Articles | Volume 6, issue 1
https://doi.org/10.5194/wes-6-111-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-6-111-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
18 Jan 2021
Research article |
| 18 Jan 2021
| 18 Jan 2021
Model-free estimation of available power using deep learning
Department of Wind Energy, DTU, Technical University of Denmark, Frederiksborgvej 399, 4000 Roskilde, Denmark
Albert Meseguer Urbán
Department of Wind Energy, DTU, Technical University of Denmark, Frederiksborgvej 399, 4000 Roskilde, Denmark
Jaime Liew
Department of Wind Energy, DTU, Technical University of Denmark, Frederiksborgvej 399, 4000 Roskilde, Denmark
Alan Wai Hou Lio
Department of Wind Energy, DTU, Technical University of Denmark, Frederiksborgvej 399, 4000 Roskilde, Denmark
Related authors
Jens Visbech, Tuhfe Göçmen, Özge Sinem Özçakmak, Alexander Meyer Forsting, Ásta Hannesdóttir, and Pierre-Elouan Réthoré
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2023-128, https://doi.org/10.5194/wes-2023-128, 2023
Revised manuscript under review for WES
Short summary
Short summary
Leading edge erosion (LEE) can impact wind turbine aerodynamics and wind farm efficiency. This study couples LEE prediction, aerodynamic loss modeling, and wind farm flow modeling to show that LEE's effects on wake dynamics can affect overall energy production. Without preventive initiatives, the effects of LEE increase over time, resulting in significant annual energy production (AEP) loss.
Jaime Liew, Tuhfe Göçmen, Alan W. H. Lio, and Gunner Chr. Larsen
Wind Energ. Sci., 8, 1387–1402, https://doi.org/10.5194/wes-8-1387-2023, https://doi.org/10.5194/wes-8-1387-2023, 2023
Short summary
Short summary
We present recent research on dynamically modelling wind farm wakes and integrating these enhancements into the wind farm simulator, HAWC2Farm. The simulation methodology is showcased by recreating dynamic scenarios observed in the Lillgrund offshore wind farm. We successfully recreate scenarios with turning winds, turbine shutdown events, and wake deflection events. The research provides opportunities to better identify wake interactions in wind farms, allowing for more reliable designs.
Jens Visbech, Tuhfe Göçmen, Charlotte Bay Hasager, Hristo Shkalov, Morten Handberg, and Kristian Pagh Nielsen
Wind Energ. Sci., 8, 173–191, https://doi.org/10.5194/wes-8-173-2023, https://doi.org/10.5194/wes-8-173-2023, 2023
Short summary
Short summary
This paper presents a data-driven framework for modeling erosion damage based on real blade inspections and mesoscale weather data. The outcome of the framework is a machine-learning-based model that can predict and/or forecast leading-edge erosion damage based on weather data and user-specified wind turbine characteristics. The model output fits directly into the damage terminology used by the industry and can therefore support site-specific maintenance planning and scheduling of repairs.
Johan Meyers, Carlo Bottasso, Katherine Dykes, Paul Fleming, Pieter Gebraad, Gregor Giebel, Tuhfe Göçmen, and Jan-Willem van Wingerden
Wind Energ. Sci., 7, 2271–2306, https://doi.org/10.5194/wes-7-2271-2022, https://doi.org/10.5194/wes-7-2271-2022, 2022
Short summary
Short summary
We provide a comprehensive overview of the state of the art and the outstanding challenges in wind farm flow control, thus identifying the key research areas that could further enable commercial uptake and success. To this end, we have structured the discussion on challenges and opportunities into four main areas: (1) insight into control flow physics, (2) algorithms and AI, (3) validation and industry implementation, and (4) integrating control with system design
(co-design).
Konstanze Kölle, Tuhfe Göçmen, Irene Eguinoa, Leonardo Andrés Alcayaga Román, Maria Aparicio-Sanchez, Ju Feng, Johan Meyers, Vasilis Pettas, and Ishaan Sood
Wind Energ. Sci., 7, 2181–2200, https://doi.org/10.5194/wes-7-2181-2022, https://doi.org/10.5194/wes-7-2181-2022, 2022
Short summary
Short summary
The paper studies wind farm flow control (WFFC) in simulations with variable electricity prices. The results indicate that considering the electricity price in the operational strategy can be beneficial with respect to the gained income compared to focusing on the power gain only. Moreover, revenue maximization by balancing power production and structural load reduction is demonstrated at the example of a single wind turbine.
