Wind Speed Time Series Research Articles

Understanding wind turbine power converter reliability under realistic wind conditions

AbstractThe reliability of wind turbine power converters is crucial for analyzing wind energy project costs, and for estimating maintenance and downtime. The published literature in this field relies on evaluating the reliability effect of wind speed to estimate the converter lifetime. However, this paper demonstrates that wind turbulence intensity, which has not been widely considered in similar reliability analyses, shows a significant impact on converter lifetime. This paper uses 821 10‐min wind speed time series sampled at 1 Hz on the two most commonly deployed wind turbine converter topologies: the two‐level voltage source and the three‐level neutral point clamped. Electromechanical and thermal modelling, combined with statistical analysis shows that mean wind speed and turbulence intensity both impact the lifetime of both converter topologies. However, the paper estimates that the three‐level converter can operate 2.4 to 4.0 times longer than the two‐level converter depending on the operating wind speed and turbulence intensity.

Short-term wind speed forecasts through hybrid model based on improved variational mode decomposition

ABSTRACT Scientific and accurate wind predictions are the basis for exploiting and utilizing wind energy. Combining the VMD and KELM, this research proposes a new hybrid model to capture the pattern of wind speed change, the parameters of which are optimized by the Spotted Hyena Optimizer(SHO) and Seagull Optimization Algorithm(SOA), respectively. The VMD is optimized by the SHO to achieve the purpose of adaptive decomposition of historical wind speed time series. After that, the parameters of the KELM are optimized by the SOA. Then, the decomposed wind speed series is input into the optimized KELM. The output prediction Intrinsic Mode Functions(IMFs) is added up to obtain the short-term wind speed prediction results. The measured wind speeds for four seasons were selected as the case study for the proposed model. The prediction results are compared with the measured wind speed series to verify the accuracy and reliability of the model. Besides, the prediction accuracy and stability of the proposed model are better than traditional prediction models, with stronger performance and lower computational cost. The results of case studies indicate that the proposed model can satisfy the need for actual applications.

The value of wake steering wind farm flow control in US energy markets

Abstract. Wind farm flow control represents a category of control strategies for achieving wind-plant-level objectives, such as increasing wind plant power production and/or reducing structural loads, by mitigating the impact of wake interactions between wind turbines. Wake steering is a wind farm flow control technology in which specific turbines are misaligned with the wind to deflect their wakes away from downstream turbines, thus increasing overall wind plant power production. In addition to promising results from simulation studies, wake steering has been shown to successfully increase energy production through several recent field trials. However, to better understand the benefits of wind farm flow control strategies such as wake steering, the value of the additional energy to the electrical grid should be evaluated – for example, by considering the price of electricity when the additional energy is produced. In this study, we investigate the potential for wake steering to increase the value of wind plant energy production by combining model predictions of power gains using the FLOw Redirection and Induction in Steady State (FLORIS) engineering wind farm flow control tool with historical electricity price data for 15 existing US wind plants in four different electricity market regions. Specifically, for each wind plant, we use FLORIS to estimate power gains from wake steering for a time series of hourly wind speeds and wind directions spanning the years 2018–2020, obtained from the ERA5 reanalysis dataset. The modeled power gains are then correlated with hourly electricity prices for the nearest transmission node. Through this process we find that wake steering increases annual energy production (AEP) between 0.4 % and 1.7 %, depending on the wind plant, with average increases in potential annual revenue (i.e., annual revenue of production, ARP) 4 % higher than the AEP gains. For most wind plants, ARP gain was found to exceed AEP gain. But the ratio between ARP gain and AEP gain is greater for wind plants in regions with high wind penetration because electricity prices tend to be relatively higher during periods with below-rated wind plant power production, when wake losses occur and wake steering is active; for wind plants in the Southwest Power Pool – the region with the highest wind penetration analyzed (31 %) – the increase in ARP from wake steering is 11 % higher than the AEP gain. Consequently, we expect the value of wake steering, and other types of wind farm flow control, to increase as wind penetration continues to grow.

