Wind Speed Time Series Research Articles

Data-driven surrogate model for wind turbine damage equivalent load

Abstract. Aeroelastic simulations are employed to assess wind turbines in accordance with IEC standards in the time domain. These analyses enable the evaluation of fatigue and extreme loads experienced by wind turbine components. Such simulations are essential for several reasons, including but not limited to reducing safety margins in wind turbine component design by accounting for a wide range of uncertainties in wind and wave conditions and fulfilling the requirements of the digital twin, which necessitates a comprehensive set of simulations for calibration. Thus, it is essential to develop computationally efficient yet accurate models that can replace costly aeroelastic simulations and data processing. To address this challenge, we propose a data-driven approach to construct surrogate models for the damage equivalent load (DEL) based on aeroelastic simulation outputs. Our method provides a quick and efficient way to calculate DEL using wind input signals without the need for time-consuming aeroelastic simulations. Our study focuses on utilizing a sequential machine learning (ML) method to map wind speed time series to DEL. Additionally, we demonstrate the versatility of the developed and trained surrogate models by testing them on a wind turbine in the wake and applying transfer learning to enhance their predictive accuracy.

Hybrid wind speed optimization forecasting system based on linear and nonlinear deep neural network structure and data preprocessing fusion

Wind speed time series forecasting has been widely used in wind power generation. However, the nonlinear and non-stationary characteristics of wind speed make accurate wind speed forecasting a difficult task. In recent years, the rapid development of artificial intelligence and machine learning technology provides a new solution to the problem of wind speed forecasting. Combining the advance of artificial intelligence and data analysis strategy, this paper proposes a wind speed forecasting system based on multi-model fusion and integrated learning. Considering the differences in data observation and training principles of various algorithms and exploiting the advantages of each model, a wind speed forecasting system with multiple machine learning algorithms embedded in integrated learning is constructed, which includes three modules: data preprocessing, optimization and forecasting. The data preprocessing module can conduct quantitative analysis through input data decomposition and feature extraction, and the combination of multi-objective intelligent optimization algorithm and combined forecasting method can effectively forecast the wind speed time series. The validity of the algorithm is verified using the data of Shandong wind farm in China. The forecasting results show that compared with the traditional single model forecasting, the proposed integrated wind speed forecasting system based on the fusion of multiple models has higher forecasting accuracy.

Wind turbine foundation ring fatigue reliability analysis under wind-load using SCADA system

Under the action of wind load, the foundation ring of the fan will generate stress concentration and alternating stress, leading to fatigue failure. Based on the average wind speed obtained from the supervisory control and data acquisition (SCADA) system, the orthogonal expansion method of random pulsating wind field and the number theory point selection method are used to calculate and simulate the corresponding pulsating wind speed time series, and then calculate the wind speed time series and wind load time series. Based on the ABAQUS finite element software, a model of a 5 MW wind turbine is established. The modal analysis is used to obtain the modal vibration pattern and the intrinsic frequency to verify the reasonableness of the structural modeling. Subsequently, the wind load time series is applied to the wind turbine model to obtain the stress time series using instantaneous modal dynamic analysis (Modal dynamics). The stress time series at the location of maximum stress concentration in the foundation ring is extracted, and the stress time series with the same stress amplitude is obtained through conversion, which has Wiener characteristics. After obtaining the stress amplitude using the rainflow counting method, the fatigue reliability is calculated based on the structural fatigue reliability analysis method considering the threshold crossing duration of the random process. This research holds reference significance for the calculation of fatigue reliability under approximate working conditions.