Tuhfe Göçmen, Filippo Campagnolo, Thomas Duc, Irene Eguinoa, Søren Juhl Andersen, Vlaho Petrović, Lejla Imširović, Robert Braunbehrens, Jaime Liew, Mads Baungaard, Maarten Paul van der Laan, Guowei Qian, Maria Aparicio-Sanchez, Rubén González-Lope, Vinit V. Dighe, Marcus Becker, Maarten J. van den Broek, Jan-Willem van Wingerden, Adam Stock, Matthew Cole, Renzo Ruisi, Ervin Bossanyi, Niklas Requate, Simon Strnad, Jonas Schmidt, Lukas Vollmer, Ishaan Sood, and Johan Meyers
Wind Energ. Sci., 7, 1791–1825, https://doi.org/10.5194/wes-7-1791-2022, https://doi.org/10.5194/wes-7-1791-2022, 2022
Short summary
Short summary
The FarmConners benchmark is the first of its kind to bring a wide variety of data sets, control settings, and model complexities for the (initial) assessment of wind farm flow control benefits. Here we present the first part of the benchmark results for three blind tests with large-scale rotors and 11 participating models in total, via direct power comparisons at the turbines as well as the observed or estimated power gain at the wind farm level under wake steering control strategy.
Paul Hulsman, Søren Juhl Andersen, and Tuhfe Göçmen
Wind Energ. Sci., 5, 309–329, https://doi.org/10.5194/wes-5-309-2020, https://doi.org/10.5194/wes-5-309-2020, 2020
Short summary
Short summary
We aim to develop fast and reliable surrogate models for yaw-based wind farm control. The surrogates, based on polynomial chaos expansion, are built using high-fidelity flow simulations combined with aeroelastic simulations of the turbine performance and loads. Optimization results performed using two Vestas V27 turbines in a row for a specific atmospheric condition suggest that a power gain of almost 3 % ± 1 % can be achieved at close spacing by yawing the upstream turbine more than 15°.
Thomas Duc, Olivier Coupiac, Nicolas Girard, Gregor Giebel, and Tuhfe Göçmen
Wind Energ. Sci., 4, 287–302, https://doi.org/10.5194/wes-4-287-2019, https://doi.org/10.5194/wes-4-287-2019, 2019
Short summary
Short summary
Wind turbine wake recovery is very sensitive to ambient atmospheric conditions. This paper presents a way of including a local turbulence intensity estimation from SCADA into the Jensen wake model to improve its accuracy. This new model procedure is used to optimize power production of an operating wind farm and shows that some gains can be expected even if uncertainties remain high. These optimized settings are to be implemented in a field test campaign in the scope of the SMARTEOLE project.
Jens Visbech, Tuhfe Göçmen, Özge Sinem Özçakmak, Alexander Meyer Forsting, Ásta Hannesdóttir, and Pierre-Elouan Réthoré
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2023-128, https://doi.org/10.5194/wes-2023-128, 2023
Revised manuscript under review for WES
Short summary
Short summary
Leading edge erosion (LEE) can impact wind turbine aerodynamics and wind farm efficiency. This study couples LEE prediction, aerodynamic loss modeling, and wind farm flow modeling to show that LEE's effects on wake dynamics can affect overall energy production. Without preventive initiatives, the effects of LEE increase over time, resulting in significant annual energy production (AEP) loss.
Jaime Liew, Tuhfe Göçmen, Alan W. H. Lio, and Gunner Chr. Larsen
Wind Energ. Sci., 8, 1387–1402, https://doi.org/10.5194/wes-8-1387-2023, https://doi.org/10.5194/wes-8-1387-2023, 2023
Short summary
Short summary
We present recent research on dynamically modelling wind farm wakes and integrating these enhancements into the wind farm simulator, HAWC2Farm. The simulation methodology is showcased by recreating dynamic scenarios observed in the Lillgrund offshore wind farm. We successfully recreate scenarios with turning winds, turbine shutdown events, and wake deflection events. The research provides opportunities to better identify wake interactions in wind farms, allowing for more reliable designs.
Jens Visbech, Tuhfe Göçmen, Charlotte Bay Hasager, Hristo Shkalov, Morten Handberg, and Kristian Pagh Nielsen
Wind Energ. Sci., 8, 173–191, https://doi.org/10.5194/wes-8-173-2023, https://doi.org/10.5194/wes-8-173-2023, 2023
Short summary
Short summary
This paper presents a data-driven framework for modeling erosion damage based on real blade inspections and mesoscale weather data. The outcome of the framework is a machine-learning-based model that can predict and/or forecast leading-edge erosion damage based on weather data and user-specified wind turbine characteristics. The model output fits directly into the damage terminology used by the industry and can therefore support site-specific maintenance planning and scheduling of repairs.
Johan Meyers, Carlo Bottasso, Katherine Dykes, Paul Fleming, Pieter Gebraad, Gregor Giebel, Tuhfe Göçmen, and Jan-Willem van Wingerden
Wind Energ. Sci., 7, 2271–2306, https://doi.org/10.5194/wes-7-2271-2022, https://doi.org/10.5194/wes-7-2271-2022, 2022
Short summary
Short summary
We provide a comprehensive overview of the state of the art and the outstanding challenges in wind farm flow control, thus identifying the key research areas that could further enable commercial uptake and success. To this end, we have structured the discussion on challenges and opportunities into four main areas: (1) insight into control flow physics, (2) algorithms and AI, (3) validation and industry implementation, and (4) integrating control with system design
(co-design).
