Wind Speed Model Research Articles

Modeling the wind speed in North Morocco

The change of the wind speed is strictly related to several natural factors such as local topographical and the ground cover variations, then any adjustment has to take into account the statistical variation for each specific region under study. Unlike the Weibull distribution, which is most used in wind speed modeling, we investigate two alternative distribution functions for wind speed by using the extreme value theory. The generalized Champernowne distribution function and the mixture Log-normal-Pareto distribution function are considered. We demonstrate that the proper generalized extreme value distribution gives a good fit for wind speed in the North Moroccan. In order to validate the models, a comparison of the produced aggregate wind energy in the aeolian wind turbine was being established. The empirical study shows that the generalized extreme value distribution reflects better the intensity of the wind power energy.

A new generalization of Lindley distribution for modeling of wind speed data

The most suitable source of energy for human use is wind energy, which is competitive and supports the energy demand of a large population. In this study, we introduced a new probability distribution for the analysis of wind speed data. The newly developed distribution is known as “New Alpha power transformed power Lindley”. Some mathematical properties of the proposed distribution were derived including reliability function, failure rate, moments and associated measures, quantile function. The model parameters were estimated using the maximum likelihood approach. The performance of the estimation method was assessed via a simulation study. The wind speed datasets were analyzed using new distribution and compare its modeling performance with eleven renowned generalizations of Lindley distributions (Lindley, power Lindley, Marshall–Olkin Lindley, exponentiated Lindley, Pseudo Lindley, Quasi Lindley, Gamma Lindley, generalized inverse Lindley, extended Lindley, exponentiated power Lindley, extended inverse Lindley and extended power Lindley). To good fitting probability distribution function, log-likelihood, root mean square error, coefficient of determination, Akaike Information Criteria for each distribution have been calculated. Additionally, estimated density and cdf curves were fitted over the observed wind speed dataset. Findings showed that the proposed distribution provides the best fitting according to model selection criteria. On the other hand, exponentiated power Lindley and extended power Lindley distribution are the next best distributions for modeling wind speed data for selected stations. Overall, outcomes show the practicality, accuracy, and adequacy of the newly proposed distribution depicting wind energy data.

Assessment of CMIP6 Model Performance for Wind Speed in China

As the major renewable energy, wind can greatly reduce carbon emissions. Following the “carbon neutral” strategy, wind power could help to achieve the realization of energy transformation and green development. Based on ERA5 reanalysis data and the multi-ensemble historical and scenario simulations of the Coupled Model Intercomparison Project Phase 6 (CMIP6), a variety of statistical analyses are used to evaluate the performance of CMIP6 simulating the wind speed in China. The conclusions are as follows: spatial patterns of the nine CMIP6 models are similar with ERA5, but BCC-CSM2-MR and MRI-ESM2-0 highly overestimate the wind speed in northwest China. CESM2-WACCM, NorESM2-MM, and HadGEM3-GC31-MM behave better than the other six CMIP6 models in four specific regions are chosen for detailed study. CESM2-WACCM, NorESM2-MM, and HadGEM3-GC31-MM tend to simulate a larger wind speed than ERA5 except the yearly averaged wind speed in region II and region IV. CESM2-WACCM and NorESM2-MM simulate a large monthly mean wind speed, but the value is relatively close with ERA5 in the summer. HadGEM3-GC31-MM overestimates wind speed in region I and region II from April to October, but gets closer with ERA during winter. CESM2-WACCM, NorESM2-MM, and HadGEM3-GC31-MM simulate an increasing trend in Tibetan Plateau and Xinjiang in the next 100 years, while NorESM2-MM projects rising wind speed in the eastern part of Inner Mongolia, and HadGEM3-GC31-MM simulates increasing wind speed in the northeast and central China. The future wind speed in three models is projected to decline in region I, and the value of HadGEM3-GC31-MM is much larger. In region II, wind speed simulated by three models is projected to decrease, but the wind speed from HadGEM3-GC31-MM in region III and modeled wind speed in region IV from NorESM2-MM would climb with the slope equal to 0.0001 and 0.0012, respectively. This study indicates that the CMIP6 models have certain limitations to perform realistic wind changes, but CMIP6 could provide available reference for the projection of wind in specific areas.

