Search

In the wind turbine wake control research, the analytical wake model does not consider the influence of direct control parameters on the wind turbine wake flow field, and its prediction accuracy is by no means satisfying. The numerical simulation method can accurately predict the wake effect, but its low computational efficiency renders it unable to be used in the iterative control optimization study. In this paper, a new wake model coupled with the direct control parameters (tip speed ratio and pitch angle) of a single wind turbine is built based on the machine learning algorithm for which the widely applied Artificial Neural Network (ANN) is applied for instance. By combining the ANN wake model with different wake superposition models, the best combinatorial model for quantitative evaluation of multiple wake interferences is achieved, which not only has great accuracy but also ensures high calculation efficiency. On top of the established combinatorial wake model, three in-line wind turbines are investigated for assessing the effectiveness of wake control optimization with respect to the traditional greedy control. The results show that by optimizing the control parameters (tip speed ratio and pitch angle) of wind turbines, the total power of the three wind turbine units is increased by 1.15~3.48% depending on the incoming wind speeds and distances apart between wind turbines. The power variation of each wind turbine shows that the increase in total power is achieved by the decreased power of the first wind turbine and the increased power of the second and third wind turbines. The research verifies the effectiveness of adopting optimized wind turbine wake control on the total wind farm power improvement numerically. [ABSTRACT FROM AUTHOR]

In this paper, a 3D wake model considering both axial and radial wind speed variations along the incoming wind direction, and the non-flat topography effect on the wind flow, is developed for the layout optimization of a real onshore wind farm. The effectiveness of two methods (i.e., the discretization method that divides the wind scenario into small intervals and the Monte Carlo method which randomly generates the discrete wind speed samples), for evaluating the overall wind farm power production under the wind speed variation of Weibull distribution is investigated for the comparative study. It is found that the Monte Carlo power evaluation method achieves a better outcome than the traditional discretization method, with more total power output and less computational cost. Through the layout optimization with a total of 15 wind turbines installed, the individual wind turbine yields more than 533 kW power out of 536 kW theoretical wake-free power. As the installed wind turbine number increases, the maximum discrepancy of the actual wind turbine power output with respect to the theoretical power increases from 3 kW (with 15 wind turbines) to 6 kW (with 20 wind turbines). Through the comparative study of different wind rotation scenarios, it is found that the maximum discrepancy of individual actual wind turbine power outputs is 8 kW and 13 kW for a rotational angle of 30 ° and 60 ° , respectively. Under the scenario of 90 ° wind rotation scenario, the maximum individual power output deficit with 20 installed wind turbines is around 20 kW and the discrepancy of the total power output by comparing to the baseline wind model is maximally 1% proving the robustness of the optimization results with respect to the wind scenario variation. [ABSTRACT FROM AUTHOR]

• Classical greedy, optimization-based, and reinforcement learning (RL) control policies are compared for multiple offshore turbines. • Deep deterministic policy gradient (DDPG) algorithm is adopted to train the RL yaw control agent. • Superiority of RL over greedy control, particularly below rated wind speeds, is validated. • RL achieves a remarkable 32.63 % more cumulative power generation than optimized control at lower wind speeds. • Model-free adaptation by RL substantially enhances control robustness across a spectrum of changing wind scenarios. Wind farm wake interactions are critical determinants of overall power generation efficiency. To address these challenges, coordinated yaw control of turbines has emerged as a highly effective strategy. While conventional approaches have been widely adopted, the application of contemporary machine learning techniques, specifically reinforcement learning (RL), holds great promise for optimizing wind farm control performance. Considering the scarcity of comparative analyses for yaw control approaches, this study implements and evaluates classical greedy, optimization-based, and RL policies for in-line multiple wind turbine under various wind scenario by an experimentally validated analytical wake model. The results unambiguously establish the superiority of RL over greedy control, particularly below rated wind speeds, as RL optimizes yaw trajectories to maximize total power capture. Furthermore, the RL-controlled policy operates without being hampered by iterative modeling errors, leading to a higher cumulative power generation compared to the optimized control scheme during the control process. At lower wind speeds (5 m/s), it achieves a remarkable 32.63 % improvement over the optimized strategy. As the wind speed increases, the advantages of RL control gradually diminish. In consequence, the model-free adaptation offered by RL control substantially bolsters robustness across a spectrum of changing wind scenarios, facilitating seamless transitions between wake steering and alignment in response to evolving wake physics. This analysis underscores the significant advantages of data-driven RL for wind farm yaw control when compared to traditional methods. Its adaptive nature empowers the optimization of total power production across a range of diverse operating regimes, all without the need for an explicit model representation. [ABSTRACT FROM AUTHOR]