DMPR: A novel wind speed forecasting model based on optimized decomposition, multi-objective feature selection, and patch-based RNN

As the global demand for sustainable energy continues to grow, accurate wind speed prediction becomes crucial for optimizing the allocation of wind energy resources and enhancing the efficiency of wind power generation. This paper presents a composite prediction model that integrates Optimized Decomposition, Multi-Objective Feature Selection (MOFS), Patch-Based Recurrent Neural Networks (RNNs), and Cross-Attention Mechanisms. Initially, the wind speed time series is decomposed using RIME-optimized Variational Mode Decomposition (VMD), and sample entropy of each component is calculated to reconstruct high, medium, and low-frequency components. Subsequently, these components are patched to serve as inputs to the RNN layers. The third step involves the incorporation of exogenous variables, where MOFS is employed for feature selection, followed by a decomposition and reconstruction through RIME-optimized VMD. This process applies Variate-wise Cross-Attention Mechanism on the high, medium, and low-frequency components of both endogenous and exogenous variables. Finally, the outputs from all processing steps are integrated through a normalization layer and a feed-forward layer to produce the final prediction results. Experimental results demonstrate that our proposed model, through meticulous preprocessing and advanced architectural design, significantly improves the accuracy of wind speed predictions.

Joint Analysis of Solar Radiation and Wind Speed: Approach With Sliding Windows

Objective: This paper aims to characterise the daily fluctuations of the wind speed and solar radiation time series of some cities in the State of Bahia, Brazil, from January 2009 to December 2018, using the sliding window approach. Theoretical Framework: Due to its complexity and importance for life on planet Earth, climate change and its socio-environmental impacts are subject to studies by the scientific community and governmental and non-governmental institutions. Wind speed and solar radiation are among the elements that are relevant to climate change. Method: The DCCA Cross-Correlation Coefficient (ρDCCA) was applied to meet the objective. Five cities in Bahia, with different biomes, were selected for the modelling. Results and Discussion: The descriptive one with sliding windows identified a predominance of greater relative variation around the mean in the solar radiation time series and divergent signs in the asymmetry of wind speed and solar radiation. It was found in the cross-correlation estimation, via ρDCCA, positive and negative correlations varying according to the city, the size of the window (w) and the evaluated temporal scale (n). Conclusion: From the results and chosen methodology, one more proposal to jointly and dynamically characterise the climatic variables wind speed and solar radiation fluctuations is presented.

CEEMDAN-RIME–Bidirectional Long Short-Term Memory Short-Term Wind Speed Prediction for Wind Farms Incorporating Multi-Head Self-Attention Mechanism

Accurate wind speed prediction is extremely critical to the stable operation of power systems. To enhance the prediction accuracy, we propose a new approach that integrates bidirectional long short-term memory (BiLSTM) with fully adaptive noise ensemble empirical modal decomposition (CEEMDAN), the RIME optimization algorithm (RIME), and a multi-head self-attention mechanism (MHSA). First, the historical data of wind farms are decomposed via CEEMDAN to extract the change patterns and features on different time scales, and different subsequences are obtained. Then, the parameters of the BiLSTM model are optimized using the frost ice optimization algorithm, and each subsequence is input into the neural network model containing the MHSA for prediction. Finally, the predicted values of each component are weighted and reconstructed to obtain the predicted values of wind speed time series. According to the experimental results, the method can predict the short-term wind speeds of wind farms more accurately. We verified the effectiveness of the method by comparing it with different models.

Practical method for evaluating wind influence on autonomous ship operations (2nd report)

AbstractRecently, a considerable number of research and development projects have focused on automatic vessels. A highly realistic simulator is needed to validate control algorithms for autonomous vessels. For instance, when considering the automatic berthing/unberthing of a vessel, the effect of wind in such low-speed operations cannot be ignored because of the low rudder performance during slow harbor maneuvers. Therefore, a simulator used to validate an automatic berthing/unberthing control algorithm should be able to reproduce the time histories of wind speed and wind direction realistically. Therefore, in our first report on this topic, to obtain the wind speed distribution, we proposed a simple algorithm to generate the time series and distribution of wind speed only from the mean wind speed. However, for wind direction, the spectral distribution could not be determined based on our literature surveys, and hence, a simple method for estimating the coefficients of the stochastic differential equation (SDE) could not be proposed. In this study, we propose a new methodology for generating the time history of wind direction based on the results of Kuwajima et al.’s work. They proposed a regression equation of the standard deviation of wind direction variation for the mean wind speed. In this study, we assumed that the wind direction distribution can be represented by a linear filter as in our previous paper, and its coefficients are derived from Kuwajima’s proposed equation. Then, as in the previous report, the time series of wind speed and wind direction can be calculated easily by analytically solving the one-dimensional SDE. The joint probability density functions of wind speed and wind direction obtained by computing them independently agree well with the measurement results.

