Search

Yaw misalignment can make a wake steer, which is an effective method to increase the power of wind farms but it also increases the fatigue load of the turbines. In this paper, the combination of yaw offset and pitch control (CYMP) is studied to analyse the potential mitigation of wake, focusing on the wind velocity and turbulence of the wake distribution, power increment, and fatigue load reduction. The simulation case study shows that the method of CYMP can reduce the fatigue load by 10.29% and increase the total power by 1.7% compared with only wake steering in FAST.Fram. The Collaborative MPC (CoMPC) method based on CYMP is proposed to the real-time wake control in this research, which can increase power by more than 2% and reduce thrust by more than 4% than greedy control under 10 m/s turbulent wind. [ABSTRACT FROM AUTHOR]

In order to increase the economic benefits of offshore wind farms, reducing the wake effect on the power and fatigue load of wind farms is one of the fundamental ways. In this study, the optimal method of combing yaw offset and pitch control (CYOPC) is put forward for wind farm power and fatigue loads below rated wind speed. To quantify potential power increase and fatigue loads decrease, three turbines in China’s Binhai offshore wind farm are investigated using FAST.Farm. The simulation studies are carried out in region 2 of turbine operation and compared with under yaw control only. Results indicate that the CYOPC method has the potential to increase power and reduce fatigue load.

Yaw misalignment can make a wake steer, which is an effective method to increase the power of wind farms but it also increases the fatigue load of the turbines. In this paper, the combination of yaw offset and pitch control (CYMP) is studied to analyse the potential mitigation of wake, focusing on the wind velocity and turbulence of the wake distribution, power increment, and fatigue load reduction. The simulation case study shows that the method of CYMP can reduce the fatigue load by 10.29% and increase the total power by 1.7% compared with only wake steering in FAST.Fram. The Collaborative MPC (CoMPC) method based on CYMP is proposed to the real-time wake control in this research, which can increase power by more than 2% and reduce thrust by more than 4% than greedy control under 10 m/s turbulent wind.

This work proposes a novel data-driven model capable of providing accurate predictions for the power generation of all wind turbines in wind farms of arbitrary layout, yaw angle configurations and wind conditions. The proposed model functions by encoding a wind farm into a fully connected graph and processing the graph representation through a graph transformer. The resultant graph transformer surrogate demonstrates robust generalisation capabilities and effectively uncovers latent structural patterns embedded within the graph representation of wind farms. The versatility of the proposed approach extends to the optimisation of yaw angle configurations through the application of genetic algorithms. This evolutionary optimisation strategy facilitated by the graph transformer surrogate achieves prediction accuracy levels comparable to industrially standard wind farm simulation tools, with a relative accuracy of more than 99% in identifying optimal yaw angle configurations of previously unseen wind farm layouts. An additional advantage lies in the significant reduction in computational costs, positioning the proposed methodology as a compelling tool for efficient and accurate wind farm optimisation. • A novel wind farm scale model is developed based on graph transformers. • Graph transformers can identify wake interactions within wind farms and accurately predict wind farm power. • The developed model generalises to diverse wind farm layouts and yaw angle configurations. • The proposed model achieves more than 99% accuracy when used as a surrogate for PyWake in yaw angle optimisation. [ABSTRACT FROM AUTHOR]

A new wind farm during its development phase requires a technical evaluation of its annual power prediction and noise issue in the area in and around the wind farm. In this paper, for the first time, an advanced numerical method for wind farm assessment is developed, which consists of a Reynolds averaged Navier-Stokes - Actuator Disc model for the flow modelling, a semi-engineering model for the noise source modelling, and a parabolic wave equation model for the sound propagation modelling. The developed method can evaluate both annual energy production of wind farm and noise emission at receivers nearby. The wind farm considered in this study is located in a typical mountainous area. The energy production of the wind turbines is simulated and compared with measured data. The flow simulations over the complex terrain are performed using the in-house developed Navier-Stokes solver. A wind farm noise map is created by solving the parabolic wave equation. The obtained flow results are the inputs to the parabolic wave equation solver for sound propagation. The numerical computations are performed on a standard high-performance computer cluster. The developed numerical method provides a reliable assessment method for wind farm about its energy efficiency and noise features. • The paper aimed at developing environmental friendly wind farm. • A method is developed to evaluate both AEP and noise emission of a wind farm. • A mountainous wind farm noise map is created. • It is found that flow and terrain undulation are the two key factors. [ABSTRACT FROM AUTHOR]

Machine learning is frequently applied in the wind energy industry to build statistical models of wind farm power production using atmospheric data as input. In the field of wind power forecasting, in particular, there has been substantial research into finding the best-performing learning algorithms that improve model predictions. Overlooked in the literature, however, is the influence of atmospheric turbulence and stability measurements in improving model predictions. It has been well-established through observations and physical models that these effects can have considerable influence on wind farm power production; yet consideration of these effects in statistical models is almost entirely absent from the literature. In this work, we examine the impact of atmospheric turbulence and stability inputs on statistical model predictions of wind farm power output. Hourly observations from a wind farm in the Pacific Northwest United States located in very complex terrain are used. Five common learning algorithms and nine atmospheric variables are considered, five of which represent some measure of turbulence or stability. We find a considerable improvement in hourly power predictions when some measure of turbulence or stability is included in the model. In particular, turbulent kinetic energy was found to be the most important variable apart from wind speed and more important than wind direction, pressure, and temperature. By contrast, the choice of learning algorithm is shown to be relatively less important in improving predictions. Based on this work, we recommend that turbulence and stability variables become standard inputs into statistical models of wind farm power production. • Turbulence and stability are almost never considered in wind plant ML models. • All turbulence and stability variable are statistically significant. • Turbulent kinetic energy is the most significant variable after wind speed. • Choice of variables is more important than choice of algorithm. [ABSTRACT FROM AUTHOR]