The existing decentralized wind farm control incorporating the wind turbine wake interaction has almost all concentrated on the condition of fixed wind speed/direction without considering the variability of wind in nature. Meanwhile, most of the current wake models cannot meet the requirement for wind turbine control optimization research with the high demand of wake calculation speed and accuracy. In this paper, a novel decentralized control strategy, named the wind-interval-based (WIB) control which adopts the uniform operation among the same interval of variable wind speeds/directions, is proposed for the control optimization study of in-line two scaling wind turbines for demonstration. To prove the effectiveness of the new control mechanism, the ideal instantaneous control is introduced for the comparative study. At the same time, a wake model incorporating the two directly controllable parameters (i.e., the tip speed ratio λ and pitch angle γ) is established based on artificial neural network (ANN). The comparative results show that the total power output applying the instantaneous control and the new WIB control mechanisms are increased by 0.1%–4.1% and 0.45%–3.9% depending on the tested wind scenarios, respectively. By comparing the optimized power output with the two controls, it is found that the error between them is generally lower than 3%, while the proposed WIB control reduces the operational difficulty to a large extent facilitating its application to the real wind turbine operation in reality. In summary, this paper shows that the new proposed WIB control not only reduces the difficulties of the wind turbine control mechanism, but maintains the control effectiveness by achieving a comparable total power output with respect to the traditional instantaneous control, which is of great significance to the wind farm developer. [ABSTRACT FROM AUTHOR]

A comprehensive understanding of wind turbine wake characteristics is vital, particularly in the context of expanding large offshore wind farms. Existing wake measurement techniques provide only spatially sparse wake measurement data, limiting their utility in precise wind turbine design and control. This paper introduces a data-driven approach that combines proper orthogonal decomposition (POD) with machine learning (ML) techniques, designing a Reduced Order Modeling-based Wake Flow Estimation (ROM-WFE) framework. This framework establishes a nonlinear mapping between sensor measurements and low-dimensional POD coefficients. Two distinct sensor placements, wall-mounted and wake-mounted, are investigated for real measurement scenarios. The results highlight the effectiveness of the proposed wake flow estimation method in reconstructing a complete flow field from exceptionally sparse sensor data, with both wall-mounted and wake-mounted strategies, exhibiting promising results with maximum relative errors of 6.37% and 4.51%, respectively. From the reliability assessments considering various configurations of POD modes and sensor numbers, the ROM-WFE framework demonstrates its capability to estimate wake flow effectively, offering a cost-effective tool for practical applications. Furthermore, the framework maintains accuracy even with high-noise and low-frequency data, demonstrating robustness and generalization. This method significantly contributes to wind turbine wake prediction controller design, promising accurate and robust wake flow field estimation, potentially revolutionizing active wake control and enhancing wind farm operational efficiency. • Combining POD and ML techniques to establish a Reduced Order Modeling-based Wake Flow Estimation (ROM-WFE) framework. • Exploring the effectiveness of ROM-WFE in wall- and wake-mounted sensor placement strategies. • Utilizing fewer than three sensors enhances practicality for real-world applications and improves wind farm efficiency. • Demonstrating resilience and adaptability, maintaining accuracy even with high-noise, low-frequency data. [ABSTRACT FROM AUTHOR]

