Wind Field Predictions Research Articles

Ultra Short Term Wind Power Prediction Model Based on WRF Wind Speed Prediction and CatBoost

Due to the urgent requirements of clean energy development, the installed capacity of wind turbine is gradually increasing. In order to achieve effective wind turbine grid control, accurate wind power prediction is very important. In this paper, based on the US Atmospheric Research Center (NCAR) Weather Research and Forecast (WRF) model, the predicted wind field is obtained. Then, a super short-term fast wind power prediction model is proposed, which is composed of Spearman correlation coefficient method for feature extraction and catboost algorithm. With historical power, historical wind speed and predicted wind speed as inputs, the predicted power in the next 4 hours (15 minutes interval) is output. In order to evaluate the prediction ability of the proposed model, four algorithms, LSTM, CatBoost, XGBoost and LightBGM, are adopted. Taking root mean square error (RMSE), mean absolute error (MAE) and training time as evaluation indexes, the results show that CatBoost has the best comprehensive performance.

Fast simulation of high resolution urban wind fields at city scale

High resolution urban wind field simulations are limited in small simulation domain, short simulation period, or stable boundary conditions due to the high computational requirements. To address these limitations, non-intrusive reduced order models (NIROMs) are developed in this study and first realized the prediction of high-resolution 3D wind field in a city-scale area (~150 km2) during a long simulation period (4 weeks). Within the NIROM, 3D convolutional autoencoder and eXtreme Gradient Boost regression models (XGBoost) are adopted. The urban airflow can be predicted rapidly by the XGBoost-decoder models with the input of boundary conditions via boundary conditions - latent variable - full-order wind fields. By comparing NIROM simulations to large-eddy simulations, we find that the NIROM with portable model size is capable for capturing the main spatial distribution characteristics of urban airflow. Moreover, the relationship between wind speed and building distribution indicates that the sparse layout with taller buildings can yield a 2-fold increase in the near-ground wind speed compared to the dense layout with lower buildings, which also benefits pedestrian thermal comfort and pollutant dissipation. Furthermore, this study can assist the optimization of urban ventilation and air quality in urban planning.

Longitudinal wind field prediction based on DDPG

Longitudinal wind field prediction based on DDPG

Understanding the Major Impact of Planetary Boundary Layer Schemes on Simulation of Vertical Wind Structure

The structure and evolution of the atmospheric planetary boundary layer (PBL) plays an important role in the physical and chemical processes of cloud–radiation interaction, vertical mixing and pollutant transport in the atmosphere. The PBL parameterization scheme describes the vertical transport of atmospheric momentum, heat, water vapor and other physical quantities in the boundary layer. The accuracy of wind field simulation and prediction is one of the most significant parameters in the field of atmospheric science and wind energy. Limited by the observation data, there are few studies on wind energy development. A 3D Doppler wind LiDAR (DWL) providing the high-vertical-resolution wind data over the urban complex underlying surface in February 2018 was employed to systematically evaluate the accuracy of vertical wind field simulation for the first time. 11 PBL schemes of the Weather Research and Forecasting Model (WRF) were employed in simulation. The model results were evaluated in groups separated by weather (sunny days, hazy days and windy days), observation height layers of wind field, and various observation wind speeds. Among these factors, the simulation accuracy is most closely related to the observation height layers of wind field. The simulation is fairly accurate at a height of 1000–2000 m, as most of the relative mean biases for wind speed and wind direction are less than 20% and 6% respectively. Below 1000 m, the wind speed and direction biases are about 30–150% m·s−1 and 6–30%, respectively. Moreover, when the observed wind speed was lower than 5 m·s−1, the biases were usually large, and the wind speed relative mean bias reaches up to 50–300%. In addition, the accuracy of the simulated wind profile is better in the range of 10–15 m·s−1 than other speed ranges, and is better above 1000 m than below 1000 m in the boundary layer. We see that the WRF boundary layer schemes have different applicabilities to different weather conditions. The WRF boundary layer schemes have significant differences in wind field simulations, with larger error under the complex topographies. A PBL scheme is not likely to maintain its advantages in the long term under different conditions including altitude and weather conditions.