Classification and identification of extreme wind events by CNNs based on Shapelets and improved GASF-GADF

In this manuscript, we propose an automatic classification and recognition method for extreme wind events based on Convolutional Neural Networks (CNNs) and combining the Shapelet Transform (ST) algorithm with the improved Gramian Angular Summation Field - Gramian Angular Difference Field (GASF-GADF) 2D images construction format. First, a CNN model suitable for wind speed time series 2D images classification and recognition among five mainstream CNNs (ResNet-50, ShuffleNet0.5 × , DenseNet-121, EfficientNet-B2, and EfficientNetV2-S) is preferred based on the basic Gramian Angular Field (GAF) method; then, the improved GASF-GADF images construction format is proposed, and the optimal CNN is used to compare the classification and recognition results based on other three image conversion methods: Markov Transition Field (MTF), GASF, GADF. Last, it is proposed to utilize the ST algorithm to extract the feature subsequence Shapelets of wind speed time series to further improve the classification and recognition effect on extreme wind events. The effectiveness and applicability of the proposed method were verified through three extreme wind event datasets in this paper.The results show that the combination of Shapelets and the improved GASF-GADF images transformation method proposed in this paper can effectively enhance the classification and recognition of extreme wind events by CNNs. Among them, EfficientNetV2-S combined with the method proposed in this paper achieves 99.50%, 99.50% and 97.50% recognition Accuracy for thunderstorm, gust front and typhoon, respectively. Meanwhile, it still has good robustness for extreme wind events disturbed by noise.

Short-Term Wind Speed Prediction Study Based on Variational Mode Decompositions–Sparrow Search Algorithm–Gated Recurrent Units

Improving the accuracy of short-term wind speed predictions is crucial for mitigating the impact on power systems when integrating wind power into an electricity grid. This study developed a hybrid short-term wind speed prediction method, termed VMD–SSA–GRU, by combining variational mode decomposition (VMD) with gated recurrent units (GRUs) and optimizing it using a sparrow search algorithm (SSA). Initially, VMD was used to decompose the wind speed time series into subtime series. After reconstructing these subtime series, a GRU model was employed to establish separate prediction models for each series. Furthermore, an enhanced SSA was proposed to optimize the hyperparameters of the GRU model, which improved the prediction accuracy. Ultimately, the sub-series predictions were aggregated to produce the final wind speed prediction values. The predictive accuracy of this model was validated using the wind speed data measured at a meteorological station near a bridge site. The performance of the VMD–SSA–GRU model was compared with several other hybrid models, including those using wavelet transform, long short-term memory, and other neural networks. Comparably, the RMSE value of the VMD-SSA-GRU model was lower by 25.3%, 60.2%, and 61.7% in comparison to the VMD–SSA–LSTM, VMD–GRU, and VMD–LSTM models, respectively. The experimental results demonstrated that the proposed method achieved higher prediction accuracy than traditional methods.