Real-time acquisition of dynamic wake field information has garnered substantial attention in the wind farm industry, as it provides a crucial data source for intelligent wind farm monitoring and control. However, the existing wind measurement technologies, such as light detection and ranging (LiDAR), are limited to sparse data point measurements. This paper explores the utilization of a Physics-Informed Neural Network (PINN) to reconstruct wind turbine wake dynamics, specifically focusing on the influence of active wind turbine yaw operation on wake evolution. The methodology involves creating a tailored loss function that combines sparse wake measurement data with the Navier-Stokes (NS) equations. More precisely, the neural network incorporates the NS equations as constraints to guide the prediction of physical quantities in the output, including downwind velocity, crosswind velocity, and pressure. Taking the dynamic wake during yawing as a case study, the proposed method showcases remarkable universality and robustness across diverse scenarios involving varying scanning angle intervals, measurement point spacings, frequencies, and noise levels. It successfully captures the dynamic trends in wake evolution during yawing and accurately forecasts the wake trajectory and deflection. Even when tested with actual wake measurement data, the method can still effectively reconstruct the flow field, indicating significant potential for the real wind farm yaw control. • Dynamic spatiotemporal wake reconstruction of a utility-scale yawed wind turbine is carried out in this paper. • A novel approach combining physics-informed neural network with sparse LiDAR measurement is proposed. • The neural network maps spatiotemporal coordinates [ t , x , y ] to flow physical quantities [ u , v , p ] integrated with NS equations. • Various cases with different LiDAR measurement parameters are investigated for sensitivity and robustness analysis. • The new approach shows great effectiveness in reconstructing dynamic wake behavior of trajectory and deflection changes. [ABSTRACT FROM AUTHOR]

Featured Application: The comparative results of the effectiveness of different wind turbine placement methods will facilitate the application of a more advantageous method to be used for the wind farm design, and hence improve the cost effectiveness of wind power exploitation. For the exploitation of wind energy, planning/designing a wind farm plays a crucial role in the development of wind farm project, which must be implemented at an early stage, and has a vast influence on the stages of operation and control for wind farm development. As a step of the wind farm planning/designing, optimizing the wind turbine placements is an effective tool in increasing the power production of a wind farm leading to an increased financial return. In this paper, the optimization of an offshore wind farm with an irregular boundary is carried out to investigate the effectiveness of grid and coordinate wind farm design methods. In the study of the grid method, the effect of grid density on the layout optimization results is explored with 20 × 30 and 40 × 60 grid cells, and the means of coping with the irregular wind farm boundary using different wind farm design methods are developed in this paper. The results show that, depending on the number of installed wind turbines, a power output increase from 1% to 1.5% is achieved by increasing the grid density from 20 × 30 to 40 × 60. However, the computational time is more than doubled, rising from 23 h to 47 h with 40 wind turbines being optimized from the coarse grid cells to the densified grid cells. In comparison, the coordinate method is the best option for achieving the largest power increase of 1.5% to 2% (relative to the coarse 20 × 30 grid method), while the least computational time (21 h with 40 wind turbines optimized) is spent. [ABSTRACT FROM AUTHOR]

Optimal design of wind turbine placement in a wind farm is one of the most effective tools to reduce wake power losses by alleviating the wake effect in the wind farm. In comparison to the discrete grid-based wind farm design method, the continuous coordinate method has the property of continuously varying the placement of wind turbines, and hence, is far more capable of obtaining the global optimum solutions. In this paper, the coordinate method was applied to optimize the layout of a real offshore wind farm for both simplified and realistic wind conditions. A new analytical wake model (Jensen-Gaussian model) taking into account the wake velocity variation in the radial direction was employed for the optimization study. The means of handling the irregular real wind farm boundary were proposed to guarantee that the optimized wind turbine positions are feasible within the wind farm boundary, and the discretization method was applied for the evaluation of wind farm power output under Weibull distribution. By investigating the wind farm layout optimization under different wind conditions, it showed that the total wind farm power output increased linearly with an increasing number of wind turbines. Under some particular wind conditions (e.g., constant wind speed and wind direction, and Weibull distribution), almost the same power losses were obtained under the wake effect of some adjacent wind turbine numbers. A common feature of the wind turbine placements regardless of the wind conditions was that they were distributed along the wind farm boundary as much as possible in order to alleviate the wake effect. [ABSTRACT FROM AUTHOR]