Research on variable pitch control strategy of direct-driven offshore wind turbine using KELM wind speed soft sensor

This study proposes a modeling method of soft measurement of offshore wind speed using Kernal Extreme Learning Machine (KELM). The soft measurement model of offshore wind speed is presented based on the data-driven method and kernel function extreme learning machine. An improved gray Wolf optimization algorithm is applied to optimize its parameters to enhance the measurement accuracy. Finally, based on the established offshore wind speed measurement model, a feedforward and feedback variable rotor controller is designed and verified by simulation, which proves the effectiveness of the research in this study.

Hybrid Deep Learning Model for Short-Term Wind Speed Forecasting Based on Time Series Decomposition and Gated Recurrent Unit

Accurate wind speed prediction has been becoming an indispensable technology in system security, wind energy utilization, and power grid dispatching in recent years. However, it is an arduous task to predict wind speed due to its variable and random characteristics. For the objective to enhance the performance of forecasting short-term wind speed, this work puts forward a hybrid deep learning model mixing time series decomposition algorithm and gated recurrent unit (GRU). The time series decomposition algorithm combines the following two parts: (1) the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and (2) wavelet packet decomposition (WPD). Firstly, the normalized wind speed time series (WSTS) are handled by CEEMDAN to gain pure fixed-frequency components and a residual signal. The WPD algorithm conducts the second-order decomposition to the first component that contains complex and high frequency signal of raw WSTS. Finally, GRU networks are established for all the relevant components of the signals, and the predicted wind speeds are obtained by superimposing the prediction of each component. Results from two case studies, adopting wind data from laboratory and wind farm, respectively, suggest that the related trend of the WSTS can be separated effectively by the proposed time series decomposition algorithm, and the accuracy of short-time wind speed prediction can be heightened significantly mixing the time series decomposition algorithm and GRU networks.

Long short-term memory (LSTM)-based wind speed prediction during a typhoon for bridge traffic control

A short-term wind speed prediction framework is proposed for bridge traffic control under strong winds. The framework mainly focuses on improving the prediction accuracy for the timeframe of traffic control during a typhoon. Two concepts are newly proposed to achieve the goal: 1) hybrid modeling of wind speed at the bridge; and, 2) the adoption of a time-shifted data correction (TSDC) method. First, the hybrid modeling considers two available data types, one from a structural health monitoring system of the bridge and the other from the regional specialized meteorological center (RSMC). The training features of a long short-term memory (LSTM) approach are chosen based on the maximum sustained winds of a typhoon. Second, the TSDC method accounts for a time-delay phenomenon between the maximum wind speed at the bridge deck and the maxima or minima of the selected features. The Mean Absolute Error (MAE)-based grid search method determines the preferable combinations of two parameters: input data length and the time-shifted length of the training data. As a numerical example, typhoons from 2020 are used as test data to demonstrate the improvement in prediction performance via the use of hybrid modeling and the TSDC method.

Dynamic Equivalent Modeling of Wind Farm Based on Dominant Variable Hierarchical Clustering Algorithm

The actual operating state of the wind turbine group is influenced by the wake effect and control mode; however, the current models cannot describe the actual operating state very well. A dynamic equivalent modeling method for a doubly fed wind power generator is proposed on the basis of ensuring the accurate description of the wind turbine group. As the clustering index, dominant variables are used in the hierarchical clustering algorithm, which are extracted by principal component analysis. Three dynamic equivalent models of 24 wind turbines are established using PSCAD software platform, which use 13 state variables, wind speed, and dominant variables as clustering indexes, respectively. Furthermore, the active power and reactive power output curves of wind farm are simulated in the case of the three-phase short-circuit fault on the system side or wind speed fluctuation, respectively. The simulation results demonstrate that it is reasonable and effective to extract slip ratio and wind turbine torque as clustering index, and the maximal relative error between the dominant variable equivalent model and 13-state-variable model is only 9.9%, which is greatly lower than that of the wind speed model, K-means clustering model, neural network model, and support vector machine model. This model is easy to implement and has wider application prospect, especially for characteristics analysis of large-scale wind farm connected to power grid.

Weather forecasting based on data-driven and physics-informed reservoir computing models.

In response to the growing demand for the global energy supply chain, wind power has become an important research subject among studies in the advancement of renewable energy sources. The major concern is the stochastic volatility of weather conditions that hinder the development of wind power forecasting approaches. To address this issue, the current study proposes a weather prediction method divided into two models for wind speed and atmospheric system forecasting. First, the data-based model incorporated with wavelet transform and recurrent neural networks is employed to predict the wind speed. Second, the physics-informed echo state network was used to learn the chaotic behavior of the atmospheric system. The findings were validated with a case study conducted on wind speed data from Turkmenistan. The results suggest the outperformance of physics-informed model for accurate and reliable forecasting analysis, which indicates the potential for implementation in wind energy analysis.