A short-term wind speed prediction method based on the BLS–RVM hybrid model

Abstract The study introduces a novel approach to short-term wind speed forecasting, which amalgamates statistical and machine learning techniques through the utilization of a hybrid model consisting of the broad learning system (BLS) and the relevance vector machine (RVM), to account for the nonstationary characteristics of wind speed data. Firstly, the initial wind speed time series is preprocessed using singular spectrum analysis to achieve noise reduction. Subsequently, the denoised wind speed time series is predicted using generalized learning system (BLS), and the prediction error is obtained. Finally, the prediction error of BLS is further predicted using RVM, and the final prediction result is obtained by combining it with the prediction results of BLS. By integrating multiple algorithms, this novel wind speed forecasting hybrid model improves prediction accuracy and can adapt to different wind speed characteristics and complex wind speed fluctuations. Through a case study, we find that this model outperforms other comparative models in terms of prediction, fully demonstrating its superiority.

Short-term wind speed prediction based on improved Hilbert–Huang transform method coupled with NAR dynamic neural network model

Wind energy, as a renewable energy source, offers the advantage of clean and pollution-free power generation. Its abundant resources have positioned wind power as the fastest-growing and most widely adopted method of electricity generation. Wind speed stands as a key characteristic when studying wind energy resources. This study primarily focuses on predictive models for wind speed in wind energy generation. The intense intermittency, randomness, and uncontrollability of wind speeds in wind power generation present challenges, leading to high development costs and posing stability challenges to power systems. Consequently, scientifically forecasting wind speed variations becomes imperative to ensure the safety of wind power equipment, maintain grid integration of wind power, and ensure the secure and stable operation of power systems. This holds significant guiding value and significance for power production scheduling institutions. Due to the complexity of wind speed, scientifically predicting its fluctuations is crucial for ensuring the safety of wind power equipment, maintaining wind power integration systems, and ensuring the secure and stable operation of power systems. This research aims to enhance the accuracy and stability of wind speed prediction, thereby reducing the costs associated with wind power generation and promoting the sustainable development of renewable energy. This paper utilizes an improved Hilbert–Huang transform (HHT) using complementary ensemble empirical mode decomposition (CEEMD) to overcome issues in the traditional empirical mode decomposition (EMD) method, such as component mode mixing and white noise interference. Such an approach not only enhances the efficiency of wind speed data processing but also better accommodates strong stochastic and nonlinear characteristics. Furthermore, by employing mathematical analytical methods to compute weights for each component, a dynamic neural network model is constructed to optimize wind speed time series modeling, aiming for a more accurate prediction of wind speed fluctuations. Finally, the optimized HHT-NAR model is applied in wind speed forecasting within the Xinjiang region, demonstrating significant improvements in reducing root mean square errors and enhancing coefficient of determination. This model not only showcases theoretical innovation but also exhibits superior performance in practical applications, providing an effective predictive tool within the field of wind energy generation.

An innovative interpretable combined learning model for wind speed forecasting

Wind energy is taken as one of the most potential green energy sources, whose accurate and stable prediction is important to improve the efficiency of wind turbines as well as to guarantee the power balance and economic dispatch of power systems and equipment safety. However, the random and fluctuating nature of wind speed poses a great risk to wind power grid connections. To address the issues of low prediction performance and lack of interpretable analysis in most past studies, this research proposes an interpretable combined learning model for wind speed time series prediction by combining linear models, different neural networks, and deep learning by introducing interpretable TFT models. To test the effectiveness of the forecasting models, the presented combined model is verified using eight wind speed datasets covering four seasons collected from two wind farms in Shaanxi, China. The experimental results show that the average root mean squared error of the one-step, two-step, and three-step predictions on the eight datasets for proposed model are 0.3448, 0.4586 and 0.6164, respectively, which are much better than the six single models and the six combined models with different strategies. And proposed model outperforms the single model and combined model in most cases, with 86.80% and 92.01% of the DM values greater than the corresponding critical values when the significance level is set to 0.01 and 0.1, respectively. Finally, the proposed model is discussed and analyzed in depth through interpretability analysis of the combined model, which further validates the potential of the model and also provides a reference for other time series forecasting studies.