Complete and clear global wind turbine wake data is very important for the study of wind turbine wake characteristics in increasingly large offshore wind farms. Existing wake measurement techniques can only obtain local high-resolution (HR) wake flow field, or sacrifice accuracy to obtain larger measurement area, which is insufficient for accurate modeling of wake effect. To overcome this challenge, this paper proposes a novel super-resolution (SR) reconstruction approach that can reconstruct the global HR wake flow field from low-resolution (LR) wake flow field measurement data effectively. The proposed approach utilizes a deep learning framework called down-sampled skip-connection and multi-scale network. The performance of the SR approach is evaluated by enhancing the resolution of the wake flow field at different scale factors, and its potential application is demonstrated by assessing the prediction accuracy of three typical wake models. The results indicate that the resolution of the global wind turbine wake can be improved by 16 times using the SR model, and the reconstructed global SR wake flow fields are consistent with the ground truth in terms of both the spatial distribution and the temporal variation. By comparing the prediction results of three different wake models with the LR or SR wake data, it is shown that the SR flow reconstruction method can be applied to more accurately evaluate the wake model prediction performance, which has the potential to improve wake models. Overall, this study presents an innovative solution to the problem of incomplete and inaccurate wake flow measurement in the wind energy industry, which could reduce the workload of experimental measurements and the cost burden of accurate measuring equipment for engineering applications. • A novel deep learning method is proposed to facilitate high resolution wake flow measurement of offshore wind turbine. • The deep learning framework adopts down-sampled skip-connection and multi-scale network. • Super-resolution flow field is achieved by reconstructing global high-resolution wake from local low-resolution wake. • Resolution of reconstructed wake flow attains 16 times improvement with great accuracy in spatiotemporal distribution. • Super-resolution reconstruction framework has been successfully applied for better assessing the prediction accuracy of traditional wake models. [ABSTRACT FROM AUTHOR]

Extensive power losses of wind farm have been witnessed due to the wake interactions between wind turbines. By applying analytical wake models which describe the wind speed deficits in the wake quantitatively, the power losses can be regained to a large extent through wind farm layout optimization, and this has been extensively reported in literature. Nevertheless, the effectiveness of the analytical wake models in predicting the wind farm power production have rarely been studied and compared for wind farm with both constant and variable wind turbine hub heights. In this study, the effectiveness of three different analytical wake models (PARK model, Larsen model and B-P model) is thoroughly compared over a wide range of wake properties. After the validation with the observation data from offshore wind farm, CFD simulations are used to verify the effectiveness of the analytical wake models for an onshore wind farm. The results show that when using the PARK model the surface roughness value ( z 0 ) must be carefully tuned to achieve good performance in predicting the wind farm power production. For the other two analytical wake models, their effectiveness varies depending on the situation of wind farm (offshore or onshore) and the wind turbine hub heights (constant or variable). It was found that the results of B-P model agree well with the CFD simulations for offshore wind farm, but not for the onshore wind farm. The Larsen model is more accurate for the wind farm with variable wind turbine hub heights than those with constant wind turbine hub height. [ABSTRACT FROM AUTHOR]

Recently wind energy has become one of the most important alternative energy sources and is growing at a rapid rate because of its renewability and abundancy. For the clustered wind turbines in a wind farm, significant wind power losses have been observed due to wake interactions of the air flow induced by the upstream turbines to the downstream turbines. One approach to reduce power losses caused by the wake interactions is through the optimization of wind farm layout, which determine the wind turbine positions and control strategy, which determine the wind turbine operations. In this paper, a new approach named simultaneous layout plus control optimization is developed. The effectiveness is studied by comparison to two other approaches (layout optimization and control optimization). The results of different optimizations, using both grid based and unrestricted coordinate wind farm design methods, are compared for both ideal and realistic wind conditions. Even though the simultaneous layout plus control optimization is theoretically superior to the others, it is prone to the local minima. Through the parametric study of crossover and mutation probabilities of the optimization algorithm, the results of the approach are generally satisfactory. For both simple and realistic wind conditions, the wind farm with the optimized control strategy yield 1–3 kW more power per turbine than that with the self-optimum control strategy, and the unrestricted coordinate method yield 1–2 kW more power per turbine than the grid based method. [ABSTRACT FROM AUTHOR]

