Wind Speed Estimation Research Articles

Prediction of wind fields in mountains at multiple elevations using deep learning models

To optimize the site selection of wind turbines, it is essential to understand the variability of wind speeds at different elevations on mountains and their wind characteristics. The erection of anemometer at a large altitude in mountainous regions poses significant financial and safety challenges. Therefore, it is of utmost importance to design a method that facilitates the estimation of multiple high-elevation wind speeds utilizing low-elevation measurements. This study built a graph data structure by assimilating prior knowledge, including the mountain topography and relative position of the anemometer. A custom-designed graph neural network model was designed to predict wind speed data at high-elevation regions based on wind speed data at a low-elevation region. Moreover, an enhanced UNet model was employed to predict wind field data at higher elevations utilizing predicted wind speed data. To improve the stability and performance of the model, the flux conservation equation was integrated into the loss function of the graph neural network. The results suggest that integrating mountain information and physical loss in the model can significantly improve the accuracy of wind speed data predictions. The graph neural network has remarkably enhanced the performance of the UNet model.

Wind field simulation using WRF model in complex terrain: A sensitivity study with orthogonal design

Accurately simulating wind speed is of utmost importance for wind power assessments. The objective of this study is to investigate the performance of wind speed simulation in complex terrain using different parameterization schemes from the Weather Research and Forecasting (WRF) model, employing an orthogonal design methodology. Specifically, nine WRF simulations are conducted based on the orthogonal test, considering various configurations of the planetary boundary layer (PBL), microphysics (MP), and land surface (LS) options. The numerical results are then compared to actual wind data obtained from a measuring station at two different heights (50 m and 80 m) during summer and winter periods. Furthermore, range and variance analyses are employed to rank the three schemes and identify the optimal combination. Moreover, we examine the impact of each parameterization scheme on the accuracy of wind speed predictions based on the results obtained from the orthogonal simulations. Additionally, we discuss the influence of using different evaluation indices within the orthogonal test on the outcomes and analyze the WRF simulated results under the optimal scheme combination. Lastly, we conduct an uncertainty analysis of results from the optimal scheme combination. The findings reveal that both the PBL and MP schemes exhibit highly significant effects on the accuracy of wind speed predictions (significance: **), followed by the LS scheme (significance: *). The order of importance for these three options is ranked as follows: PBL > MP > LS, which is independent of the seasons. The optimal configurations vary from summer and winter periods. Specifically, the optimal scheme combination is determined to be PBL-ACM2, MP-Kessler, and LS-Noah MP in summer, while PBL-BouLac, MP-Lin, and LS-Noah MP in winter. The simulating accuracy of the wind speeds is satisfactory under this optimal combination when considering the uncertainty of on-site measurements during these two periods. These results provide valuable insights for selecting appropriate PBL, MP, and LS options (from the WRF model) for wind speed estimates and wind power development in the studied region.

Impact of probe volume and peak detection methods on lidar rotor effective wind speed and turbulence intensity estimations

Lidar simulation techniques are a suitable and increasingly reliable alternative for testing lidar measuring strategies and illustrating their response when combined with modelled wind fields. In this work, two simulation tools are combined to assess the uncertainty in the derivation of the rotor effective wind speed and the wind speed variance from a forward-looking nacelle-mounted continuous wave lidar wind speed estimations. These uncertainties are analysed for a variety of atmospheric turbulence levels and lidar measuring strategies. A synthetic turbulence generator is used to create the reference wind fields. Subsequently, a lidar simulator operated in a continuous-wave mode is used to scan the synthetic wind fields and perform a sensitivity analysis by comparing first- and second-order statistics against reference values. The lidar simulator is enhanced with three Doppler peak detection methods, namely the maximum, the median and the centroid, to extract radial wind speeds from the velocities found within the probe volume. The results show that probe volume and peak detection methods influence the uncertainty of the wind speed variance. The uncertainty in time-averaged and instantaneous rotor effective wind speed estimations is not sensitive to the lidar spatial averaging or peak detection methods investigated. Finally, we saw that the turbulence intensity influences the derived lidar quantities and is the main driver of the variations in rotor effective wind speed uncertainty estimations.