Spatiotemporal wind field prediction based on physics-informed deep learning and LIDAR measurements

Spatiotemporal wind field information is of great interest in wind industry e.g. for wind resource assessment and wind turbine/farm monitoring & control. However, its measurement is not feasible because only sparse point measurements are available with the current sensor technology such as LIDAR. This work fills the gap by developing a method that can achieve spatiotemporal wind field predictions by combining LIDAR measurements and flow physics. Specifically, a deep neural network is constructed and the Navier–Stokes equations, which provide a good description of atmospheric flows, are incorporated in the deep neural network by employing the physics-informed deep learning technique. The training of this physics-incorporated deep learning model only requires the sparse LIDAR measurement data while the spatiotemporal wind field in the whole domain (which cannot be measured) can be predicted after training. This study, which can discover complex wind patterns that do not present in the training dataset, is totally distinct from previous machine learning based wind prediction studies which treat machine learning models as “black-box” and require the corresponding input and target values to learn complex relations. The numerical results on the prediction of the wind field in front of a wind turbine show that the proposed method predicts the spatiotemporal flow velocity (including both downwind and crosswind components) in the whole domain very well for a wide range of scenarios (including various measurement noises, resolutions, LIDAR look directions, and turbulence levels), which is promising given that only line-of-sight wind speed measurements at sparse locations are used.

Measurement and Prediction of Wind Fields at an Offshore Site by Scanning Doppler LiDAR and WRF

LiDAR-based wind speed measurements have seen a significant increase in interest in wind energy. However, reconstruction of wind speed vector from a LiDAR-measured radial wind speed is still a challenge. Furthermore, for extensive application of LiDAR technology, it can be used as a means to validate simulation and analytical models. To that end, this study employed scanning Doppler LiDAR for assessment of wind fields at an offshore site and compared Weather Research and Forecasting (WRF)-based mesoscale simulations and several wake models with the measurements. Firstly, the effect of carrier-to-noise-ratio (CNR) and data availability on the quality of scanning LiDAR measurements was evaluated. Analysis of vertical profiles show that the average wind speed is higher for wind blowing from the sea than that blowing from the land. Furthermore, profiles obtained from the WRF simulation also show a similar tendency in the LiDAR measurements in general, though it overestimates the wind speeds at higher altitudes. A method for reconstruction of wind fields from plan-position indicator (PPI) and range height indicator (RHI) scans of LiDAR-measured line of sight velocities was then proposed and first used to investigate the effect of coastal terrain. An internal boundary layer with strong shear could be observed to develop from the coastline. Finally, the flow field around wind turbine was measured using PPI scan and used to validate wake models.

In-flight Wind Field Identification and Prediction of Parafoil Systems

The wind field is an essential factor that affects accurate homing and flare landing of parafoil systems. In order to obtain the ambient wind field during the descent of a parafoil system, a combination method of in-flight wind field identification and prediction is proposed. First, a wind identification method only using global position system information is derived based on the flight dynamics of parafoil systems. Then a wind field prediction model is constructed using the atmospheric dynamics, and the low-altitude wind field is predicted based on the identified wind field of high-altitude. Finally, simulations of wind field identification and prediction are conducted. The results demonstrate that the proposed method can identify the wind fields precisely and also predict the wind fields reasonably. This method can potentially be applied in practical parafoil systems to provide wind field information for homing tasks.

Prediction of wind field and power production over complex terrain and its validation by field measurement

Prediction of wind field and power production over complex terrain and its validation by field measurement

Trajectory control of aerostat based on prediction of stratospheric wind field

Trajectory control of aerostat based on prediction of stratospheric wind field

Wind tunnel experiments and numerical fluid simulations using an isolated hill for improving wind field prediction accuracy near the ground surface

Wind tunnel experiments and numerical fluid simulations using an isolated hill for improving wind field prediction accuracy near the ground surface

Numerical simulation and prediction of spatial wind field under complex terrain

A computational fluid dynamics numerical simulation of a spatial wind field under a complex terrain was conducted, and a prediction model of wind characteristics was proposed based on the correlation of simulation results. A large eddy simulation turbulent model was employed to simulate the behavior of the turbulent flow of the spatial wind field by using OpenFOAM 4.0. Then, the prediction model of the spatial wind field was established according to the “triangle edge angle relationship” for the mean wind velocity and spatial correlation analysis for the fluctuating wind velocity. The predicted model was further validated by simulation velocity time histories, reaching good agreement with the simulated results, which indicated that the predicted model had a higher precision. Finally, the proposed model was utilized to predict natural wind field characteristics, and they were compared with field measurement data acquired from ultrasonic anemometers. A comparison of the fluctuating wind velocity time histories, mean wind speeds, and fluctuating wind velocity spectra indicated that the predicted model was practical.