Konstanze Kölle, Tuhfe Göçmen, Irene Eguinoa, Leonardo Andrés Alcayaga Román, Maria Aparicio-Sanchez, Ju Feng, Johan Meyers, Vasilis Pettas, and Ishaan Sood
Wind Energ. Sci., 7, 2181–2200, https://doi.org/10.5194/wes-7-2181-2022, https://doi.org/10.5194/wes-7-2181-2022, 2022
Short summary
Short summary
The paper studies wind farm flow control (WFFC) in simulations with variable electricity prices. The results indicate that considering the electricity price in the operational strategy can be beneficial with respect to the gained income compared to focusing on the power gain only. Moreover, revenue maximization by balancing power production and structural load reduction is demonstrated at the example of a single wind turbine.
Tuhfe Göçmen, Filippo Campagnolo, Thomas Duc, Irene Eguinoa, Søren Juhl Andersen, Vlaho Petrović, Lejla Imširović, Robert Braunbehrens, Jaime Liew, Mads Baungaard, Maarten Paul van der Laan, Guowei Qian, Maria Aparicio-Sanchez, Rubén González-Lope, Vinit V. Dighe, Marcus Becker, Maarten J. van den Broek, Jan-Willem van Wingerden, Adam Stock, Matthew Cole, Renzo Ruisi, Ervin Bossanyi, Niklas Requate, Simon Strnad, Jonas Schmidt, Lukas Vollmer, Ishaan Sood, and Johan Meyers
Wind Energ. Sci., 7, 1791–1825, https://doi.org/10.5194/wes-7-1791-2022, https://doi.org/10.5194/wes-7-1791-2022, 2022
Short summary
Short summary
The FarmConners benchmark is the first of its kind to bring a wide variety of data sets, control settings, and model complexities for the (initial) assessment of wind farm flow control benefits. Here we present the first part of the benchmark results for three blind tests with large-scale rotors and 11 participating models in total, via direct power comparisons at the turbines as well as the observed or estimated power gain at the wind farm level under wake steering control strategy.
Liang Dong, Wai Hou Lio, and Eric Simley
Wind Energ. Sci., 6, 1491–1500, https://doi.org/10.5194/wes-6-1491-2021, https://doi.org/10.5194/wes-6-1491-2021, 2021
Short summary
Short summary
This paper suggests that the impacts of different turbulence models should be considered as uncertainties while evaluating the benefits of lidar-assisted control (LAC) in wind turbine design. The value creation of LAC, evaluated using the Kaimal turbulence model, will be diminished if the Mann turbulence model is used instead. In particular, the difference in coherence is more significant for larger rotors.
Jaime Liew, Albert M. Urbán, and Søren Juhl Andersen
Wind Energ. Sci., 5, 427–437, https://doi.org/10.5194/wes-5-427-2020, https://doi.org/10.5194/wes-5-427-2020, 2020
Short summary
Short summary
In wind farms, the interaction between neighboring turbines can cause notable power losses. The focus of the paper is on how the combination of turbine yaw misalignment and wake effects influences the power loss in a wind turbine. The results of the paper show a more notable power loss due to turbine misalignment when turbines are closely spaced. The presented conclusions enable better predictions of a turbine's power production, which can assist the wind farm design process.
Paul Hulsman, Søren Juhl Andersen, and Tuhfe Göçmen
Wind Energ. Sci., 5, 309–329, https://doi.org/10.5194/wes-5-309-2020, https://doi.org/10.5194/wes-5-309-2020, 2020
Short summary
Short summary
We aim to develop fast and reliable surrogate models for yaw-based wind farm control. The surrogates, based on polynomial chaos expansion, are built using high-fidelity flow simulations combined with aeroelastic simulations of the turbine performance and loads. Optimization results performed using two Vestas V27 turbines in a row for a specific atmospheric condition suggest that a power gain of almost 3 % ± 1 % can be achieved at close spacing by yawing the upstream turbine more than 15°.
Thomas Duc, Olivier Coupiac, Nicolas Girard, Gregor Giebel, and Tuhfe Göçmen
Wind Energ. Sci., 4, 287–302, https://doi.org/10.5194/wes-4-287-2019, https://doi.org/10.5194/wes-4-287-2019, 2019
Short summary
Short summary
Wind turbine wake recovery is very sensitive to ambient atmospheric conditions. This paper presents a way of including a local turbulence intensity estimation from SCADA into the Jensen wake model to improve its accuracy. This new model procedure is used to optimize power production of an operating wind farm and shows that some gains can be expected even if uncertainties remain high. These optimized settings are to be implemented in a field test campaign in the scope of the SMARTEOLE project.