Measured and estimated wind speed of a stand-alone energy system with controlled bi-directional DC-DC battery bank

Simple control of a stand-alone variable speed wind turbine with a permanent magnet synchronous generator (PMSG) is presented in this paper. PMSG fed different types of loads by means of a converter where switched mode rectifier is connected to the PMSG, boost DC-DC converter, and voltage source inverter (VSI). The wind turbine is operated at measured wind speed and it is tested at estimated wind speed which is based on the power calculation of turbine power, generating electric power, losses power, and the dynamic power during the variation of wind speed. The estimation of wind speed would provide a scope of what a control method is applicable in practice and this would increase the performance by scheduling the connected loads. The bidirectional battery charger is controlled and used during the shortage of wind speed. The converter of the battery charger is controlled and implemented on an embedded system by using an STM32-based microcontroller. During the shortage or fluctuation of wind speed, the load voltage is controlled within the acceptable limit, where the voltage has been compensated. An extensive simulation has been conducted by MATLAB/Simulink, and the system shows a good dynamic response to the variation and decrease in wind speed.

A wavelet transform based stationary transformation method for estimating the extreme value of the non-stationary wind speeds

The rational estimation of extreme wind speeds is crucial. As reported, in the Chinese area, the measured wind speed variation from different meteorological observatories shows a general non-stationary trend in the past 40 years due to urbanization factors or temperature variation. Thus, the non-stationary extreme value analysis (TNGEV) of the measured wind speed is required. However, TNGEV is relatively complicated. Under such a background, in this paper, a novel simplified wavelet transform-based stationary transformation method (PNGEV) is proposed for the extreme value analysis of the non-stationary wind speeds. This paper firstly derives the proposed time-varying extreme value distribution parameter form, combining the wavelet transform and moving average. Secondly, a case study is provided to illustrate and verify this proposed method (PNGEV), using the 40-year daily maximum wind speeds recorded from 1981 to 2020 in Baoshan District Shanghai, China. The effectiveness of the proposed method (PNGEV) is verified by comparing it with TNGEV in the return period and the risk of failure. By comparison, it can be figured out that the proposed PNGEV is practicable and outperforms TNGEV in the stability of the return period calculation, as well as the time-varying extreme value distribution establishment.

Tropical cyclones’ acoustic reconnaissance

Acoustic reconnaissance of tropical cyclones with underwater gliders is an emerging approach for a comprehensive understanding of the oceanic conditions leading to the formation and intensification of cyclones and for aiding in wind speed forecasting. Shaw et al. (1978) showed that the underwater sound pressure level is in the linear relationship to the logarithm of the moderate local wind speed. Wilson and Makris (2006) proposed an acoustic surface source model for hurricane wind speeds. The model requires a parameterization of the winds’ contribution. The inversion of the acoustic data leads to estimation of the local wind speeds. The Gulf of Mexico acoustic dataset, collected by the bottom-anchored monitoring system during the passage of storm Barry (2019), is analyzed and correlated with the high-resolution wind speed data generated by the Weather Research and Forecast model. The efficacy of gliders outfitted with acoustic system to provide the real-time reporting of the local wind speeds is also discussed based on the flights’ recorded soundscapes. Acoustic glider reconnaissance offers a safe and cost-efficient way of contributing new type data to NOAA and US NAVY weather forecasting models. [Work supported by the Office of the Under Secretary of Defense for Research and Engineering, award# FA9550-21-1-0215.]

A New ANN Technique for Short-Term Wind Speed Prediction Based on SCADA System Data in Turkey

The restored interest now receives renewable energy due to the global decline in greenhouse gas emanations and fossil fuel combustion. The fasted growing energy source, wind energy generation, is recognized as a clean energy source that has grown fast and is used extensively in wind power-producing facilities. This study’s short-term wind speed estimations are made using a multivariate model based on an artificial neural network (ANN) that combines several local measurements, including wind speed, wind direction, LV active power, and theoretical power curve. The dataset was received from Turkey’s SCADA system at 10-min intervals, and the actual data validated the expected performance. The research took wind speed into account as an input parameter and created a multivariate model. To perform prediction outcomes on time series data, an algorithm such as an artificial neural network (ANN) is utilized. The experiment verdicts reveal that the ANN algorithm produces reliable predicting results when metrics like 0.693 for MSE, 0.833 for RMSE and 0.96 for R-squared or Co-efficient of determination are considered.

