Wind Speed Prediction Research Articles

Prediction for Coastal Wind Speed Based on Improved Variational Mode Decomposition and Recurrent Neural Network

Accurate and comprehensive wind speed forecasting is crucial for improving efficiency in offshore wind power operation systems in coastal regions. However, raw wind speed data often suffer from noise and missing values, which can undermine the prediction performance. This study proposes a systematic framework, termed VMD-RUN-Seq2Seq-Attention, for noise reduction, outlier detection, and wind speed prediction by integrating Variational Mode Decomposition (VMD), the Runge–Kutta optimization algorithm (RUN), and a Sequence-to-Sequence model with an Attention mechanism (Seq2Seq-Attention). Using wind speed data from the Shidao, Xiaomaidao, and Lianyungang stations as case studies, a fitness function based on the Pearson correlation coefficient was developed to optimize the VMD mode count and penalty factor. A comparative analysis of different Intrinsic Mode Function (IMF) selection ratios revealed that selecting a 50% IMF ratio effectively retains the intrinsic information of the raw data while minimizing noise. For outlier detection, statistical methods were employed, followed by a comparative evaluation of three models—LSTM, LSTM-KAN, and Seq2Seq-Attention—for multi-step wind speed forecasting over horizons ranging from 1 to 12 h. The results consistently showed that the Seq2Seq-Attention model achieved superior predictive accuracy across all forecast horizons, with the correlation coefficient of its prediction results greater than 0.9 in all cases. The proposed VMD-RUN-Seq2Seq-Attention framework outperformed other methods in the denoising, data cleansing, and reconstruction of the original wind speed dataset, with a maximum improvement of 21% in accuracy, producing highly accurate and reliable results. This approach offers a robust methodology for improving data quality and enhancing wind speed forecasting accuracy in coastal environments.

Evaluating the Accuracy of the ERA5 Model in Predicting Wind Speeds Across Coastal and Offshore Regions

Evaluating the Accuracy of the ERA5 Model in Predicting Wind Speeds Across Coastal and Offshore Regions

A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.

This study introduces a high-resolution wind nowcasting model designed for aviation applications at Madeira International Airport, a location known for its complex wind patterns. By using data from a network of six meteorological stations and deep learning techniques, the produced model is capable of predicting wind speed and direction up to 30-minute ahead with 1-minute temporal resolution. The optimized architecture demonstrated robust predictive performance across all forecast horizons. For the most challenging task, the 30-minute ahead forecasts, the model achieved a wind speed Mean Absolute Error (MAE) of 0.78 m/s and a wind direction MAE of 33.06°. Furthermore, the use of Gaussian noise concatenation to both input and label training data yielded the most consistent results. A case study further validated the model's efficacy, with MAE values below 0.43 m/s for wind speed and between 33.93° and 35.03° for wind direction across different forecast horizons. This approach shows that combining strategically deployed sensor networks with machine learning techniques offers improvements in wind nowcasting for airports in complex environments, possibly enhancing operational efficiency and safety.

A Wind Speed Forecasting Method Using Gaussian Process Regression Model Under Data Uncertainty

Abstract Wind speed forecasting plays a pivotal role in power prediction, daily operations, and optimal scheduling of wind farms. However, accurately predicting wind speed remains challenging due to data uncertainties and the inherent randomness of wind resources. This paper introduces a novel wind speed forecasting method by combining Bayesian discrete wavelet packet thresholding (BDWPT) into Gaussian Process Regression (GPR). The BDWPT method is first employed to adaptively remove noise from wind speed data, retaining the main trend characteristics of the time series while removing redundant information. The GPR model is then utilized to capture the remaining randomness and effectively predict future probabilistic trends in wind speed. Comparative studies using real-world wind farm data demonstrate the advantages of the proposed method in both one-step and multistep forecasting scenarios, showcasing its potential to enhance turbine design and power management under uncertain conditions.