Wind Speed Forecasting Based on Phase Space Reconstruction and a Novel Optimization Algorithm

The wind power generation capacity is increasing rapidly every year. There needs to be a corresponding development in the management of wind power. Accurate wind speed forecasting is essential for a wind power management system. However, it is not easy to forecast wind speed precisely since wind speed time series data are usually nonlinear and fluctuant. This paper proposes a novel combined wind speed forecasting model that based on PSR (phase space reconstruction), NNCT (no negative constraint theory) and a novel GPSOGA (a hybrid optimization algorithm that combines global elite opposition-based learning strategy, particle swarm optimization and the genetic algorithm) optimization algorithm. SSA (singular spectrum analysis) is firstly applied to decompose the original wind speed time series into IMFs (intrinsic mode functions). Then, PSR is employed to reconstruct the intrinsic mode functions into input and output vectors of the forecasting model. A combined forecasting model is proposed that contains a CBP (cascade back propagation network), RNN (recurrent neural network), GRU (gated recurrent unit), and CNNRNN (convolutional neural network combined with recurrent neural network). The NNCT strategy is used to combine the output of the four predictors, and a new optimization algorithm is proposed to find the optimal combination parameters. In order to validate the performance of the proposed algorithm, we compare the forecasting results of the proposed algorithm with different models on four datasets. The experimental results demonstrate that the forecasting performance of the proposed algorithm is better than other comparison models in terms of different indicators. The DM (Diebold–Mariano) test, Akaike’s information criterion and the Nash–Sutcliffe efficiency coefficient confirm that the proposed algorithm outperforms the comparison models.

Interpretable extreme wind speed prediction with concept bottleneck models

Concept-bottleneck models (CBMs) are a new paradigm to construct interpretable classifiers. The CBM architecture can be regarded as a neural network with a single hidden layer whose neurons are replaced by binary classifiers. Each of these binary classifiers implements a concept, that is, it attempts to answer a meaningful yes/no question: the presence or absence of a concept in the observation presented to the network. The output layer is usually implemented as a linear stage that combines the concepts into final decisions. This paper presents an application of the CBM paradigm to a problem of Extreme Wind Speed prediction, such that the forecasting properties of the system can be interpreted in terms of different concepts considered for this problem. A significant contribution of this paper is the proposal of an automated concept generation method, with controlled sparsity, in which the concepts are automatically extracted from the branches of decision trees fitted with informative features that capture the dynamics of the wind speed time series. The final forecasting system is able to predict extreme wind speed values in wind farms with good accuracy and interpretable results, as experiments over real wind speed data from a wind farm in Spain show.

Long, short, and mediumterms wind speed prediction model based on LSTM optimized by improved moth flame optimization algorithm.

Time series prediction of wind speed has been widely used in wind power generation. The volatility and instability of wind speed have a large negative impact on wind turbines and power systems, which can lead to grid collapse in severe cases. Therefore, accurate wind speed prediction is crucial for wind power generation. In this paper, considering the influence of different parameters on algorithm training and prediction, an improved moth flame optimization algorithm is constructed to optimize the LSTM wind energy prediction system to obtain better performance. The system consists of three modules: data preprocessing, optimization, and prediction. The data preprocessing module uses fuzzy information granulation to blur the input data. On this basis, the combination of swarm intelligent optimization algorithm and prediction model can effectively predict wind speed time series. Taking the California wind farm as an example, the MAPE of the experiment in the short-term forecast is 3.15%, the MAPE of the medium-term forecast is 4.38%, and the MAPE of the long-term forecast is 18.28%. The experimental results show that the proposed model has obvious advantages over the previous model.

Clustering of Wind Speed Time Series as a Tool for Wind Farm Diagnosis

In several industrial fields, environmental and operational data are acquired with numerous purposes, potentially generating a huge quantity of data containing valuable information for management actions. This work proposes a methodology for clustering time series based on the K-medoids algorithm using a convex combination of different time series correlation metrics, the COMB distance. The multidimensional scaling procedure is used to enhance the visualization of the clustering results, and a matrix plot display is proposed as an efficient visualization tool to interpret the COMB distance components. This is a general-purpose methodology that is intended to ease time series interpretation; however, due to the relevance of the field, this study explores the clustering of time series judiciously collected from data of a wind farm located on a complex terrain. Using the COMB distance for wind speed time bands, clustering exposes operational similarities and dissimilarities among neighboring turbines which are influenced by the turbines’ relative positions and terrain features and regarding the direction of oncoming wind. In a significant number of cases, clustering does not coincide with the natural geographic grouping of the turbines. A novel representation of the contributing distances—the COMB distance matrix plot—provides a quick way to compare pairs of time bands (turbines) regarding various features.