Related subject area
Control and system identification
Load reduction for wind turbines: an output-constrained, subspace predictive repetitive control approach
A reference open-source controller for fixed and floating offshore wind turbines
Experimental results of wake steering using fixed angles
Results from a wake-steering experiment at a commercial wind plant: investigating the wind speed dependence of wake-steering performance
Model-based design of a wave-feedforward control strategy in floating wind turbines
Active flap control with the trailing edge flap hinge moment as a sensor: using it to estimate local blade inflow conditions and to reduce extreme blade loads and deflections
Wind inflow observation from load harmonics: initial steps towards a field validation
Control-oriented model for secondary effects of wake steering
Condition monitoring of roller bearings using acoustic emission
Automatic controller tuning using a zeroth-order optimization algorithm
Integrated wind farm layout and control optimization
Full-scale deformation measurements of a wind turbine rotor in comparison with aeroelastic simulations
Optimal closed-loop wake steering – Part 1: Conventionally neutral atmospheric boundary layer conditions
Grid-forming control strategies for black start by offshore wind power plants
Wind tunnel testing of wake steering with dynamic wind direction changes
Continued results from a field campaign of wake steering applied at a commercial wind farm – Part 2
Real-time optimization of wind farms using modifier adaptation and machine learning
Field testing of a local wind inflow estimator and wake detector
Design and analysis of a wake steering controller with wind direction variability
Periodic dynamic induction control of wind farms: proving the potential in simulations and wind tunnel experiments
Uncertainty identification of blade-mounted lidar-based inflow wind speed measurements for robust feedback–feedforward control synthesis
Validation of a lookup-table approach to modeling turbine fatigue loads in wind farms under active wake control
Wind direction estimation using SCADA data with consensus-based optimization
Initial results from a field campaign of wake steering applied at a commercial wind farm – Part 1
An active power control approach for wake-induced load alleviation in a fully developed wind farm boundary layer
Robust active wake control in consideration of wind direction variability and uncertainty
Automatic detection and correction of pitch misalignment in wind turbine rotors
Online model calibration for a simplified LES model in pursuit of real-time closed-loop wind farm control
Control design, implementation, and evaluation for an in-field 500 kW wind turbine with a fixed-displacement hydraulic drivetrain
Wind tunnel study on power output and yaw moments for two yaw-controlled model wind turbines
Towards practical dynamic induction control of wind farms: analysis of optimally controlled wind-farm boundary layers and sinusoidal induction control of first-row turbines
Determination of optimal wind turbine alignment into the wind and detection of alignment changes with SCADA data
System identification, fuzzy control and simulation of a kite power system with fixed tether length
A simulation study demonstrating the importance of large-scale trailing vortices in wake steering
Aero-elastic wind turbine design with active flaps for AEP maximization
Wind farms providing secondary frequency regulation: evaluating the performance of model-based receding horizon control
Field test of wake steering at an offshore wind farm
Iterative feedback tuning of wind turbine controllers
Articulated blade tip devices for load alleviation on wind turbines
Wind tunnel tests with combined pitch and free-floating flap control: data-driven iterative feedforward controller tuning
Periodic stability analysis of wind turbines operating in turbulent wind conditions
Basic controller tuning for large offshore wind turbines
Yichao Liu, Riccardo Ferrari, and Jan-Willem van Wingerden
Wind Energ. Sci., 7, 523–537, https://doi.org/10.5194/wes-7-523-2022, https://doi.org/10.5194/wes-7-523-2022, 2022
Short summary
Short summary
The objective of the paper is to develop a data-driven output-constrained individual pitch control approach, which will not only mitigate the blade loads but also reduce the pitch activities. This is achieved by only reducing the blade loads violating a user-defined bound, which leads to an economically viable load control strategy. The proposed control strategy shows promising results of load reduction in the wake-rotor overlapping and turbulent sheared wind conditions.
Nikhar J. Abbas, Daniel S. Zalkind, Lucy Pao, and Alan Wright
Wind Energ. Sci., 7, 53–73, https://doi.org/10.5194/wes-7-53-2022, https://doi.org/10.5194/wes-7-53-2022, 2022
Short summary
Short summary
The publication of the Reference Open-Source Controller (ROSCO) provides a controller and generic controller tuning process to the wind energy research community that can perform comparably or better than existing reference wind turbine controllers and includes features that are consistent with industry standards. Notably, ROSCO provides the first known open-source controller with features that specifically address floating offshore wind turbine control.
Paul Fleming, Michael Sinner, Tom Young, Marine Lannic, Jennifer King, Eric Simley, and Bart Doekemeijer
Wind Energ. Sci., 6, 1521–1531, https://doi.org/10.5194/wes-6-1521-2021, https://doi.org/10.5194/wes-6-1521-2021, 2021
Short summary
Short summary
The paper presents a new validation campaign of wake steering at a commercial wind farm. The campaign uses fixed yaw offset positions, rather than a table of optimal yaw offsets dependent on wind direction, to enable comparison with engineering models of wake steering. Additionally, by applying the same offset in beneficial and detrimental conditions, we are able to collect important data for assessing second-order wake model predictions.
