Prediction Of Wind Velocity Research Articles

Modeling probability density functions of velocity fluctuations in wind farms

SummaryThe flow in large wind farms is a complex multiscale phenomenon, making comprehensive analytical or computational studies of velocity fluctuations challenging. Motivated by the need for simple, physics‐based analytical approaches to short‐time wind velocity prediction, we derive a statistical model for the spatio‐temporal evolution of streamwise velocity fluctuations in wind farms. Here, we show that the one‐point—one‐time probability density function of velocity fluctuations can be modeled by a weighted superposition of two Ornstein‐Uhlenbeck processes. The model is extended to a one‐particle advection model assuming Taylor's hypothesis of frozen turbulence. We find that our advection model captures the decorrelation process of streamwise velocity fluctuations observed in experiments.

Prediction of Wind Velocity and Pressure Distribution around Buildings Using AI

Prediction of Wind Velocity and Pressure Distribution around Buildings Using AI

COLLAPSE WARNING SYSTEM USING LSTM NEURAL NETWORKS FOR CONSTRUCTION DISASTER PREVENTION IN EXTREME WIND WEATHER

Strong wind during extreme weather conditions (e.g., strong winds during typhoons) is one of the natural factors that cause the collapse of frame-type scaffolds used in façade work. This study developed an alert system for use in determining whether the scaffold structure could withstand the stress of the wind force. Conceptually, the scaffolds collapsed by the warning system developed in the study contains three modules. The first module involves the establishment of wind velocity prediction models. This study employed various deep learning and machine learning techniques, namely deep neural networks, long short-term memory neural networks, support vector regressions, random forest, and k-nearest neighbors. Then, the second module contains the analysis of wind force on the scaffolds. The third module involves the development of the scaffold collapse evaluation approach. The study area was Taichung City, Taiwan. This study collected meteorological data from the ground stations from 2012 to 2019. Results revealed that the system successfully predicted the possible collapse time for scaffolds within 1 to 6 h, and effectively issued a warning time. Overall, the warning system can provide practical warning information related to the destruction of scaffolds to construction teams in need of the information to reduce the damage risk.

Prediction of Wind Velocity to Raise Vortex‐Induced Vibration through a Road‐Rail Bridge with Truss‐Shaped Girder

Vortex‐induced vibration (VIV) of bridges, related to fluid‐structure interaction and maintenance of bridge monitoring system, causes fatigue and serviceability problems due to aerodynamic instability at low wind velocity. Extensive studies on VIV have been performed by directly measuring the vortex shedding frequency and the wind velocity for indicating the largest girder displacement. However, previous studies have not investigated a prediction of wind velocity to raise VIV with a various natural frequency of the structure because most cases have been focused on the estimation of the wind velocity and peeling‐off frequency by the mounting structure at the fixed position. In this paper, the method for predicting wind velocity to raise VIV is suggested with various natural frequencies on a road‐rail bridge with truss‐shaped girder. For this purpose, 12 cases of dynamic wind tunnel test with different natural frequencies are performed by the resonance phenomenon. As a result, it is reasonable to predict wind velocity to raise VIV with maximum RMS displacement due to dynamic wind tunnel tests. Furthermore, it is found that the natural frequency can be used instead of the vortex shedding frequency in order to predict the wind velocity on the dynamic wind tunnel test. Finally, curve fitting is performed to predict the wind velocity of the actual bridge. The result is shown that predicting the wind velocity at which VIV occurs can be appropriately estimated at arbitrary natural frequencies of the dynamic wind tunnel test due to the feature of Strouhal number determined by the shape of the cross section.

Wind velocity prediction through complex kriging: formalism and computational aspects

The formalism of complex random fields is suitable for describing, in a compact and unified way, vectorial data sets in two dimensions, such as wind fields, electromagnetic fields, as well as measurements derived from any two dimensional vectorial field. This representation is rarely considered in Geostatistics, although interesting applications can be found in environmental sciences and meteorology. Moreover, the lack of procedures for modeling a complex covariance function as well as the lack of specialized routines for computing predictions in the complex case have considerably restricted the applications of these techniques. In this paper, some essential aspects of the complex formalism and some computational developments associated with fitting a complex covariance function and predicting a complex-valued random field through an ad-hoc routine are discussed. An environmental application to wind data is provided, moreover, the consistency of the proposed methodology is demonstrated through a numerical study.