Wind Speed Distributions Used in Wind Energy Assessment: A Review

With economic development and population growth, energy demand has shown an upward trend. Renewable energy is inexhaustible and causes little pollution, which has broad prospects for development. In recent years, wind energy has been developed as an essential renewable energy source. The use of wind power is very environmentally friendly and plays a critical role in economic growth. Assessing the characteristics and potential of wind energy is the first step in the effective development of wind energy. The wind speed distribution at a specific location determines the available wind energy. This paper reviews the wind speed distribution models used for wind energy assessment, and they are applicable to different wind regimes. All potential wind speed distribution models should be considered for modeling wind speed data at a particular site. Previous studies have selected several parameter estimation methods and evaluation criteria to estimate model parameters and evaluate the goodness-of-fit. This paper discusses their advantages and disadvantages. The characteristics of wind speed distribution are constantly varying geographically and temporally. Wind energy assessment should consider local geographical elements, such as local climate, topography, and thermal properties difference between the land and the sea, and focus on long-term variations in wind characteristics.

Fatigue lifespan assessment of stay cables by a refined joint probability density model of wind speed and direction

Stay cables are crucial load-bearing components of long-span cable-stayed bridges. Because they are sensitive to wind, the wind load is an important control load in their safety and fatigue evaluation. To consider the effects of variations in the wind speed and direction, a joint probability density model of wind speed and direction is proposed for evaluating the fatigue lifespan of a stay cable. For this purpose, an angular–linear model is introduced to coordinate the marginal distribution of wind speed and direction. The marginal distribution of wind speed comprises a Gumbel model, while that of the direction comprises a refined mixture of a von Mises distribution model. Subsequently, based on the dynamic simulation of a coupled wind–vehicle–bridge system, an assessment method for fatigue lifespan is developed by considering the variation of traffic flow with four load levels and variations in wind speed and direction. The results indicate that the refined angular–linear distribution model yields considerable fitting results for the measured data with respect to the wind speed and direction. Although the response and fatigue damage of a stay cable mainly depend on its length and location, the effect of the direction variation of the wind load is also not negligible. Additionally, the results from the assessment method show that the fatigue lifespan of a stay cable on the windward side of the local prevailing wind direction is relatively shorter than that of the leeward side.

Research of a combined wind speed model based on multi‐objective ant lion optimization algorithm

In the past few decades, wind power generation has gradually become an important source in the global energy market, which effectively meets the energy demand of human production activities. However, the instability and diffusion of wind speed bring difficulties to the wind energy development and promotion. For improving the predictive accuracy of original sequence, scholars have proposed a variety of prediction models, but many current forecasting models often neglect the importance of data processing and can be easily limited by a single model, which causes poor performances. Therefore, a combined model is built that mainly includes the complete ensemble empirical mode decomposition with adaptive noise, several single models, and multi-objective ant lion optimization algorithm. This combined model not only reduces the impact of high-frequency noise, but also extracts original sequences features as much as possible, combines the advantages of multiple single models, and greatly improves forecasting accuracy and stability.

Assessing boundary condition and parametric uncertainty in numerical-weather-prediction-modeled, long-term offshore wind speed through machine learning and analog ensemble

Abstract. To accurately plan and manage wind power plants, not only does the time-varying wind resource at the site of interest need to be assessed but also the uncertainty connected to this estimate. Numerical weather prediction (NWP) models at the mesoscale represent a valuable way to characterize the wind resource offshore, given the challenges connected with measuring hub-height wind speed. The boundary condition and parametric uncertainty associated with modeled wind speed is often estimated by running a model ensemble. However, creating an NWP ensemble of long-term wind resource data over a large region represents a computational challenge. Here, we propose two approaches to temporally extrapolate wind speed boundary condition and parametric uncertainty using a more convenient setup in which a mesoscale ensemble is run over a short-term period (1 year), and only a single model covers the desired long-term period (20 year). We quantify hub-height wind speed boundary condition and parametric uncertainty from the short-term model ensemble as its normalized across-ensemble standard deviation. Then, we develop and apply a gradient-boosting model and an analog ensemble approach to temporally extrapolate such uncertainty to the full 20-year period, for which only a single model run is available. As a test case, we consider offshore wind resource characterization in the California Outer Continental Shelf. Both of the proposed approaches provide accurate estimates of the long-term wind speed boundary condition and parametric uncertainty across the region (R2>0.75), with the gradient-boosting model slightly outperforming the analog ensemble in terms of bias and centered root-mean-square error. At the three offshore wind energy lease areas in the region, we find a long-term median hourly uncertainty between 10 % and 14 % of the mean hub-height wind speed values. Finally, we assess the physical variability in the uncertainty estimates. In general, we find that the wind speed uncertainty increases closer to land. Also, neutral conditions have smaller uncertainty than the stable and unstable cases, and the modeled wind speed in winter has less boundary condition and parametric sensitivity than summer.