Wind farm layout optimization results depend on the optimization objectives, such as power output and variance. This paper investigates an alternative strategy for wind farm layout optimization by trading off the mean wind power output and power variance. Two optimization schemes, the weighted optimization and confidence interval optimization are compared in term of their performances on trading off energy-variance. For the weighted optimization, the objective function weight value α varies from 0 to 1 (implying the optimization objective shifts its weight from the power variance to the power output), while for the confidence interval (CI) optimization, either the lower or the upper limit of power output CI is maximized/minimized. It is found that the CI maximization achieves a trade-off of mean power output and power variance similar to the weighted optimization with α ≥ 0.6 , and the same individual power output range (192 kW–207 kW) is obtained with staggered placements of wind turbines. The CI minimization obtains a trade-off of average power output and power variance close to the weighted optimization with α ≤ 0.4 , and the optimal wind turbine locations are aligned. The advantage of CI optimization lies on its capability of predicting the power output uncertainty. • Wind farm layout optimization trading-off the mean and the variance of the power output is conducted. • Two optimization schemes (weighted and confidence interval optimization) are compared. • CI maximization achieves a trade-off similar to the weighted optimization with α ≥ 0.6. • CI minimization obtains a trade-off close to the weighted optimization with α ≤ 0.4. • The advantage of CI optimization lies on its capability of predicting the power output uncertainty. [ABSTRACT FROM AUTHOR]

In this paper, a real wind farm layout optimization is carried out by applying the novel optimized wind farm control strategy (coordinating wind turbine operations by setting different axial induction values) and multiple wind turbine hub height selections. The unrestricted coordinate method (using Cartesian coordinates to determine wind turbine positions) is applied to study the effectiveness of different wind farm control strategies and wind turbine hub heights on the wind farm optimization. Means of handling the irregular boundary constraints and calculating the wind speed over non-flat terrain at different heights are proposed for the real wind farm. The results show that the optimized control strategy can always yield better results than the self-optimum control strategy, achieving a smaller cost of energy production and a larger wind farm efficiency. Quantitatively, the optimized control strategy yields approximately 9 kW more power per turbine than the self-optimum control strategy and reduces the cost of energy by 0.08 million dollars per megawatt with 39 wind turbines installed. The application of different hub height turbines facilitates to place wind turbines more flexibly achieving better optimization results than that with constant hub height turbines. [ABSTRACT FROM AUTHOR]

Abstract This paper aims to systematically study the wind farm optimization with the continuous selection of wind turbine placement (using Cartesian coordinates) and wind turbine hub height (restrained among a predefined range). Two case studies are performed. The first case involves an ideal two-dimensional (i.e., flat terrain) wind farm, and the other is a three-dimensional wind farm with real terrain altitudes. The schemes of simultaneously optimizing the wind farm layout and wind turbine hub heights applying the simplified and augmented PARK wake model are established for the ideal and real wind farm cases, respectively. The results show that applying different wind turbine hub heights for the wind farm layout optimization yields significant improvement: up to a 0.2 MW increase in total power and a 2% increase of the wind farm efficiency for the ideal wind farm. However, for the real wind farm the effectiveness of applying different wind turbine hub heights varies depending on the number of turbines installed. With less number of turbines installed, the impact of varying hub heights is small. However, significant improvements can be achieved as the number of turbines increases. With 39 wind turbines, the wind farm cost of energy can be reduced by $15000 per megawatt and the wind farm efficiency can increase by up to 0.2%. Given the nameplate capacity and the lifespan of wind farm project, the resulting effect on total energy production can be significant and thus improve the competitiveness of wind power exploitation. Highlights • A combined optimization of wind turbine positions and hub heights is conducted with continuous variation. • A computationally-efficient method considering wake effect over non-flat terrain is applied. • Ideal wind farm yields 0.2 MW more power and 2% increase in efficiency with maximum hub height difference of 40 m. • Real wind farm reduces cost of energy by $15000 per megawatt with maximum hub height difference of 40 m. [ABSTRACT FROM AUTHOR]