MIESTC: A Multivariable Spatio-Temporal Model for Accurate Short-Term Wind Speed Forecasting

Wind speed forecasting is an essential part of weather prediction, with significant value in economics, business, and management. Utilizing multiple meteorological variables can improve prediction accuracy, but existing methods face challenges such as mixing and noise due to variable differences, as well as difficulty in capturing complex spatio-temporal dependencies. To address these issues, this study introduces a novel short-term wind speed forecasting model named as MIESTC. The proposed model employs an independent encoder to extract features from each meteorological variable, mitigating the issues of noise that are caused by variable mixing. Then, a multivariate spatio-temporal correlation module is used to capture the global spatio-temporal dependencies between variables and model their interactions. Experimental results on the ERA5-LAND dataset show that, compared to the ConvLSTM, UNET, and SimVP models, the MIESTC model reduces RMSE by 14.60%, 8.64%, and 10.41%, respectively, for a 1 h prediction duration. For a 6 h prediction duration, the corresponding reductions are 13.91%, 8.20%, and 6.95%, validating its superior performance in short-term wind speed forecasting. Furthermore, an analysis of variable impacts reveals that U10, V10, and T2M play dominant roles in wind speed prediction, while TP exhibits a relatively lower impact, aligning with the results of the correlation analysis. These findings underscore the potential of MIESTC as an effective and reliable tool for short-term wind speed prediction.

A novel hybrid deep learning model for ultra-short-term prediction of wind speed

A novel hybrid deep learning model for ultra-short-term prediction of wind speed

Uncertainty prediction of wind speed based on improved multi-strategy hybrid models

<p>Accurate interval prediction of wind speed plays a vital role in ensuring the efficiency and stability of wind power generation. Due to insufficient traditional wind speed interval prediction methods for mining nonlinear features, in this paper, a novel interval prediction method was proposed by combining improved wavelet threshold and deep learning (BiTCN-BiGRU) with the nutcracker optimization algorithm (NOA). First, NOA was used to optimize the wavelet transform (WT) and BiTCN-BiGRU. Second, we applied NOA-WT to smooth the wind speed data. Then, to capture nonlinear features of time series, phase space reconstruction (PSR) was utilized to identify chaotic characteristics of the processed data. Finally, the NOA-BiTCN-BiGRU model was built to perform wind speed interval prediction. Under the same hyperparameters and network structure settings, a comparison with other deep learning methods showed that the prediction interval coverage probability (PICP) and prediction interval mean width (PIMW) of NOA-WT-BiTCN-BiGRU model achieves the best balance, with good prediction accuracy and generalization performance. This research can provide reference and guidance for nonlinear time-series interval prediction in the real world.</p>

A novel spatiotemporal fusion wind speed prediction method under wind farm control center: BiTCN–transformer–cross-attention

A novel spatiotemporal fusion wind speed prediction method under wind farm control center: BiTCN–transformer–cross-attention

A multi-scale component feature learning framework based on CNN-BiGRU and online sequential regularized extreme learning machine for wind speed prediction

A multi-scale component feature learning framework based on CNN-BiGRU and online sequential regularized extreme learning machine for wind speed prediction

Challenges and potential solutions for the global optimization of "Offshore Wind Energy — Multi-Marine Resources" integration system in the Beibu Gulf of Guangxi

<p>The development of a national energy base and modern energy system in the Beibu Gulf of Guangxi requires an innovative energy system. General energy system only consists of a single marine energy resource, this work introduces an "Offshore Wind Energy—Multi-Marine Resources" integration system, which distinctively centers on offshore wind power while incorporating seawater hydrogen production, pumped storage, seawater desalination, marine aquaculture, and other marine resource utilization complexes. Its potential challenges during its future construction and potential solutions for the global optimization that need to be addressed are as follows: 1) creating a high-precision wind speed prediction model across multiple scales; 2) developing a global optimization model for the system under multiple uncertainties; and 3) proposing a resilience assessment method for systems subjected to unconventional external shocks. This integration system can contribute to the comprehensive development of marine resources and the establishment of a national comprehensive energy base in Guangxi Province and around the world.</p>

A two-stage deep learning-based hybrid model for daily wind speed forecasting.

Global adoption of wind energy continues to increase, while improving the efficiency of turbine settings requires reliable wind speed (WS) models. The latest models rely on artificial intelligence (AI) optimizations which constructs tests on a range of novel hybrid models to examine the reliability. Gradient Boosting (GB), Random Forest (RF), and Long Short-Term Memory (LSTM) are used in new combinations for data pre-processing. A Time Varying Filter-based Empirical Mode Decomposition (TVFEMD) model is coupled with the GB and LSTM standalone models, to create TVFEMD-GB and TVFEMD-LSTM hybrids, which are run in competition with each other. Eventually, a preferred hybrid form is established, simultaneous hybridization of TVFEMD with GB and LSTM. This study is the first to hybridize these fundamental systems, and create a TVFEMD-GB-LSTM model that can forecast WS. This study finds that the novel hybrid models exhibit superior performance to standalone GB and LSTM models, opening the pathway to alternative WS prediction techniques.