Short-Term Forecast and Error Analysis of Wind Power Based on Weight Factors

For power grid with large-scale wind energy, the short-term wind power prediction is important to the grid’s scheduling and stable operating. The overall short-term forecast for wind power connected to the grid relies on the wind velocity and historical power data. Firstly, K-means clustering is introduced to model the power grid, so that the relationship between wind velocity and power can be perfectly described. Considering that there are multiple factors contributing to the prediction of wind velocity and power, we use real data of 15 wind generating set to obtain dependable weight factors of all those dimensions. With the support of mass data, the prediction of power is proved by several measurements (ME, MRE, MAE, RMSE) to be accurate.

The Applicability of Two-Equation Turbulence Models in Wind Velocity Prediction

Wind power prediction plays a pivotal role in reducing the wind power’s negative impact on grid and improving the market competiveness of wind energy. The prediction of wind speed is the key procedure of short-term wind power prediction. In this paper, a wind speed predicting approach based on CFD model was employed, and in order to improve the accuracy of the predicted wind speed, the two turbulence models of standard κ-ε model and RNG κ-ε model, which were applied in the computation of flow field, were studied and compared. The result shows that it has high accuracy on simulating the flow field and predicting wind speed by both the standard κ-ε model and RNG κ-ε model, and the precision is a little bit better when RNG κ-ε model is adopted. On the other hand, the convergence is better when standard κ-ε model is adopted.

Performance Optimization of Building Integrated-Mounted Wind Turbine

Building integrated-mounted wind turbine (BUWT) is one of the most promising renewable energy devices. However, this renewable energy technology is not fully spread principally due to two factors such as uncertainty in the prediction of wind velocity and high turbulence intensity around the building. In this work, the Taguchi method and the analysis of variance (ANOVA) on a horizontal-axis wind turbine has been applied, to study the influence of geometrical parameters such as building depth, width and height, as well as turbine position on the roof and turbine height. To evaluate the above-cited effects, the airflow around an isolated building of parametrical dimension has been simulated using a Computation Fluid Dynamic (CFD) code calibrated against experimental data in a previous paper from the authors. The results reported in the present paper outline the relative effects of the main building geometrical parameters on the performance of a rooftop installed wind turbine and establish basic guidelines for the optimal location of such turbines.

The hourly average solar wind velocity prediction based on support vector regression method

A new neural network technique, support vector regression (SVR), is applied to forecast the solar wind (SW) velocity. SVR is a non-linear efficient tool for high data processing based on statistical learning theory. Its advantage is that the input only requires several periods data (about four 27-d solar-rotation periods to SW velocity prediction in this study), and the prediction is quite reliable. In our work, we deliberately choose the typical SW data covering all main space weather conditions: the SW data during the 9 yr from 1998 to 2006, which includes the periods of the SW speed variation associated with high-speed streams from coronal hole and coronal mass ejections. The performance of the SVR is measured by calculating the absolute average fractional deviation and correlation coefficient between the SVR model and observed SW velocity. We find that the predicted velocity values are over 90 per cent of the observed ones, i.e. the new approach is accurate and reliable in forecasting SW velocity. Based on the error difference, it can be concluded that the SVR technique can lend itself to future space weather forecasting models.

Towards practical use of LES in wind engineering

This paper reviews large-scale computing results currently obtained by the large eddy simulation (LES) technique for various wind engineering problems. The LES or direct numerical simulation (DNS) techniques should be used to numerically simulate unsteady flow phenomena. LES is appropriate for wind engineering applications because its computational power and memory requirements are reasonable. The present study discusses the applicability of LES to several issues such as wind-resistant design, prediction of wind velocity affected by terrain or ground surface conditions, and estimation of turbulence structures and atmospheric diffusion in urban areas. Thus far, numerical validation has been performed mainly by comparison with experimental data. However, when considering the complexity of actual conditions and the natural wind environment, direct comparison with full-scale measurement data is very important in all cases to verify the effectiveness of LES in wind engineering.

Prediction of wind velocity fluctuations from upstream data

A wind velocity prediction scheme which utilizes data from an upwind anemometer to predict the occurence of significant lulls in the wind at a downwind test site has been developed. A computer system developed for the purpose of monitoring and predicting wind conditions calculates the time for lulls in the wind to travel from the upwind prediction anemometer to the test site. The prediction scheme utilizes Taylor's hypothesis with a modification to account for the fact that, in a shear flow, significant gusts and lulls are not transported at a rate which corresponds to the measured mean velocity. Two prediction algorithms are presented. The first algorithm provides the highest probability of successful predictions while the second provides larger prediction lead times. Data from field tests have indicated that significant gusts and lulls can persist for several hundred meters and that prediction times in excess of 1–2 min can be achieved under certain atmospheric conditions.