A non-parametric approach for wind speed distribution mapping

Statistical methods to estimate wind resources at unsampled locations in a region can serve as an initial step to identify locations that warrant further investigation. There has been an ongoing effort to develop approaches for mapping the parameters of the wind speed distribution with statistical methods. This approach enables a comprehensive understanding of the wind resource variability across the entire region by considering the full wind speed distribution rather than focusing solely on mean values. The present study proposes a non-parametric approach to map the wind speed distribution. The method's main advantage is that it avoids constraining the region to a single distribution family and is thus more flexible than existing methods. In the proposed approach, a number of wind speed quantiles are first mapped in the region using machine learning techniques. Afterwards, the wind speed distribution is estimated by fitting an asymmetric kernel estimator to the estimated wind speed quantiles at unsampled locations. The new approach was compared to the standard statistical method based on mapping the regional wind speed distribution parameters. The results indicate that the non-parametric approach leads in the best scenario to a 9% and 6% drop in the Kolmogorov-Smirnov statistic on average during cross-validation and validation, respectively. The Birnbaum-Saunders and the Log-Normal kernels gave a better fit to the estimated wind speed quantiles than the Weibull kernel. The proposed approach is recommended in regions with high wind regime variability.

Joint Return Value Estimation of Significant Wave Heights and Wind Speeds with Bivariate Copulas

Joint Return Value Estimation of Significant Wave Heights and Wind Speeds with Bivariate Copulas

The Application of the Long-Short Term Memory (LSTM) Forecasting Method on the Impact of Tropical Cyclones in Indonesia

Effective disaster mitigation strategies are paramount in the realm of risk management concerning natural calamities, with the primary objective of mitigating potential devastation. A pragmatic and impactful method involves predicting the contributory aspects of such disasters, encompassing variables such as torrential rainfall and formidable wind velocities that tropical cyclones bring. In this study, a comparative analysis of forecasting methodologies is undertaken, precisely the Long Short-Term Memory (LSTM) technique and the Holt Winter approach, both directed toward gauging the impact of tropical cyclones. This investigation focuses on two critical factors: the forecast of precipitation intensity and the estimation of maximum wind speed. The outcomes underscore the superior predictive capabilities of the LSTM method, unequivocally revealing its aptitude for predicting rainfall and wind speed. Impressively, the LSTM method yields remarkable precision levels of 97.433% for rainfall and an even higher accuracy of 99.018% for maximum wind speed forecasting. In essence, this study highlights LSTM's efficacy in disaster prediction with substantial accuracy.

Individual Pitch Control of Wind Turbine System by Estimating Wind Speed Using Pitching Moment

Individual Pitch Control of Wind Turbine System by Estimating Wind Speed Using Pitching Moment

Go with the Flow: Estimating Wind Using Uncrewed Aircraft

This paper presents a fundamentally different approach to wind estimation using Uncrewed Aircraft (UA) than the vast majority of existing methods. This method uses no on-board flow sensor and does not attempt to estimate thrust or drag forces. Using only GPS and orientation sensors, the strategy estimates wind vectors in an Earth-fixed frame during turning maneuvers. The method presented here is called the Wind-Arc method. The philosophy behind this method has been seen in practice, but this paper presents an alternative derivation with resulting performance evaluations in simulations and flight tests. The simulations verify the method provides perfect performance under ideal conditions using simulated GPS, heading angle, and satisfied assumptions. When applied to experimental flight test data, the method works and follows both the airspeed and wind speed trends, but improvements can still be made. Wind triangles are displayed at each instant in time along the flight path that illustrate the graphical nature of the approach and solution. Future work will include wind gust estimation and a Quality of Estimate (QoE) metric to determine what conditions provide good wind speed estimates while preserving the method’s generality and simplicity.

Robust variable step P&O algorithm based MPPT for PMSG wind generation system using estimated wind speed compensation technique