Wind turbine wake modelling is of crucial importance to accurate resource assessment, to layout optimisation, and to the operational control of wind farms. This work proposes a surrogate model for the representation of wind turbine wakes based on a state-of-the-art graph representation learning method termed a graph neural network. The proposed end-to-end deep learning model operates directly on unstructured meshes and has been validated against high-fidelity data, demonstrating its ability to rapidly make accurate 3D flow field predictions for various inlet conditions and turbine yaw angles. The specific graph neural network model employed here is shown to generalise well to unseen data and is less sensitive to over-smoothing compared to common graph neural networks. A case study based upon a real world wind farm further demonstrates the capability of the proposed approach to predict farm scale power generation. Moreover, the proposed graph neural network framework is flexible and highly generic and as formulated here can be applied to any steady state computational fluid dynamics simulations on unstructured meshes. • A novel wind turbine wake model is developed based on graph representation learning. • The developed model can generate 3D wake field predictions rapidly and accurately. • The graph neural network employed is directly compatible with unstructured meshes. • The proposed model is validated on a real-scale wind farm. [ABSTRACT FROM AUTHOR]

The power prediction is important for the safe and efficient operation of new wind farms with small data. However, there is a lack of research on improving the prediction accuracy. Here we propose a novel dual-meta pool model to realize multi-step prediction based on learning the data knowledge contained in relevant wind farms. By analysing the essence of neural network, we defined meta-data to express and extract the data knowledge. For meta-data classification, we designed a new unsupervised classification method based on the accuracy of data tail part. A convolutional neural network is used to learn the mapping relationship between meta-data and their labels. To make multi-step prediction, we proposed a novel meta-method which contains Hilbert spatial transformation, data extension and neural network. To verify the performance, eight comparison models are used to predict the last 30 data of two wind farms which only contain 96 data. The results show that the proposed dual-meta pool method has smaller prediction errors than other models, which average mean absolute errors are 13.33 and 2.42, respectively. • New dual-meta pool prediction model for small sample data. • New unsupervised classification method based on data tail part. • Mapping relationship construction by convolutional neural network. • New meta-method for multi-step prediction of meta-data. [ABSTRACT FROM AUTHOR]

Rising global temperature and environmental pollution as well as the demand for energy consumption have made finding new and affordable clean energy resources a serious challenge for governments. A possible solution could be renewable resources such as solar, wind or geothermal energies. Restructuring and deregulation have provided a competitive environment which makes analysis of these new energy sources necessary. Wind farms have been receiving more attention from governments because of their noticeable generation capability. The stochastic nature of the wind inflicts uncertainty on the output generation of wind farms which then causes some limitations for the participation of these farms in the electricity market. Thus, in this paper the effects of uncertainty in predicting the wind farm's power on locational marginal price in the market have been studied. According to the advantages and disadvantages of wind farm's power uncertainties, a procedure to maximize the social welfare is presented. The studies have been done on an 8-bus network for 24 h in a day-ahead electricity market. To do this, the farm power is predicted using Neural Network and Wavelet Transform and its uncertainties are calculated using the asymmetric Quantile Regression method. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a prediction model is proposed for wind farm power forecasting by combining the wavelet transform, chaotic time series and GM(1,1) method. The wavelet transform is used to decompose wind farm power into several detail parts associated with high frequencies and an approximate part associated with low frequencies. The characteristic of each high frequencies signal is identified, if it is chaotic time series then use weighted one-rank local-region method to predict it. If not, use GM(1,1) model to predict it. And the GM(1,1) model is also used to predict the approximate part of the low frequencies. In the end, the final forecasted result for wind farm power is obtained by summing the predicted results of all extracted high frequencies and the approximate part. According to the predicted results, the proposed method can improve the prediction accuracy of the wind farm power. [Copyright &y& Elsevier]

Wind turbine power curves are often used for monitoring the performance of wind turbines and play an important role in wind power forecasting. Various factors such as age of turbines, installed location, air density, wind direction and measurement errors cause non-homogeneity among observed data, which often influences the accuracy of fitted power curves. To overcome this problem, a hybrid estimation approach is proposed, based on weighted balanced loss functions that account for both estimation error and goodness of fit by shrinking estimates toward standardized target models. Two different weighting schemes are developed to incorporate the non-homogeneity of data in the estimation process. The proposed algorithm is compared with commonly used power curve estimation methods based on classical least squares, natural splines, and local linear smoothing methods. The performance of the original and proposed hybrid methods is evaluated using a historical data set collected from a wind farm located in Canada. Results show that hybrid methods can be used as an effective tool to improve the performance of existing power curve modeling approaches. Consequently, proposed methods can facilitate more robust monitoring the performance of wind turbines as well as wind power forecasting. • We propose a novel approach for wind turbine power curve modeling by developing a new optimality criterion based on a weighted balanced loss function. • We develop an innovative approach of weighing between model learned from data (using a goodness of fit criterion) and pre-existing robust target estimators of power curves. • Two new weighting schemes are developed to rectify the effect of heteroscedasticity of observed data. • Results can be used for more robust prediction of wind power as wind turbine performance monitoring. [ABSTRACT FROM AUTHOR]