Dynamic rating of overhead transmission lines over complex terrain using a large-eddy simulation paradigm

Dynamic Line Rating (DLR) enables rating of power line conductors using real-time weather conditions. Conductors are typically operated based on a conservative static rating that assumes worst case weather conditions to avoid line sagging to unsafe levels. Static ratings can cause unnecessary congestion on transmission lines. To address this potential issue, a simulation-based dynamic line rating approach is applied to an area with moderately complex terrain. A micro-scale wind solver — accelerated on multiple graphics processing units (GPUs) — is deployed to compute wind speed and direction in the vicinity of powerlines. The wind solver adopts the large-eddy simulation technique and the immersed boundary method with fine spatial resolutions to improve the accuracy of wind field predictions. Statistical analysis of simulated winds compare favorably against wind data collected at multiple weather stations across the testbed area. The simulation data is then used to compute excess transmission capacity that may not be utilized because of a static rating practice. Our results show that the present multi-GPU accelerated simulation-based approach — supported with transient calculation of conductor temperature with high-order schemes — could be used as a non-intrusive smart-grid technology to increase transmission capacity on existing lines.

Small UAS-Based Wind Feature Identification System Part 1: Integration and Validation.

This paper presents a system for identification of wind features, such as gusts and wind shear. These are of particular interest in the context of energy-efficient navigation of Small Unmanned Aerial Systems (UAS). The proposed system generates real-time wind vector estimates and a novel algorithm to generate wind field predictions. Estimations are based on the integration of an off-the-shelf navigation system and airspeed readings in a so-called direct approach. Wind predictions use atmospheric models to characterize the wind field with different statistical analyses. During the prediction stage, the system is able to incorporate, in a big-data approach, wind measurements from previous flights in order to enhance the approximations. Wind estimates are classified and fitted into a Weibull probability density function. A Genetic Algorithm (GA) is utilized to determine the shaping and scale parameters of the distribution, which are employed to determine the most probable wind speed at a certain position. The system uses this information to characterize a wind shear or a discrete gust and also utilizes a Gaussian Process regression to characterize continuous gusts. The knowledge of the wind features is crucial for computing energy-efficient trajectories with low cost and payload. Therefore, the system provides a solution that does not require any additional sensors. The system architecture presents a modular decentralized approach, in which the main parts of the system are separated in modules and the exchange of information is managed by a communication handler to enhance upgradeability and maintainability. Validation is done providing preliminary results of both simulations and Software-In-The-Loop testing. Telemetry data collected from real flights, performed in the Seville Metropolitan Area in Andalusia (Spain), was used for testing. Results show that wind estimation and predictions can be calculated at 1 and a wind map can be updated at 0.4 . Predictions show a convergence time with a 95% confidence interval of approximately 30 .

Predictability of wind‐induced sea surface transport in coastal areas

AbstractIn this work we investigated the predictability of the wind‐induced sea surface transport in coastal areas. The wind fields predicted by two state‐of‐the‐art meteorological models, namely ECMWF and SKIRON, were used as forcing for a hydrodynamic and particle‐tracking model applied to reproduce a set of observed drifters trajectories in a coastal area of the Mediterranean Sea. A set of anemometric data derived by in situ measurements were also adopted as model forcing to reproduce the observed drifter paths. This approach provided a baseline that was used as a reference for evaluating the effects of the predicted wind accuracy on the numerical model solution. The accuracy of the simulation results obtained using, as model forcing, the observed wind data was fair and suitable for most of the operational oceanographic purposes. It decreased when using the wind data predicted by the two meteorological models. In particular, the results obtained using ECMWF data were about 3 times more accurate than the ones obtained using SKIRON ones. The uncertainties were strongly dependent on the range of observed wind speed classes with a different behavior depending on the type of adopted wind data. Finally, the amplification of the errors in predicting the sea surface transport generated by the inaccuracies of the predicted wind fields was quantified.

A copula-based approach for the estimation of wave height records through spatial correlation

Information on the wave climate at a particular location is essential in many areas of coastal engineering from the design of coastal structures to flood risk analysis. It is most commonly obtained either by direct measurements or hindcast from meteorological data. The extended deployment of a wave buoy to directly measure wave conditions and the application of wave transformation models used in hindcasting, including public domain models such as Wavewatch and SWAN, are both expensive. The accuracy of the results given by the latter are also highly sensitive to the quality of the wind data used as input. In this paper a new copula-based approach for predicting the wave height at a given location by exploiting the spatial dependence of the wave height at nearby locations is proposed. By working directly with wave heights, it provides an alternative method to hindcasting from observed or predicted wind fields when limited information on the wave climate at a particular location is available. It is shown to provide predictions of a comparable accuracy to those given by existing numerical models.