To expedite the cost recovery of the wind energy conversion system (WECS), maximizing power availability at all times is of utmost importance. Therefore, the primary objective of Maximum Power Point Tracking (MPPT) algorithms is to optimize power output by ensuring the achievement of maximum power under varying wind speeds. The perturbation and observation algorithm are widely recognized as the most well-known technique used in wind energy conversion systems (WECS) due to its versatility. Although this algorithm is valued for its simplicity and cost-effectiveness, it does have a significant drawback. Peculiarly, it is insensitive to fluctuations in instantaneous wind speed conditions and lacks accurate step size estimation. To address these limitations, a novel approach called the Robust Variable Step P&O (RVS-P&O) technique has been proposed. The RVS-P&O technique aims to overcome the aforementioned drawbacks. The control strategy employed by the proposed RVS-P&O-MPPT algorithm is based on three fundamental concepts: a new normalization of the selection of the step size, a novel correction procedure to estimate the power variation and wind speed estimation (WSE) algorithm based on the artificial neural network (ANN) controller. Simulations have been carried out by means of MATLAB/Simulink environment. The findings indicate the superiority of the proposed RVS-P&O algorithm compared to several P&O implementations: fixed Large Step (LS), fixed Small Step (SS), Variable Step (VS) and Modified (M)-P&O. The developed algorithm allows reaching 99.79% of wind energy conversion system (WECS) efficiency. This allows obtaining an enhancement of 2.19% in comparison to VS-P&O technique which is the most competing algorithm. Further, the response speed is clearly improved compared to the various P&O versions, as the settling time (sec) is of 0.0074 while that of VS and M−P&O is of 0.0157 and 0.0079, respectively. Indeed, to enhance the quality of the injected power into the grid, a Second Order Sliding Mode Controller (SOSMC) based Super Twisting Algorithm (STA) is proposed. The results show the suggested technique outperforms the PI and First Order (FO)-SMC for current THD minimization by attenuating the odd harmonics without chattering phenomenon.

Digital Twin as a Virtual Sensor for Wind Turbine Applications

Digital twins (DTs) have been implemented in various applications, including wind turbine generators (WTGs). They are used to create virtual replicas of physical turbines, which can be used to monitor and optimize their performance. By simulating the behavior of physical turbines in real time, DTs enable operators to predict potential failures and optimize maintenance schedules, resulting in increased reliability, safety, and efficiency. WTGs rely on accurate wind speed measurements for safe and efficient operation. However, physical wind speed sensors are prone to inaccuracies and failures due to environmental factors or inherent issues, resulting in partial or missing measurements that can affect the turbine’s performance. This paper proposes a DT-based sensing methodology to overcome these limitations by augmenting the physical sensor platform with virtual sensor arrays. A test bench of a direct drive WTG based on a permanent magnet synchronous generator (PMSG) was prepared, and its mathematical model was derived. MATLAB/Simulink was used to develop the WTG virtual model based on its mathematical model. A data acquisition system (DAS) equipped with an ActiveX server was used to facilitate real-time data exchange between the virtual and physical models. The virtual sensor was then validated and tuned using real sensory data from the physical turbine model. The results from the developed DT model showed the power of the DT as a virtual sensor in estimating wind speed according to the generated power.

Evaluation of HY-2C and CFOSAT Satellite Retrieval Offshore Wind Energy Using Weather Research and Forecasting (WRF) Simulations

This study simulated the spatial distribution of wind speeds and wind energy density by using the WRF model, and we used the WRF-simulated results to evaluate the sea surface wind speeds retrieved from the HY-2C and CFOSAT satellite-borne microwave scatterometers over the Yellow Sea region. The main conclusions were as follows: (1) The combination of the MRF boundary layer parameterization scheme, the MM5 near-surface parameterization scheme, and the Global Data Assimilation System (GDAS) initial field demonstrated the best performance in simulating the 10 m wind speed in the Yellow Sea region, with a root-mean-square error (RMSE) of 1.57, bias of 1.24 m/s, and mean absolute percentage error (MAPE) of 17%. (2) The MAPE of the HY-2C inversion data was 9%, while the CFOSAT inversion data had an MAPE of 6%. The sea surface wind speeds derived from the HY-2C and CFOSAT satellite scatterometer inversions demonstrated high accuracy and applicability in this region. (3) The wind speed was found to increase with altitude over the Yellow Sea, with higher wind speeds observed in the southern region compared to the northern region. The wind power density increased with altitude, and the wind power density in the southern area of the Yellow Sea was higher than in the northern region. (4) The CFOSAT satellite inversion products were in good agreement with the WRF simulation results under low wind speed conditions. In contrast, the HY-2C satellite inversion products showed better agreement under moderate wind speed conditions. Under high wind speed conditions, both satellite inversion products exhibited minor deviations, but the HY-2C product had an overall overestimation, while the CFOSAT product remained within the range of −1 to 1 m/s. (6) The wind power density increased with the satellite-inverted 10 m wind speed. When the 10 m wind speed was less than 9 m/s, the wind power density exhibited a roughly cubic trend of increase. However, when the 10 m wind speed exceeded 9 m/s, the wind power density no longer increased with the rise in 10 m wind speed. These findings provide valuable insights into wind energy resources in the Yellow Sea region and demonstrate the effectiveness of satellite scatterometer inversions for wind speed estimation. The results have implications for renewable energy planning and management in the area.