Eric Simley, Paul Fleming, Nicolas Girard, Lucas Alloin, Emma Godefroy, and Thomas Duc
Wind Energ. Sci., 6, 1427–1453, https://doi.org/10.5194/wes-6-1427-2021, https://doi.org/10.5194/wes-6-1427-2021, 2021
Short summary
Short summary
Wake steering is a wind farm control strategy in which upstream wind turbines are misaligned with the wind to deflect their low-velocity wakes away from downstream turbines, increasing overall power production. Here, we present results from a two-turbine wake-steering experiment at a commercial wind plant. By analyzing the wind speed dependence of wake steering, we find that the energy gained tends to increase for higher wind speeds because of both the wind conditions and turbine operation.
Alessandro Fontanella, Mees Al, Jan-Willem van Wingerden, and Marco Belloli
Wind Energ. Sci., 6, 885–901, https://doi.org/10.5194/wes-6-885-2021, https://doi.org/10.5194/wes-6-885-2021, 2021
Short summary
Short summary
Floating wind is a key technology to harvest the abundant wind energy resource of deep waters. This research introduces a new way of controlling the wind turbine to better deal with the action of waves. The turbine is made aware of the incoming waves, and the information is exploited to enhance power production.
Sebastian Perez-Becker, David Marten, and Christian Oliver Paschereit
Wind Energ. Sci., 6, 791–814, https://doi.org/10.5194/wes-6-791-2021, https://doi.org/10.5194/wes-6-791-2021, 2021
Short summary
Short summary
Active trailing edge flaps can potentially enable further increases in wind turbine sizes without the disproportionate increase in loads, thus reducing the cost of wind energy even further. Extreme loads and critical deflections of the turbine blade are design-driving issues that can effectively be reduced by flaps. This paper considers the flap hinge moment as an input sensor for a flap controller that reduces extreme loads and critical deflections of the blade in turbulent wind conditions.
Marta Bertelè, Carlo L. Bottasso, and Johannes Schreiber
Wind Energ. Sci., 6, 759–775, https://doi.org/10.5194/wes-6-759-2021, https://doi.org/10.5194/wes-6-759-2021, 2021
Short summary
Short summary
A previously published wind sensing method is applied to an experimental dataset obtained from a 3.5 MW turbine and a nearby hub-tall met mast. The method uses blade load harmonics to estimate rotor-equivalent shears and wind directions at the rotor disk. Results indicate the good quality of the estimated shear, both in terms of 10 min averages and of resolved time histories, and a reasonable accuracy in the estimation of the yaw misalignment.
Jennifer King, Paul Fleming, Ryan King, Luis A. Martínez-Tossas, Christopher J. Bay, Rafael Mudafort, and Eric Simley
Wind Energ. Sci., 6, 701–714, https://doi.org/10.5194/wes-6-701-2021, https://doi.org/10.5194/wes-6-701-2021, 2021
Short summary
Short summary
This paper highlights the secondary effects of wake steering, including yaw-added wake recovery and secondary steering. These effects enhance the value of wake steering especially when applied to a large wind farm. This paper models these secondary effects using an analytical model proposed in the paper. The results of this model are compared with large-eddy simulations for several cases including 2-turbine, 3-turbine, 5-turbine, and 38-turbine cases.
Daniel Cornel, Francisco Gutiérrez Guzmán, Georg Jacobs, and Stephan Neumann
Wind Energ. Sci., 6, 367–376, https://doi.org/10.5194/wes-6-367-2021, https://doi.org/10.5194/wes-6-367-2021, 2021
Short summary
Short summary
Roller bearing failures in wind turbines' gearboxes lead to long downtimes and high repair costs. This paper should form a basis for the implementation of a predictive maintenance system. Therefore an acoustic-emission-based condition monitoring system is applied to roller bearing test rigs. The system has shown that a damaged surface can be detected at least ~ 4 % (8 h, regarding the time to failure) and possibly up to ~ 50 % (130 h) earlier than by using the vibration-based system.
Daniel S. Zalkind, Emiliano Dall'Anese, and Lucy Y. Pao
Wind Energ. Sci., 5, 1579–1600, https://doi.org/10.5194/wes-5-1579-2020, https://doi.org/10.5194/wes-5-1579-2020, 2020
Short summary
Short summary
New wind turbine designs require updated control parameters, which should be optimal in terms of the performance measures that drive hardware design. We show how a zeroth-order optimization algorithm can randomly generate control parameters, use simulation results to estimate the gradient of the parameter space, and find an optimal set of those parameters. We then apply this automatic controller tuning procedure to three problems in wind turbine control.
Mads M. Pedersen and Gunner C. Larsen
Wind Energ. Sci., 5, 1551–1566, https://doi.org/10.5194/wes-5-1551-2020, https://doi.org/10.5194/wes-5-1551-2020, 2020
Short summary
Short summary
In this paper, the influence of optimal wind farm control and optimal wind farm layout is investigated in terms of power production. The capabilities of the developed optimization platform is demonstrated on the Swedish offshore wind farm, Lillgrund. It shows that the expected annual energy production can be increased by 4 % by integrating the wind farm control into the design of the wind farm layout, which is 1.2 % higher than what is achieved by optimizing the layout only.