Prediction of hourly wind speed time series at unsampled locations using machine learning

Various models for wind speed mapping have been developed, with increasing attention on models focusing on mapping wind speed distribution. This study extends these models to predict hourly wind speed time series at unsampled locations. A model based on the quantile mapping (QM) procedure was compared to a traditional and machine-learning model to interpolate wind speed spatially. These proposed models were also used with inputs from the ERA5 reanalysis dataset, enabling them to consider local variation in orography and large-scale wind fields. A widely used procedure for mean bias correction of reanalysis based on the Global Wind Atlas (GWA) was implemented and compared to the proposed models. It was found that the QM and machine learning model, both using input from ERA5, significantly outperformed GWA bias correction in terms of time series correlation and probability distribution. Despite being more computationally intensive than GWA bias correction, both models are recommended due to their significantly (in a statistical sense) superior performance.

Synthetic wind speed time series generation by dynamic factor model

The global transition to renewable energy is driven by the fight against climate change. Wind power plays a crucial role in reducing dependence on fossil fuels and greenhouse gas emissions. Therefore, addressing uncertainties in wind speed variations requires innovative solutions. This study proposes a Bayesian-based approach using a Dynamic Factor Model to generate synthetic monthly average wind speed series. The Dynamic Factor Model framework captures temporal and spatial correlations, improving wind resource representation in operational planning models. The model's autoregressive configuration with common factors, prior distributions, and Bayesian inference techniques enhances predictive capabilities. Validation exercises confirm the model's reliability, accurately capturing seasonal oscillations and spatial correlations across eight wind farms. The study highlights the usefulness of the Dynamic Factor Model in evaluating wind projects and optimizing energy generation strategies, effectively mitigating wind uncertainty, and facilitating renewable energy integration in Brazil's power mix.

Optimized extreme learning machine using genetic algorithm for short-term wind power prediction

Through the much defiance facing energy today, it has become necessary to rely on wind energy as a source of unlimited renewable energies. However, energy planning and regulation require wind capacity forecasting, because oscillations of wind speed drastically affect directly power generation. Therefore, several scenarios must be provided to allow for estimating uncertainties. To deal with this problem, this paper exploits the major advantages of the regularized extreme learning machine algorithm (R-ELM) and thus proposes a model for predicting the wind energy generated for the next hour based on the time series of wind speed. The R-ELM is combined with the genetic algorithm which is designed to optimize the most important hyperparameter which is the number of hidden neurons. Thus, the proposed model aims to forecast the average wind power per hour based on the wind speed of the previous hours. The results obtained showed that the proposed method is much better than those reported in the literature concerning the precision of the prediction and the time convergence.

Improving short-term offshore wind speed forecast accuracy using a VMD-PE-FCGRU hybrid model

The integration of large-scale offshore wind power into the power grid presents significant challenges for grid operation and dispatch due to the variability and intermittency of offshore wind energy. However, non-stationarities and noise in wind speed time series pose challenges. This study proposes a VMD-PE-FCGRU methodology to address this challenge of predicting offshore wind speeds. Firstly, the Variational Mode Decomposition (VMD) algorithm decomposes the original wind speed signal, considering the strong fluctuations and high noise inherent to offshore wind energy. A corresponding performance evaluation index is established to assess the effectiveness of this deconstruction process. To further enhance the model's (GRU) ability to capture time series information, a Position Encoding layer (PE) has been added, and the network is deepened through a Fully Connected Neural Network (FCNN). This allows multi-dimensional time series features to be input into the Gated Recurrent Unit (GRU) network for forecast. The accuracy of the proposed method is then verified using measured historical data from the wind tower of an offshore wind farm in Guangdong. Experimental results demonstrate that the proposed method can accurately forecast short-term wind speeds for offshore wind farms, with a Mean Absolute Error (MAE) of 0.199 and a Mean Absolute Percentage Error (MAPE) of only 2.45%. Moreover, the qualified rate (r) reaches 100%, providing an accurate reference for real-time power grid dispatching and can inform decision-making for the integration of offshore wind power into the grid.