Multistep Wind Speed Prediction Based on the Fractional‐Order Longicorn Swarm Algorithm and the Two‐Stage Modal Decomposition Strategy

Least squares support vector machine (LSSVM) and variational mode decomposition are common research methods for wind speed time series prediction. Addressing the challenge of selecting relevant parameters of LSSVM and VMD, a fractional‐order Beetle swarm optimization algorithm is proposed to optimize the relevant parameters. To weaken the negative impact of wind speed volatility on the accuracy of the prediction model, a two‐stage modal decomposition strategy based on extreme‐point symmetric mode decomposition, FO‐BSO algorithm, and VMD is proposed. ESMD is used to decompose the original wind speed time series. The diversity entropy is introduced as the criterion, and the FO‐BSO‐VMD secondary decomposition is applied for the high‐entropy modal components to further weaken the volatility of wind speed. Simulation results show that compared with the original LSSVM model, the ESMD‐FO‐BSO‐VMD‐LSSVM model presented in this study exhibits an average 44.10% increase in the fitting degree of wind speed prediction over three steps, which verifies the superior performance of the model in short‐term multistep wind speed prediction.

Machine Learning Techniques for Anomaly Detection in High-Frequency Time Series of Wind Speed and Greenhouse Gas Concentration Measurements

Machine Learning Techniques for Anomaly Detection in High-Frequency Time Series of Wind Speed and Greenhouse Gas Concentration Measurements

Santa Ana Winds: Multifractal Measures and Singularity Spectrum

A multifractal analysis based on the time series of temperature, pressure, relative humidity, wind speed, and wind direction was performed for 16 weather stations located in the hydrographic basin of the Guadalupe River in Baja California, Mexico. Our analysis included a 38-year dataset from MERRA-2 database, we investigated the multifractal nature of daily time series data for climatic variables associated with the Santa Ana Winds. We employed the Multifractal Detrended Fluctuation Analysis (MFDFA) method to extract multifractal complexity parameters (α0, ∆α, and r). This was adequate to evaluate the multifractality of the time series that represented the conditions of the phenomenon’s occurrence. From the estimation of the generalized Hurst exponent (hq), it was possible to characterize the time series of the meteorological variables in terms of the characteristics of persistence, anti-persistence, or randomness. Finally, the values corresponding to the parameters and characteristics of the multifractal spectrum or singularities can be used as quantitative and qualitative indicators to describe the dynamics of meteorological processes during the occurrence of the Santa Ana winds in the Guadalupe basin.

A novel hybrid algorithm based on Empirical Fourier decomposition and deep learning for wind speed forecasting

As the demand for renewable energy is increasing, wind speed forecasting (WSF) becomes increasingly popular and essential for wind power generation. Several methods have been developed in the literature for WSF. However, WSF accuracy is challenging to obtain due to its non-stationary and non-linear character. To overcome this issue, this study suggests a novel integrated forecasting model for WSF. In the majority of cases, decomposition techniques are essential for removing noise and extracting patterns from non-stationary and non-linear wind speed time series. Among these decomposition techniques, the most widely used decomposition methods based on frequency domain theory are the Fourier decomposition method (FDM), the empirical wavelet transform (EWT), and the variational mode decomposition (VMD). However, FDM decomposition gives inconsistent results, EWT has mixed problems, and VMD is unsuitable for non-stationary time series. Thus, a novel combined model based on empirical Fourier decomposition (EFD) techniques, long short-term memory (LSTM) neural networks, and the Grey Wolf optimizer (GWO) is proposed in this paper. Initially, the wind speed time series is decomposed using EFD into a set of sub-series and a residual, which is a stationary sub-series that can be easily modelled by a recurrent neural network (RNN). Further, the matching LSTM is used to forecast each sub-series and residual, while the GWO optimizes the sub-series estimated output, resulting in improved prediction precision and stability. In order to assess the model performance, five wind speed datasets from various places in India are employed. The findings show that the proposed model is the top performing model among the other ten models; The average statistical score obtained from all datasets reduces 11.01% in the mean absolute error (MAE), 10.68% in the root mean square error (RMSE) and 10.73% in the mean absolute percentage error (MAPE). Further, regularity conditions for universal consistency of proposed model is also proved mathematically.