Oscillation analysis of doubly-fed unit considering wind speed variation

Tower shadow effect and wind shear may cause power oscillation of the unit. In order to study the influence of tower shadow effect and wind shear on the output power of wind turbine, a doubly-fed turbine was taken as an example. Firstly, the influence of tower shadow effect and wind shear was considered to study the periodic power fluctuation characteristics of wind turbines. Then, according to the dynamic model of mechanical transmission mechanism, the influences of the inertia constants of generator, fan and the stiffness coefficient of the shaft system on the transient performance of the wind power generation system were considered respectively. Finally, a single machine infinite bus system model including wind speed model is built on PSCAD/EMTDC platform for simulation. The results show that the tower shadow effect and wind shear component can cause the power fluctuation of the turbine. When the power fluctuation frequency of the turbine is equal to the natural oscillation frequency of the wind turbine shafting, the resonance of the turbine occurs, and the amplitude of oscillation is the largest. Changing the transmission parameters will affect the power fluctuation amplitude and speed response speed of the unit.

Wind speed modeling over complex terrain with the artificial neural network in the measure-correlate-predict technique: A case study of Malaysia

This study aimed to create a Malaysian wind map of greater accuracy. Compared to a previous wind map, spatial modeling input was increased. The Genetic Algorithm-optimized Artificial Neural Network Measure–Correlate–Predict method was used to impute missing data, and managed to control over- or under-prediction issues. The established wind map was made more reliable by including surface roughness to simulate wind flow over complex terrain. Validation revealed that the current wind map is 33.833% more accurate than the previous wind map. Furthermore, the correlation coefficient between wind map-simulated data and observed data was high as 0.835. In conclusion, the new and improved wind map for Malaysia simulates data with acceptable accuracy.

Performance Comparison of New Generation Parameter Estimation Methods for Weibull Distribution to Compute Wind Energy Density

To install a wind energy conversion system to a region, the wind speed characteristics of that region must be identified. The two-parameter Weibull distribution is highly efficient in modeling wind speed characteristics. In this study, the wind speed data of 32 cities in three different regions of Turkey have been comparatively analysed to estimate Weibull distribution function parameters by the use of three well-known methods (Graphical Method (GM), Maximum Likelihood Method (MLM), Justus Moment Method (JMM)) and three new parameter estimation methods (Energy Pattern Factor Method (EPFM), Wind Energy Intensification Method (WEIM), Power Density Method (PD)) which have been proposed in recent years. Three years of hourly wind speed data of the specified regions have been used. The performance metrics of these analyses have been compared using Wind Energy Error (WEE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2). The results have shown that while the PD method has high model performance, the JMM is closely competitive with the MLM. Besides, the wind energy densities that were estimated by using actual data have been compared with the resulting Weibull distribution. It has been clear that the method that has the closest estimation to the actual values is the PD method.

A Hybrid Optimized Model of Adaptive Neuro-Fuzzy Inference System, Recurrent Kalman Filter and Neuro-Wavelet for Wind Power Forecasting Driven by DFIG

Renewable energy resources are playing a compromising role in the new generation of sustainable energy and smart grid. Wind power is playing a crucial role these days to minimize the fossil fuel emissions. Their integration is depending on a highly accurate forecasting model due to its intermittency, nonlinearity, and fluctuation. This work presents a hybrid optimized model of Adaptive Neuro-Fuzzy Inference System (ANFIS), Recurrent Kalman Filter (RKF) and Neuro-Wavelet (WNN) for Wind Power Forecasting Driven by doubly fed induction generator (DFIG). The predictions of individual models and hybrid of ANFIS, RKF and WNN models for wind speed and power generated are compared with other published work results in the literature. Six different hybrid models are proposed (ANFIS+WNN+RKF, ANFIS+RKF+WNN, WNN+ANFIS+RKF, WNN+RKF+ANFIS, RKF+WNN+ANFIS, RKF+ANFIS+WNN). The results of this work indicate that all proposed hybrid models are performing well but the hybrid of ANFIS+RKF+WNN in sequence has the optimal performance compared to other models.