Stephanie Lehnhoff, Alejandro Gómez González, and Jörg R. Seume
Wind Energ. Sci., 5, 1411–1423, https://doi.org/10.5194/wes-5-1411-2020, https://doi.org/10.5194/wes-5-1411-2020, 2020
Short summary
Short summary
The application of an optical measurement method for the determination of rotor blade deformation and torsion based on digital image correlation (DIC) is presented. Measurement results are validated by comparison with comparative measurement data. Finally, aeroelastic simulation results are compared to DIC results. It is shown that the measured deformation is in very good agreement with the simulations, and therefore DIC has great potential for the experimental validation of aeroelastic codes.
Michael F. Howland, Aditya S. Ghate, Sanjiva K. Lele, and John O. Dabiri
Wind Energ. Sci., 5, 1315–1338, https://doi.org/10.5194/wes-5-1315-2020, https://doi.org/10.5194/wes-5-1315-2020, 2020
Short summary
Short summary
Wake losses significantly reduce the power production of utility-scale wind farms since all wind turbines are operated in a greedy, individual power maximization fashion. In order to mitigate wake losses, collective wind farm operation strategies use wake steering, in which certain turbines are intentionally misaligned with respect to the incoming wind direction. The control strategy developed is dynamic and closed-loop to adapt to changing atmospheric conditions.
Anubhav Jain, Jayachandra N. Sakamuri, and Nicolaos A. Cutululis
Wind Energ. Sci., 5, 1297–1313, https://doi.org/10.5194/wes-5-1297-2020, https://doi.org/10.5194/wes-5-1297-2020, 2020
Short summary
Short summary
This paper provides an understanding of grid-forming control of wind turbines that can enable their black-start and islanding functionalities. Four control strategies have been tested with the aim to compare their capability to deal with the energization transients of an HVDC-connected offshore wind power plant, while maintaining stable offshore voltage and frequency. This is a step forward in overcoming wind turbine control challenges to provide black-start/restoration ancillary services.
Filippo Campagnolo, Robin Weber, Johannes Schreiber, and Carlo L. Bottasso
Wind Energ. Sci., 5, 1273–1295, https://doi.org/10.5194/wes-5-1273-2020, https://doi.org/10.5194/wes-5-1273-2020, 2020
Short summary
Short summary
The performance of an open-loop wake-steering controller is investigated with a new wind tunnel experiment. Three scaled wind turbines are placed on a large turntable and exposed to a turbulent inflow, resulting in dynamically varying wake interactions. The study highlights the importance of using a robust formulation and plant flow models of appropriate fidelity and the existence of possible margins for improvement by the use of dynamic controllers.
Paul Fleming, Jennifer King, Eric Simley, Jason Roadman, Andrew Scholbrock, Patrick Murphy, Julie K. Lundquist, Patrick Moriarty, Katherine Fleming, Jeroen van Dam, Christopher Bay, Rafael Mudafort, David Jager, Jason Skopek, Michael Scott, Brady Ryan, Charles Guernsey, and Dan Brake
Wind Energ. Sci., 5, 945–958, https://doi.org/10.5194/wes-5-945-2020, https://doi.org/10.5194/wes-5-945-2020, 2020
Short summary
Short summary
This paper presents the results of a field campaign investigating the performance of wake steering applied at a section of a commercial wind farm. It is the second phase of the study for which the first phase was reported in a companion paper (https://wes.copernicus.org/articles/4/273/2019/). The authors implemented wake steering on two turbine pairs and compared results with the latest FLORIS model of wake steering, showing good agreement in overall energy increase.
Leif Erik Andersson and Lars Imsland
Wind Energ. Sci., 5, 885–896, https://doi.org/10.5194/wes-5-885-2020, https://doi.org/10.5194/wes-5-885-2020, 2020
Short summary
Short summary
The article describes a hybrid modeling approach to optimize the energy capture of wind farms. Hybrid modeling combines mechanistic and
data-driven models. The data-driven part is used to correct inaccuracies of the mechanistic model. The hybrid approach allows for adjustment of the mechanistic model beyond simple parameter estimation. It is, therefore, an attractive approach in wind farm control. The approach is illustrated in several numerical case studies.
Johannes Schreiber, Carlo L. Bottasso, and Marta Bertelè
Wind Energ. Sci., 5, 867–884, https://doi.org/10.5194/wes-5-867-2020, https://doi.org/10.5194/wes-5-867-2020, 2020
Short summary
Short summary
This paper validates a method to estimate the vertical wind shear and detect the presence and location of an impinging wake with field data. Shear and wake awareness have multiple uses, from turbine and farm control to monitoring and forecasting.
Results indicate a very good correlation between the estimated vertical shear and the one measured by a met mast and a remarkable ability to locate and track the motion of an impinging wake on an affected rotor.