A Novel Hybrid Deep Learning Model for Forecasting Ultra-Short-Term Time Series Wind Speeds for Wind Turbines

Accurate forecasting of ultra-short-term time series wind speeds (UTSWS) is important for improving the efficiency and safe and stable operation of wind turbines. To address this issue, this study proposes a VMD-AOA-GRU based method for UTSWS forecasting. The proposed method utilizes variational mode decomposition (VMD) to decompose the wind speed data into temporal mode components with different frequencies and effectively extract high-frequency wind speed features. The arithmetic optimization algorithm (AOA) is then employed to optimize the hyperparameters of the model of the gated recurrent unit (GRU), including the number of hidden neurons, training epochs, learning rate, learning rate decay period, and training data temporal length, thereby constructing a high-precision AOA-GRU forecasting model. The AOA-GRU forecasting model is trained and tested using different frequency temporal mode components obtained from the VMD, which achieves multi-step accurate forecasting of the UTSWS. The forecasting results of the GRU, VMD-GRU, VMD-AOA-GRU, LSTM, VMD-LSTM, PSO-ELM, VMD-PSO-ELM, PSO-BP, VMD-PSO-BP, PSO-LSSVM, VMD-PSO-LSSVM, ARIMA, and VMD-ARIMA are compared and analyzed. The calculation results show that the VMD algorithm can accurately mine the high-frequency components of the time series wind speed, which can effectively improve the forecasting accuracy of the forecasting model. In addition, optimizing the hyperparameters of the GRU model using the AOA can further improve the forecasting accuracy of the GRU model.

Probabilistic Wind Speed Forecasting for Wind Turbine Allocation in the Power Grid

To face the growing electricity demand, several countries have adopted the solution of clean energy and use renewable energy sources (e.g., wind and solar) to reinforce the stability of the power network, especially during peak demand periods. Forecasting wind power generation is one of the important tasks for the network regulator. This paper deals with the probabilistic forecasting of hourly wind speed time series. In this approach, instead of evaluating a single-point forecast, an intraday interval prediction is provided, which allows modeling the probability distribution of the wind speed process at any specific hour. Practically, the quantification of uncertainty might be of particular interest for risk management purposes associated with wind power generation. The definition of interval prediction is based on the notion of conditional quantiles. In this paper, we introduce a new statistical approach, which deals with the nonstationarity behavior of the wind speed process, to define the conditional quantile predictor. The proposed approach was applied and evaluated on hourly wind speed processes. The suggested methodology provides accurate single-point forecasts using the conditional median as the predictor. Furthermore, the obtained hourly interval predictions are small and well adapted to the shape of the daily wind speed curves, which confirms the efficiency of the proposed approach.

EPNN-based prediction of meteorological data for renewable energy systems

In this paper, an application of an Evolving Polynomial Neural Network (EPNN) for prediction of meteorological time series (global solar irradiation, air temperature, relative humidity, and wind speed) is described. Prediction of such data plays a very important role in design of the renewable energy systems. The problem of time series prediction is formulated as a system identification problem, where the input of the system is the past values (y (t - 1), y (t - 2), y (t - 3), …) of a time series and its desired output (y (t), y (t + 1), y (t + 2), …) are the future of a time series. In this study, a dataset of meteorological time series for five years collected in Algiers (Algeria) by the National Office of Meteorology has been used. The obtained results showed a good agreement between both series, measured and predicted. The correlation coefficient ( r ) is arranged between 0.9821 and 0.9923, the mean relative error over the whole data set is not exceed 15.4 %. The proposed model provides more accurate results than other ANN’s architecture, wavenet (wavelet-network) and Adaptive Neuro-Fuzzy Inference Scheme (ANFIS). In order to show the effectiveness of the proposed predictor, the predicted data have been used for sizing, and prediction of the output energy of photovoltaic systems.

Robust multi-step wind speed forecasting based on a graph-based data reconstruction deep learning method

Against global warming, wind energy has increasingly become a stable form of power supply. Accurate prediction of wind speed is crucial for turbine control and wind farm dispatch, contributing to stable and continued wind energy utilization. However, it is very difficult to accomplish satisfactory wind speed forecasting, especially multi-step forecasting, due to the stochastic, random and volatile characteristic of wind speed series with complex fluctuations. This study is elaborated to propose a novel method based on “data graph” reconstruction and long short term memory (LSTM) network, to achieve accurate and robust multi-step wind speed forecasting. To obtain implicit correlations between wind speed series, the time series data are reconstructed into matrices like “data graphs”. To achieve better computing efficiency and forecasting accuracy, the convolutional neural network (CNN) is adopted to extract the features in the “data graphs”. Then the extracted data graph features are imported into the bidirectional-LSTM (bi-LSTM) network module, which takes the input in forward and backward directions, respectively, to extract more temporal information. For adequate performance assessment, experiments are carried out on data sets of an actual wind farm located in a mountainous region in China. The results show that the proposed method outperforms classic meta-model based and hybrid-model based methods in accuracy, stability and computing efficiency. The results reveal that the data graph reconstruction combined with the CNN is able to extract the hidden features of the wind speed time series data. The proposed CNN-bi-LSTM method effectively improve the multi-step wind speed prediction accuracy.