Wind speed forecasting one step ahead using different input vectors in a neural network

This study introduces a method for predicting wind speed in Baja California Sur, Mexico, using long-short-term memory (LSTM) neural networks applied to hourly time series data. Measurements from January 2016, provided by Mexico's Federal Electricity Commission (CFE), were analyzed to optimize the model inputs and reduce forecast errors. The data was statistically described to identify relevant patterns and then normalized to improve model training. Several LSTM network configurations were tested and compared based on error metrics. Initial models with six variables in input vectors were unsatisfactory. However, three additional models with five, three, and two inputs were developed. The model with five inputs and one output (5I, 1O) achieved the lowest error metrics: Mean Absolute Error (MAE) of 0.72, Root Mean Square Error (RMSE) of 0.923, and Normalized Root Mean Square Error (NRMSE) of 0.161, indicating the best performance among the tested models.

Wind speed prediction by utilizing geographic information system and machine learning approach: A case study of Karabük province in Türkiye

Wind speed prediction by utilizing geographic information system and machine learning approach: A case study of Karabük province in Türkiye

Deep learning framework for wind speed prediction in Saudi Arabia

Deep learning framework for wind speed prediction in Saudi Arabia

Wind speed prediction model based on multiscale temporal‐preserving embedding broad learning system

AbstractThe inherent randomness and intermittent nature of wind speed fluctuations pose significant challenges in accurately predicting future wind speeds. To address this complexity, a wind speed prediction model based on a multiscale temporal‐preserving embedding broad learning system (MTPE‐BLS) is proposed. MTPE‐BLS used the localised behaviour of wind speed data, which is simpler to model and analyse than global patterns. Firstly, frequency clustering‐based variational mode decomposition (FC‐VMD) is proposed to deal with the non‐stationary wind speed data into multiple intrinsic mode functions (IMFs). Then, temporal‐preserving embedding (TPE) is proposed to extract the underlying temporal manifold structure from the decomposed IMFs. Finally, the extracted features are mapped into the broad learning system (BLS) to establish an accurate prediction model. Experimental results on two real‐world wind speed datasets demonstrate the best performance of the proposed MTPE‐BLS model compared to that of others. Compared to the original BLS, the MTPE‐BLS achieves significant improvements, reducing the root mean square error (RMSE) and mean absolute error (MAE) by an average of 48.57% and 47.72%, respectively.

Optimizing Wind Speed Predictions in Bangladesh: Unveiling the Power of Machine Learning Approaches

Wind speed is a naturally occurring phenomenon that arises from the intricate interplay of various atmospheric processes. Wind speed prediction is pivotal in various sectors worldwide, and Bangladesh is no exception. Beyond its impact on agriculture, water management, and disaster preparedness, wind speed also plays a crucial role in urban planning and construction projects. Architects and engineers rely on accurate wind speed forecasts to design buildings and infrastructure that can withstand local wind conditions. Furthermore, the aviation and maritime industries heavily depend on wind speed predictions to ensure the safety of flights and shipping routes. Predicting wind speeds in Bangladesh poses a significant challenge due to the region's susceptibility to frequent seasonal changes influenced by its coastal location and complex, nonlinear climate patterns. To address this important aspect, we leverage Machine Learning (ML) algorithms, including Linear Discriminant Analysis (LDA), Classification and Regression Trees (CART), Random Forest (RF), K Nearest Neighbors (K-NN), and Support Vector Machine (SVM) to forecast wind speeds at various weather stations in Bangladesh. We utilized various accuracy metrics, including precision, sensitivity, specificity, F-measure, and overall accuracy, to evaluate the performances of the algorithms. The RF model outperformed the other models with an overall accuracy of 94.73% for predicting wind speed conditions in Bangladesh. On the other hand, the LDA model exhibited the lowest performance, achieving an accuracy of 93.27% in comparison to the other models. It is noticeable that the aforementioned five models showed more than 90% accuracy for windspeed prediction. Additionally, we complement our analysis with visual representations such as box plots, density plots, dot plots, parallel plots, and scatterplot matrix plots. These empirical results also highlighted the RF as the most suitable method for predicting contemporary wind speed patterns in Bangladesh. International Journal of Statistical Sciences, Vol. 24(2), November, 2024, pp 137-154

