green AI (Artificial Intelligence) technologies in the market and society, as it emerges promising technology. are used to create sustainable solutions reduce environmental impact of AI. This paper focuses on describing services challenges associated with at community level. article also highlights accuracy levels machine learning algorithms various time periods. The process choosing appropriate input parameters weather, locations, complexity outlined this examine ML algorithms. For correcting algorithm performance parameters, metrics like RMSE (root mean square error), MSE (mean MAE absolute MPE percentage error) considered. Considering results review, LSTM (long short-term memory) performed well most cases. concludes that highly advanced techniques have dramatically improved forecasting accuracy. Finally, some guidelines added further studies, needs, challenges. However, there still need more challenges, mainly area electricity storage.

Language: Английский

---

Renewable energy sources integration via machine learning modelling: A systematic literature review

Heliyon, Journal Year: 2024, Volume and Issue: 10(4), P. e26088 - e26088

Published: Feb. 1, 2024

The use of renewable energy sources (RESs) at the distribution level has become increasingly appealing in terms costs and technology, expecting a massive diffusion near future placing several challenges to power grid. Since RESs depend on stochastic —solar radiation, temperature wind speed, among others— they introduce high uncertainty grid, leading imbalance deteriorating network stability. In this scenario, managing forecasting RES is vital successfully integrate them into grids. Traditionally, physical- statistical-based models have been used predict outputs. Nevertheless, former are computationally expensive since rely solving complex mathematical atmospheric dynamics, whereas latter usually consider linear models, preventing from addressing challenging scenarios. recent years, advances machine learning techniques, which can learn historical data, allowing analysis large-scale datasets either under non-uniform characteristics or noisy provided researchers with powerful data-driven tools that outperform traditional methods. paper, systematic literature review conducted identify most widely learning-based approaches forecast results show deep artificial neural networks, especially long-short term memory accurately model autoregressive nature output, ensemble strategies, allow handling large amounts highly fluctuating best suited ones. addition, promising integrating forecasted output decision-making problems, such as unit commitment, address economic, operational managerial grid discussed, solid directions for research provided.

Language: Английский

---

Enhancing wind power prediction with self-attentive variational autoencoders: A comparative study

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102504 - 102504

Published: July 14, 2024

Accurate wind power prediction is critical for efficient grid management and the integration of renewable energy sources into grid. This study presents an effective deep-learning approach that improves short-term forecasting accuracy. The method incorporates a Variational Autoencoder (VAE) with self-attention mechanism applied in both encoder decoder. empowers model to leverage VAE's strengths time-series modeling nonlinear approximation while focusing on most relevant features within data. effectiveness this evaluated through comprehensive comparison eight established deep learning methods, including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Bidirectional LSTMs (BiLSTMs), Convolutional (ConvLSTMs), Gated Units (GRUs), Stacked Autoencoders (SAEs), Restricted Boltzmann Machines (RBMs), vanilla VAEs. Real-world data from five turbines France Turkey used evaluation. Five statistical metrics are employed quantitatively assess performance each method. results indicate SA-VAE consistently outperformed other models, achieving highest average R2 value 0.992, demonstrating its superior predictive capability compared existing techniques.

Language: Английский

---

Wind Power Prediction Based on Machine Learning and Deep Learning Models

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2022, Volume and Issue: 74(1), P. 715 - 732

Published: Sept. 22, 2022

Wind power is one of the sustainable ways to generate renewable energy. In recent years, some countries have set renewables meet future energy needs, with primary goal reducing emissions and promoting growth, primarily use wind solar power. To achieve prediction generation, several deep machine learning models are constructed in this article as base models. These regression Deep neural network (DNN), k-nearest neighbor (KNN) regressor, long short-term memory (LSTM), averaging model, random forest (RF) bagging gradient boosting (GB) regressor. addition, data cleaning preprocessing were performed data. The dataset used study includes 4 features 50530 instances. accurately predict values, we propose paper a new optimization technique based on stochastic fractal search particle swarm (SFS-PSO) optimize parameters LSTM network. Five evaluation criteria utilized estimate efficiency models, namely, mean absolute error (MAE), Nash Sutcliffe Efficiency (NSE), square (MSE), coefficient determination (R2), root squared (RMSE). experimental results illustrated that proposed using SFS-PSO model achieved best R2 equals 99.99% predicting values.

Language: Английский

---