Storage requirements to mitigate intermittent renewable energy sources: analysis for the US Northeast

Moving away from fossil fuels is essential for a sustainable future. Carrying out this transition without reversing the improvements in the quality of life is the ultimate challenge. While minimizing the anticipated impacts of climate change is the primary driver of decarbonization, the inevitable exhaustion of fossil energy sources should provide just as strong or perhaps even stronger incentives. The vast majority of publications outlining the pathways to “net-zero carbon emission” fall short from leading to a truly “fossil fuel-free” future without falling back to some level of dependence on fossil fuels with carbon capture and sequestration. While carbon capture and sequestration might be a necessary step toward decarbonization, such intermediate goals might turn into a dead end without defining the end point. The main obstacle to wider adoption of renewable energy resources is their inherent intermittency. Solar and wind are, by far, the most abundant renewable energy sources that are expected to take the lion share in transitioning to a sustainable future. Intermittency arises at multiple levels. The most recognized are the short-term (minute-by-minute, hourly, or diurnal) variations that should be the easiest to address. Less frequently realized are the seasonal and inter-annual variabilities. Seasonality poses far greater challenges than minute-by-minute or hourly variations because they lead to the absence of energy resources for prolonged periods of time. Our interest is the feasibility of a future where all energy (100%) comes from renewable sources leaving no room for fossil fuels. We carry out rudimentary statistical analyses of solar radiation and wind speed time series records to quantify the degree of their intermittencies seasonally and inter-annually. We employ a simple but robust accounting of the shortfalls when the supplies do not meet demand via a modified cumulative supply/deficit analysis that incorporates energy losses arising from transporting excess energy to storage and retrieving it as needed. The presented analysis provides guidance for choosing between the installation of excess capacity or the deployment of energy storage to guarantee reliable energy services under the assumption that the energy system is powered exclusively by renewable energy sources. This paper examines the seasonal and inter-annual variability of hydropower and biofuel resources to estimate their potential to mitigate the intermittencies of solar and wind resources. The presented analyses are meant to provide crude, bulk part estimates and are not intended for planning or operational purposes of the actual energy infrastructures. The primary focus of this paper is the Northeast region of the United States using the conterminous United States as a reference to assess the viability of reducing the energy storage need in the study region via improved connectivity to the national grid. This paper builds on the modeling exercises carried out as part of the climate-induced extremes on food, energy, water systems studies.

Investigation on the coordinated operation control technology of distributed new energy grid connection using artificial intelligence algorithms

New energy power generation has strong randomness and volatility. Especially in the case of a high proportion of NE (network security) power generation, its sudden random power generation in a short period of time will seriously affect the stable operation of the power grid. Therefore, this paper proposes BP neural network algorithm to study the distributed NE grid-connected cooperative operation control technology. First of all, this paper studies the artificial intelligence algorithm in detail and applies it to the coordinated operation control of distributed NE grid-connected; then, based on the status quo of renewable energy PG (power generation), this paper establishes a suitable wind speed time series model, and thus proposes an optimization model based on a rolling scheduling optimization algorithm. The experimental results show that the average running time of the rolling scheduling optimization algorithm is maintained at about 0.2 s, which can effectively realize online operation. In addition, through rolling adjustment, the error between the total output curve of the unit and the actual total output curve of the unit can be significantly reduced. The research shows that the rolling scheduling optimization algorithm has a good optimization effect, can promote the coordinated development of wind farms and power systems, and increase the capacity of power systems.