Eric Simley, Paul Fleming, and Jennifer King
Wind Energ. Sci., 5, 451–468, https://doi.org/10.5194/wes-5-451-2020, https://doi.org/10.5194/wes-5-451-2020, 2020
Short summary
Short summary
Wind farm wake losses occur when turbines operate in the wakes of upstream turbines. However, wake steering control can be used to deflect wakes away from downstream turbines. A method for including wind direction variability in wake steering simulations is presented here. Controller performance is shown to improve when wind direction variability is accounted for. Furthermore, the importance of wind direction variability is shown for different turbine spacings and atmospheric conditions.
Joeri Alexis Frederik, Robin Weber, Stefano Cacciola, Filippo Campagnolo, Alessandro Croce, Carlo Bottasso, and Jan-Willem van Wingerden
Wind Energ. Sci., 5, 245–257, https://doi.org/10.5194/wes-5-245-2020, https://doi.org/10.5194/wes-5-245-2020, 2020
Short summary
Short summary
The interaction between wind turbines in a wind farm through their wakes is a widely studied research area. Until recently, research was focused on finding constant turbine inputs that optimize the performance of the wind farm. However, recent studies have shown that time-varying, dynamic inputs might be more beneficial. In this paper, the validity of this approach is further investigated by implementing it in scaled wind tunnel experiments and assessing load effects, showing promising results.
Róbert Ungurán, Vlaho Petrović, Lucy Y. Pao, and Martin Kühn
Wind Energ. Sci., 4, 677–692, https://doi.org/10.5194/wes-4-677-2019, https://doi.org/10.5194/wes-4-677-2019, 2019
Short summary
Short summary
A novel lidar-based sensory system for wind turbine control is proposed. The main contributions are the parametrization method of the novel measurement system, the identification of possible sources of measurement uncertainty, and their modelling. Although not the focus of the submitted paper, the mentioned contributions represent essential building blocks for robust feedback–feedforward wind turbine control development which could be used to improve wind turbine control strategies.
Hector Mendez Reyes, Stoyan Kanev, Bart Doekemeijer, and Jan-Willem van Wingerden
Wind Energ. Sci., 4, 549–561, https://doi.org/10.5194/wes-4-549-2019, https://doi.org/10.5194/wes-4-549-2019, 2019
Short summary
Short summary
Within wind farms, the wind turbines interact with each other through their wakes. Turbines operating in these wakes have lower power production and increased wear and tear. Wake redirection is control strategy to steer the wakes aside from downstream turbines, increasing the power yield of the farm. Models for predicting the power gain and impacts on wear exist, but they are still immature and require validation. The validation of such a model is the purpose of this paper.
Jennifer Annoni, Christopher Bay, Kathryn Johnson, Emiliano Dall'Anese, Eliot Quon, Travis Kemper, and Paul Fleming
Wind Energ. Sci., 4, 355–368, https://doi.org/10.5194/wes-4-355-2019, https://doi.org/10.5194/wes-4-355-2019, 2019
Short summary
Short summary
Typically, turbines do not share information with nearby turbines in a wind farm. Relying on a single turbine sensor on the back of a turbine nacelle can lead to large errors in yaw misalignment or excessive yawing due to noisy sensor measurements. The wind farm consensus control approach in this paper shows the benefits of sharing information between nearby turbines by computing a robust estimate of the wind direction using noisy sensor information from these neighboring turbines.
Paul Fleming, Jennifer King, Katherine Dykes, Eric Simley, Jason Roadman, Andrew Scholbrock, Patrick Murphy, Julie K. Lundquist, Patrick Moriarty, Katherine Fleming, Jeroen van Dam, Christopher Bay, Rafael Mudafort, Hector Lopez, Jason Skopek, Michael Scott, Brady Ryan, Charles Guernsey, and Dan Brake
Wind Energ. Sci., 4, 273–285, https://doi.org/10.5194/wes-4-273-2019, https://doi.org/10.5194/wes-4-273-2019, 2019
Short summary
Short summary
Wake steering is a form of wind farm control in which turbines use yaw offsets to affect wakes in order to yield an increase in total energy production. In this first phase of a study of wake steering at a commercial wind farm, two turbines implement a schedule of offsets. For two closely spaced turbines, an approximate 14 % increase in energy was measured on the downstream turbine over a 10° sector, with a 4 % increase in energy production of the combined turbine pair.
Mehdi Vali, Vlaho Petrović, Gerald Steinfeld, Lucy Y. Pao, and Martin Kühn
Wind Energ. Sci., 4, 139–161, https://doi.org/10.5194/wes-4-139-2019, https://doi.org/10.5194/wes-4-139-2019, 2019
Short summary
Short summary
A new active power control (APC) approach is investigated to simultaneously reduce the wake-induced power tracking errors and structural fatigue loads of individual turbines within a wind farm. The non-unique solution of the APC problem with respect to the distribution of the individual powers is exploited. The simple control architecture and practical measurement system make the proposed approach prominent for real-time control of large wind farms with turbulent flows and wakes.