Multiobjective Economic Optimal Dispatch for the Island Isolated Microgrid under Uncertainty Based on Interval Optimization

In order to analyse the impact of renewable generation and load uncertainties on the economic operation optimization of the island microgrid, a multiobjective economic optimal dispatch model under uncertainty based on interval optimization is proposed in this paper. The mathematical model of distributed generation and the prediction model of wind speed and wave generation are established. The uncertainties of renewable generation and load are described by the interval mathematical method. On this basis, the interval multiobjective optimal dispatch model is presented. For the “battery disgusting” users on the island, the battery cost is regarded as a separate optimization objective, and a multiobjective optimization objective function to minimize the economic cost, battery cost, and pollution emission of the island microgrid is discussed. An island microgrid, composed of wind turbine, photovoltaic, wave energy generation, diesel generator, and energy storage system, is chosen as a case study. The NSGA-II algorithm is applied to solve the multiobjective optimal problem. The results for deterministic forecast data and load are analysed, and the optimal operation scheme is obtained by the improved multiobjective grey target decision-making method. The influence of renewable generation fluctuations ±10%, ±20%, and ±30% and the load fluctuations ±10% and ±20% on island microgrid operation optimization is discussed in detail, respectively. The relevant research results can provide a reference for formulating the operating scheme of the island microgrid.

Study on Wind Field Characteristics in a Coastal Plain Based on a New Three-Dimensional Joint Distribution Model

This paper studied the joint probability distribution of wind speed, wind direction, and wind height. The measured wind field data of a coastal plain in Zhongshan city, Guangdong Province, China, were taken as the research object. A three-dimensional joint distribution modeling method, based on the copula function and the AL (angular–linear) model, is proposed. Firstly, the wind speed is modeled by the common distribution model, and the Weibull distribution is selected. Secondly, the mvM (mixed von Mises distribution) was used to fit the wind direction probability density, and the joint distribution of wind speed and wind direction was established based on the AL model. Finally, a three-dimensional joint distribution model of wind speed, wind direction, and height was established by considering the effect of height through the copula function. The results showed that Weibull distribution can better describe the wind speed distribution in this region. The north–south wind prevailed in this region, and the probability of the main wind direction decreased with the increase in height. The joint distribution of wind speed and direction, based on the AL model, fitted well with the measured data, and the final three-dimensional distribution model had a good fitting effect.

Modeling wind speed time series by Chebyshev polynomial expansion method

ABSTRACT This paper sets out to simulate non-Gaussian wind speed time series. Given a set of historical wind speed observations, if the cumulative distribution function is not explicitly known, a probability distribution based on Fourier series is developed to recover the analytical expression of the cumulative distribution function. The marginal transformation is then applied to map wind speed observations to the standard normal space, where the autocorrelation function is represented by a weighted sum of Chebyshev polynomials. Finally, an explicit formula is derived to generate samples of wind speed time series. Testing on three sets of historical wind speed observations, it shows that the proposed method can well match the cumulative distribution function and autocorrelation function of wind speed time series, the absolute errors between the fitted cumulative distribution function and empirical cumulative distribution function are less than ; the autocorrelation function of generated wind speed time series is in a good agreement with that of historical wind speed observations, the differences are less than .

A combined model for short-term wind speed forecasting based on empirical mode decomposition, feature selection, support vector regression and cross-validated lasso.

BackgroundThe planning and control of wind power production rely heavily on short-term wind speed forecasting. Due to the non-linearity and non-stationarity of wind, it is difficult to carry out accurate modeling and prediction through traditional wind speed forecasting models.MethodsIn the paper, we combine empirical mode decomposition (EMD), feature selection (FS), support vector regression (SVR) and cross-validated lasso (LassoCV) to develop a new wind speed forecasting model, aiming to improve the prediction performance of wind speed. EMD is used to extract the intrinsic mode functions (IMFs) from the original wind speed time series to eliminate the non-stationarity in the time series. FS and SVR are combined to predict the high-frequency IMF obtained by EMD. LassoCV is used to complete the prediction of low-frequency IMF and trend.ResultsData collected from two wind stations in Michigan, USA are adopted to test the proposed combined model. Experimental results show that in multi-step wind speed forecasting, compared with the classic individual and traditional EMD-based combined models, the proposed model has better prediction performance.ConclusionsThrough the proposed combined model, the wind speed forecast can be effectively improved.