WindFix: Harnessing the power of self-supervised learning for versatile imputation of offshore wind speed time series

The accurate prediction of offshore wind speed is crucial for effective wind energy management. Deep learning models, which utilize large-scale wind speed time series, have emerged as a prominent approach for this task. However, the availability of wind history and other oceanic data is often capriciously incomplete, with intermittent gaps in the time series due to transmission difficulties or measurement device malfunctions. This presents a significant challenge for both data preparation and model training. In this paper, a self-supervised framework, WindFix, is proposed for continuous missing-value imputation of offshore wind time series using meteorological features from both the self-spot and neighboring spots. This cutting-edge innovation integrates multiple masking techniques with enhanced transformer models, resulting in a highly efficient and versatile process that adapts seamlessly to various scenarios. The numerical results validated on wind dataset from Pacific Ocean show that the model can serve for different missing types with a mean squared error around 0.002 for the simplest case. The comprehensive analysis also provided in-depth explanations on the different patterns observed in various imputation types, attributing these to the allocation of attention weights on features.

Downscaling ERA5 wind speed data: a machine learning approach considering topographic influences

Energy system modeling and analysis can provide comprehensive guidelines to integrate renewable energy sources into the energy system. Modeling renewable energy potential, such as wind energy, typically involves the use of wind speed time series in the modeling process. One of the most widely utilized datasets in this regard is ERA5, which provides global meteorological information. Despite its broad coverage, the coarse spatial resolution of ERA5 data presents challenges in examining local-scale effects on energy systems, such as battery storage for small-scale wind farms or community energy systems. In this study, we introduce a robust statistical downscaling approach that utilizes a machine learning approach to improve the resolution of ERA5 wind speed data from around 31 km × 31 km to 1 km × 1 km. To ensure optimal results, a comprehensive preprocessing step is performed to classify regions into three classes based on the quality of ERA5 wind speed estimates. Subsequently, a regression method is applied to each class to downscale the ERA5 wind speed time series by considering the relationship between ERA5 data, observations from weather stations, and topographic metrics. Our results indicate that this approach significantly improves the performance of ERA5 wind speed data in complex terrain. To ensure the effectiveness and robustness of our approach, we also perform thorough evaluations by comparing our results with the reference dataset COSMO-REA6 and validating with independent datasets.

A Novel Ensemble Model Based on an Advanced Optimization Algorithm for Wind Speed Forecasting

Concerning the vision of achieving carbon neutral and peak carbon goals, wind energy is extremely important as a renewable and clean energy source. However, existing research ignores the implicit features of the data preprocessing technique and the role of the internal mechanism of the optimization algorithm, making it difficult to achieve high-accuracy prediction. To fill this gap, this study proposes a wind speed forecasting model that combines data denoising techniques, optimization algorithms, and machine learning algorithms. The model discusses the important parameters in the data decomposition technique, determines the best parameter values by comparing the model’s performance, and then decomposes and reconstructs the wind speed time series. In addition, a novel optimization algorithm is used to optimize the parameters of the machine learning algorithm using a waiting strategy and an aggressive strategy to improve the effectiveness of the model. Several control experiments were designed and implemented using 10-min wind speed data from three sites in Penglai, Shandong Province. Based on the numerical comparison results and the discussion of the proposed model, it is concluded that the developed model can obtain high accuracy and reliability of wind speed prediction in the short term relative to other comparative models and can have further applications in wind power plants.

Estimation of extreme wind speed based on upcrossing rate of mean wind speeds with Weibull distribution

The estimation of the extreme mean wind speed has a pivotal role in the structural wind-resistance design. For yearly maximum mean wind speed samples usually not enough, it is necessary to estimate the extreme mean wind speed from short-term mean wind speed records, such as about a few years. The upcrossing rate method, which relies on the distribution of the mean wind speed, is one of the popular extreme estimation methods. It is widely recognized that the mean wind speed follows the Weibull distribution usually and the Rayleigh distribution at some areas. The upcrossing rate method for mean wind speed time series following Rayleigh distribution was proposed by Harris. The upcrossing rate method for mean wind speed time series following the Weibull distribution is studied in the present paper, by translating the Weibull process to the Rayleigh process based on the theory of cumulative distribution function mapping. The uncertainty of the extreme mean wind speed estimated by the proposed method is investigated to consider the sampling error from short-term mean wind speed records. The effectiveness of the proposed upcrossing rate method and uncertainty analysis are verified by the numerically generated mean wind speeds based on the spectral representation method with Von der Hoven wind speed spectrum.