Obukhov Length Estimation From Spaceborne Radars

AbstractTwo air‐sea interaction quantification methods are employed on synthetic aperture radar (SAR) scenes containing atmospheric‐turbulence signatures. Quantification performance is assessed on Obukhov length L, an atmospheric surface‐layer stability metric. The first method correlates spectral energy at specific turbulence‐spectrum wavelengths directly to L. Improved results are obtained from the second method, which relies on a machine‐learning algorithm trained on a wider array of SAR‐derived parameters. When applied on scenes containing convective signatures, the second method is able to predict approximately 80% of observed variance with respect to validation. Estimated wind speed provides the bulk of predictive power while parameters related to the kilometer‐scale distribution of spectral energy contribute to a significant reduction in prediction errors, enabling the methodology to be applied on a scene‐by‐scene basis. Differences between these physically based estimates and parameterized numerical models may guide the latter's improvement.

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.

Estimation of Wind Speed Based on Schlieren Machine Vision System Inspired by Greenhouse Top Vent.

Greenhouse ventilation has always been an important concern for agricultural workers. This paper aims to introduce a low-cost wind speed estimating method based on SURF (Speeded Up Robust Feature) feature matching and the schlieren technique for airflow mixing with large temperature differences and density differences like conditions on the vent of the greenhouse. The fluid motion is directly described by the pixel displacement through the fluid kinematics analysis. Combining the algorithm with the corresponding image morphology analysis and SURF feature matching algorithm, the schlieren image with feature points is used to match the changes in air flow images in adjacent frames to estimate the velocity from pixel change. Through experiments, this method is suitable for the speed estimation of turbulent or disturbed fluid images. When the supply air speed remains constant, the method in this article obtains 760 sets of effective feature matching point groups from 150 frames of video, and approximately 500 sets of effective feature matching point groups are within 0.1 difference of the theoretical dimensionless speed. Under the supply conditions of high-frequency wind speed changes and compared with the digital signal of fan speed and data from wind speed sensors, the trend of wind speed changes is basically in line with the actual changes. The estimation error of wind speed is basically within 10%, except when the wind speed supply suddenly stops or the wind speed is 0 m/s. This method involves the ability to estimate the wind speed of air mixing with different densities, but further research is still needed in terms of statistical methods and experimental equipment.

Real‐time rotor effective wind speed estimation based on actuator disc theory: Design and full‐scale experimental validation

AbstractThe use of state estimation techniques offers a means of inferring rotor effective wind speed from standard measurements of wind turbines. Typical wind speed estimators rely upon a pre‐computed quasi‐steady aerodynamic mapping, which describes the relationship between pitch angle and tip‐speed ratio and the power coefficient. In practice, the static mapping does not capture the influence of turbine structural dynamics and atmospheric turbulence, inevitably resulting in poor performance of the wind speed estimation. In addition, the turbine aerodynamic properties might not be easily accessible. Thus, this paper presents a rotor effective wind speed estimation method that obviates the requirement for prior knowledge of turbine power coefficients. Specifically, the proposed method exploits a simple actuator disc model, where the aerodynamic power and thrust coefficients can be characterized in terms of axial induction factors. Based on this insight and standard turbine measurements, real‐time estimation of rotor effective wind speed and axial induction factors can then be achieved using a simplified turbine drive‐train model and an extended Kalman filter. In addition, the actuator disc model can be updated easily over time by calibrating solely two correction factors. Thus, the proposed algorithm presents an alternative for estimating the rotor effective wind speed, which is valuable for numerous applications, for example, LiDAR‐assisted control and coherence studies.

Super-Twisted Sliding Mode Control for Maximum Power Point Tracking of Wind Turbine Based on Neural Network

Given the difficulties in measuring the effective wind speed of wind turbine during the maximum power point tracking (MPPT) process and the unknown nature of the system, this paper proposes a neural network super-twisted sliding mode control (NNST-SMC) method with echo state network (ESN) wind speed estimation. The rotor speed and electromagnetic power are taken as ESN inputs, and the effective wind speed is estimated through the inverse model of wind turbine dynamics. The super-twisted algorithm (STA) can effectively improve the chattering problem of the traditional sliding mode control (SMC) system. The RBF neural network is introduced to compensate for disturbance and uncertainty characteristics of the wind turbine. Results show that compared with the neural network first-order sliding mode control (NNSMC) and super-twisted sliding mode control (ST-SMC), the proposed method can improve the efficiency of wind energy utilization.