STGPT2UGAN: Spatio-Temporal GPT-2 United Generative Adversarial Network for Wind Speed Prediction in Turbine Network

In a turbine network, an accurate wind speed prediction plays a key role in improving the efficiency of turbine operations. At present, Large Language Models (LLMs) have shown their strong capabilities in time sequence forecasting. Unfortunately, the existing LLM-based models face the following two difficulties in precise wind speed prediction: (1) These models fail to capture spatio-temporal correlations. (2) These models rely exclusively on supervised learning to train. Supervised learning updates parameters by optimizing a loss function, which focuses solely on improving accuracy on a specific regression or classification task rather than understanding the true data distribution. To tackle these difficulties, we devise a novel wind speed prediction architecture entitled Spatio-Temporal GPT-2 United Generative Adversarial Network (STGPT2UGAN). In particular, in order to model spatio-temporal correlations, we first design a Spatio-Temporal GPT-2 (STGPT-2), which comprises a Spatio-Temporal Block and the variant of GPT-2. Second, to improve the training of STGPT-2, a Generative Adversarial Network (GAN) is introduced to develop an adversarial training strategy. The strategy combines unsupervised training and supervised training in a complementary fashion. The unsupervised training promotes STGPT-2 to learn the distribution of true data through minimizing the adversarial loss. The supervised training intends to align the true values and the predicted values. We conduct the experiments on one real-world wind speed dataset. The experimental results verify that STGPT2UGAN outperforms the state-of-the-art benchmarks in terms of prediction precision.

Multi-Step Wind Speed Forecasting by Secondary Decomposition Algorithm and LSTM

Enhancing the reliability of wind speed forecasting is vital for efficient wind power generation. Given the wind's stochastic nature, preprocessing is crucial to obtain a clean wind speed series. This study introduces an innovative wind speed prediction model that integrates Variational Mode Decomposition (VMD), Symplectic Geometry Mode Decomposition (SGMD), and Long Short-Term Memory (LSTM). The model begins with VMD dividing the series into low- and high-frequency parts, then the SGMD further analyzes the high-frequency segment, and LSTM predicts results based on these components. Collaborative use of VMD and SGMD enables thorough decomposition of intricate wind speed data, while LSTM boosts the model's ability to capture patterns and dependencies. This hybrid model addresses the challenges posed by wind power uncertainty, aiming to efficiently integrate wind energy into power systems. The proposed hybrid model was compared to some benchmark models and outperformed them, reducing MAPE by 58% and RMSE by 31% for Dataset 1, and improving MAPE by 14% and RMSE by 36% for Dataset 2. The results confirm the competitive strength of the proposed strategy. Furthermore, the suggested two-stage decomposition technique demonstrates suitability for the examination of nonlinear characteristics in wind speed patterns.

A comprehensive evaluation of machine learning and deep learning algorithms for wind speed and power prediction

Accurate wind speed and power predictions are crucial for renewable wind energy applications. This study compares and evaluates twelve machine learning (ML) and deep learning (DL) algorithms, including single and ensemble models across various time scales from 10 min to a day and a half ahead with a particular focus on ensemble prediction algorithms. Moreover, the study proposes a wind speed and power prediction system where the outcome of the wind speed prediction (WSP) model serves as input for the wind power prediction (WPP) model. Several evaluation metrics, such as mean absolute percentage error (MAPE) and mean square error (MSE) were calculated to benchmark different model accuracies. For WSP, the extremely randomized trees, decision tree, and bagging ensemble algorithms demonstrated high accuracy across different time scales where the MAPE ranged from 3.4% to 9.2%, the MSE ranged from 0.17 to 1.15, and the adjusted coefficient of determination ranged from 94% to 99%. For WPP, bagging ensemble algorithms and extremely randomized trees were also effective for predicting different time scales where the MAPE ranged from 4.12% to 11.7% and the MSE ranged from 10945 to 2.4. Ensemble ML algorithms provide better and more accurate results than single ML algorithms. The extreme gradient boosting model showed relatively small computational time and memory according to computational cost. Moreover, this study conducted a sensitivity analysis where air pressure, wind vane, and humidity were the key predictors for WSP and WPP.

A hybrid model based on CapSA-VMD-ResNet-GRU-attention mechanism for ultra-short-term and short-term wind speed prediction

A hybrid model based on CapSA-VMD-ResNet-GRU-attention mechanism for ultra-short-term and short-term wind speed prediction