Wind speed prediction using LSTM and ARIMA time series analysis models: A case study of Gelibolu

Wind energy stands out as a prominent renewable energy source, characterized by its high efficiency, feasibility, and wide applicability. Nonetheless, the integration of wind energy into the electrical system encounters significant obstacles due to the unpredictability and variability of wind speed. Accurate wind speed prediction is essential for estimating the short-, medium-, and long-term power output of wind turbines. Various methodologies and models exist for wind speed time series prediction. This research paper proposes a combination of two approaches to enhance forecasting accuracy: deep learning, particularly Long Short-Term Memory (LSTM), and the Autoregressive Integrated Moving Average (ARIMA) model. LSTM, by retaining patterns over longer periods, improves prediction rates. Meanwhile, the ARIMA model enhances the likelihood of staying within predefined boundaries. The study utilizes daily average wind speed data from the Gelibolu district of Çanakkale province spanning 2014 to 2021. Evaluation using the root mean square error (RMSE) shows the superior forecast accuracy of the LSTM model compared to ARIMA. The LSTM model achieved an RMSE of 6.3% and a mean absolute error of 16.67%. These results indicate the potential utility of the proposed approach in wind speed forecasting, offering performance comparable to or exceeding other studies in the literature.

Selection of best wavelet functions and decomposition levels for coupling with soft computing methods in estimating ETo in coastal and island regions

ABSTRACT Mass transfer-based models are among the extensively applied reference evapotranspiration (ET o ) estimation approaches that have been proven to provide reliable estimates under certain climatic and geographical conditions. A major issue with such approaches is the high variations in wind speed time series, which is a governing meteorological parameter in mass transfer-based models. few studies have focused on applying wavelet transform as a robust pre-processing technique for ETo estimation. A major question with coupling wavelet transforms with soft computing methods would be the proper choice of the wavelet function, vanishing moments and the decomposition levels. The present study aims at assessing different wavelet functions coupled with boosted regression tree (BT) models, i.e. wavelet-BT (WBT), in estimating ET o values (through mass transfer parameters) in both coastal and island regions, where it is supposed that wind speed variations are affected by sea–inland interactions and so has the sharp variations (unlike ET o ). The obtained results showed that the coupled WBT model could improve the single BT model results to a great extent, and meanwhile, the Daubechies wavelet function with six vanishing moments provided the most accurate results in all the locations. Further, the best simulation outcomes with each wavelet function were obtained when the maximum possible decomposition level was used with each function.

Point and interval wind speed forecasting of multivariate time series based on dual-layer LSTM

Accurate prediction of wind speed is significant importance in various applications such as renewable energy management, weather prediction, and aviation safety. However, more papers only focus on the time series of wind speed, ignoring the impact of other factors on wind speed, which will reduce the effectiveness of wind speed prediction. Therefore, an innovative methodology is suggested for both point and interval forecasts of multivariate wind speed time series using a Dual-layer Long Short-Term Memory (NVDL) in this paper. The proposed multivariate forecasting model takes into account the dependencies and correlations among different variables, which are essential for capturing the complex dynamics of wind speed variations. The first layer of the Dual-layer LSTM is responsible for capturing the temporal dependencies within each variable individually, while the second layer captures the interdependencies among the variables. By incorporating this dual-layer architecture, our model effectively captures the complex spatiotemporal patterns present for multivariate wind speed information. The results obtained from both interval and point prediction demonstrate that the proposed methodology outperforms all comparative models in the precision and stability of wind speed forecasting. Therefore, the proposed forecasting methodology, characterized by minimal prediction errors and exceptional generalization ability, can be a reliable tool for smart grid programming.