A wind power forecasting system based on the weather research and forecasting model and Kalman filtering over a wind-farm in Japan

The rapid development of wind energy in Japan and the associated high uncertainties and fluctuations in power generation present a big challenge for both wind power generators and electric grids. Accurate and reliable wind power predictions are necessary to optimize the integration of wind power into existing electrical systems. In this study, a hybrid forecasting system of wind power generation was developed by integrating the Kalman filter (KF) with the high resolution Weather Research and Forecasting (WRF) model as well as an empirical formula of wind power output (power curve). The system has been validated with observations including wind speed and power output over a six-month period for 15 turbine sites at a wind farm in Awaji-island, Japan. The results show that the tuned WRF model is able to provide hub-height wind speed prediction for the target area with reliability to some extent. The predicted wind field can be substantially improved by the Kalman filter as a post-processing procedure. The 15-turbine averaged improvements of mean error, root mean square error, and correlation coefficient are 97%, 22%, and 10%, respectively. Meanwhile, the Kalman filter also demonstrates a promising capability of reducing the uncertainties in the power curve model. Systematic validations regarding both wind speed and power output were carried out against the observations for the target wind farm, which show that the hybrid power forecasting system presented in this paper can be an effective and practical tool for short-term predictions of wind speed and power output in Japan area.

Evaluation of modeled wind field for dispersion modeling

This study compares MM5 and WRF modeled upper air and surface wind speed and direction with observations from two standard meteorological stations locat;ed in areas characterized by either flat or complex terrain. Additionally, we evaluate the boundary layer height calculated by AERMET VIEW Upper Estimator. The upper air wind speed predictions of MM5 (but not of WRF) met all the acceptance criteria. In contrast, WRF surface wind predictions were mostly in better agreement with the observations than those of MM5, with a clear advantage for the 12km grid resolution over the 3km grid resolution. Modeled wind fields over complex terrain were less accurate than over flat terrain. Based on these results we conclude that in the absence of measured on-site meteorological data, WRF surface wind field predictions are expected to provide more reliable pollutant dispersion estimations and to propagate the estimation uncertainties to a lesser extent than MM5 surface wind field predictions, in particular for flat terrain scenarios.

Review on the Application of Numerical Weather Prediction in the Simulation Research of Atmospheric Dispersion

The spatial and temporal variations of wind field and the atmospheric turbulence characteristics are important factors that affect the migration and dispersion of local atmospheric pollutants. Since the numerical meteorological forecasting system with high resolution is the foundation of atmospheric dispersion simulation, more and more attention has been drawn to the application of numerical weather prediction systems in wind field prediction and atmospheric simulation. This paper reviewed the widespread application of numerical weather prediction systems in wind field prediction and atmospheric simulation with the focus on the mesoscale weather forecasting system with high resolution, for instance WRF and MM5, as well as the requirement for numerical weather prediction in the simulation research of wind field prediction and atmospheric dispersion.

Wind Power Potential in Interior Alaska from a Micrometeorological Perspective

The wind power potential in Interior Alaska is evaluated from a micrometeorological perspective. Based on the local balance equation of momentum and the equation of continuity we derive the local balance equation of kinetic energy for macroscopic and turbulent systems, and in a further step, Bernoulli’s equation and integral equations that customarily serve as the key equations in momentum theory and blade-element analysis, where the Lanchester-Betz-Joukowsky limit, Glauert’s optimum actuator disk, and the results of the blade-element analysis by Okulov and Sorensen are exemplarily illustrated. The wind power potential at three different sites in Interior Alaska (Delta Junction, Eva Creek, and Poker Flat) is assessed by considering the results of wind field predictions for the winter period from October 1, 2008, to April 1, 2009 provided by the Weather Research and Forecasting (WRF) model to avoid time-consuming and expensive tall-tower observations in Interior Alaska which is characterized by a relatively low degree of infrastructure outside of the city of Fairbanks. To predict the average power output we use the Weibull distributions derived from the predicted wind fields for these three different sites and the power curves of five different propeller-type wind turbines with rated powers ranging from 2 MW to 2.5 MW. These power curves are represented by general logistic functions. The predicted power capacity for the Eva Creek site is compared with that of the Eva Creek wind farm established in 2012. The results of our predictions for the winter period 2008/2009 are nearly 20 percent lower than those of the Eva Creek wind farm for the period from January to September 2013.

Effect of different meteorological fields on the regional air quality modelling over Pearl River Delta, China

This study evaluates the performances of three Community Multiscale Air Quality (CMAQ) model v5.0 simulations that utilise meteorological input data from the 5th-generation Mesoscale Model (MM5), the Weather Research and Forecasting (WRF) model and WRF with Four-Dimensional Data Assimilation (WRF/FDDA). Three sets of CMAQ model simulations were performed for a high air pollution episode from October 9 to October 12, 2004 over the Pearl River Delta (PRD) region, which was caused by a high-pressure system. The observations at Guangzhou urban site (113.26°E, 23.13°N) were used to evaluate the results of meteorological models and air quality models. In all three experiments, the simulated pollutants were distributed mainly in the western part of PRD, but there was still a difference of horizontal distribution among them. The predicted wind fields, relative humidity and planetary boundary layer (PBL) height in meteorological simulations were the major factors contributing to this difference.