Andreas Rott, Bart Doekemeijer, Janna Kristina Seifert, Jan-Willem van Wingerden, and Martin Kühn
Wind Energ. Sci., 3, 869–882, https://doi.org/10.5194/wes-3-869-2018, https://doi.org/10.5194/wes-3-869-2018, 2018
Short summary
Short summary
Active wake deflection (AWD) aims to increase the power output of a wind farm by misaligning the yaw of upstream turbines. We analysed the effect of dynamic wind direction changes on AWD. The results show that AWD is very sensitive towards these dynamics. Therefore, we present a robust active wake control, which considers uncertainties and wind direction changes, increasing the overall power output of a wind farm. A side effect is a significant reduction of the yaw actuation of the turbines.
Marta Bertelè, Carlo L. Bottasso, and Stefano Cacciola
Wind Energ. Sci., 3, 791–803, https://doi.org/10.5194/wes-3-791-2018, https://doi.org/10.5194/wes-3-791-2018, 2018
Short summary
Short summary
This work presents a new fully automated method to correct for
pitch misalignment imbalances of wind turbine rotors. The method
has minimal requirements, as it only assumes the availability of a
sensor of sufficient accuracy and bandwidth to detect the 1P
harmonic to the desired precision and the ability to command the
pitch setting of each blade independently from the others.
Extensive numerical simulations are used to demonstrate the new
procedure.
Bart M. Doekemeijer, Sjoerd Boersma, Lucy Y. Pao, Torben Knudsen, and Jan-Willem van Wingerden
Wind Energ. Sci., 3, 749–765, https://doi.org/10.5194/wes-3-749-2018, https://doi.org/10.5194/wes-3-749-2018, 2018
Short summary
Short summary
Most wind farm control algorithms in the literature rely on a simplified mathematical model that requires constant calibration to the current conditions. This paper provides such an estimation algorithm for a dynamic model capturing the turbine power production and flow field at hub height. Performance was demonstrated in high-fidelity simulations for two-turbine and nine-turbine farms, accurately estimating the ambient conditions and wind field inside the farms at a low computational cost.
Sebastiaan Paul Mulders, Niels Frederik Boudewijn Diepeveen, and Jan-Willem van Wingerden
Wind Energ. Sci., 3, 615–638, https://doi.org/10.5194/wes-3-615-2018, https://doi.org/10.5194/wes-3-615-2018, 2018
Short summary
Short summary
The modeling, operating strategy, and controller design for an actual in-field wind turbine with a fixed-displacement hydraulic drivetrain are presented. An analysis is given on a passive torque control strategy for below-rated operation. The turbine lacks the option to influence the system torque by a generator, so the turbine is regulated by a spear valve in the region between below- and above-rated operation. The control design is evaluated on a real-world 500 kW hydraulic wind turbine.
Jan Bartl, Franz Mühle, and Lars Sætran
Wind Energ. Sci., 3, 489–502, https://doi.org/10.5194/wes-3-489-2018, https://doi.org/10.5194/wes-3-489-2018, 2018
Short summary
Short summary
Our experimental wind tunnel study on a pair of model wind turbines demonstrates a significant potential of turbine yaw angle control for the combined optimization of turbine power and rotor loads. Depending on the turbines' relative positions to the incoming wind, a combined power increase and individual rotor load reduction can be achieved by operating the turbine rotors slightly misaligned with the main wind direction (i.e., at a certain yaw angle).
Wim Munters and Johan Meyers
Wind Energ. Sci., 3, 409–425, https://doi.org/10.5194/wes-3-409-2018, https://doi.org/10.5194/wes-3-409-2018, 2018
Short summary
Short summary
Wake interactions in wind farms result in power losses for downstream turbines. We aim to mitigate these losses through coordinated control of the induced slowdown of the wind by each turbine. We further analyze results from earlier work towards the utilization of such control strategies in practice. Coherent vortex shedding is identified and mimicked by a sinusoidal control. The latter is shown to increase power in downstream turbines and is robust to turbine spacing and turbulence intensity.
Niko Mittelmeier and Martin Kühn
Wind Energ. Sci., 3, 395–408, https://doi.org/10.5194/wes-3-395-2018, https://doi.org/10.5194/wes-3-395-2018, 2018
Short summary
Short summary
Upwind horizontal axis wind turbines need to be aligned with the main wind direction to maximize energy yield. This paper presents new methods to improve turbine alignment and detect changes during operational lifetime with standard nacelle met mast instruments. The flow distortion behind the rotor is corrected with a multilinear regression model and two alignment changes are detected with an accuracy of ±1.4° within 3 days of operation after the change is introduced.
Tarek N. Dief, Uwe Fechner, Roland Schmehl, Shigeo Yoshida, Amr M. M. Ismaiel, and Amr M. Halawa
Wind Energ. Sci., 3, 275–291, https://doi.org/10.5194/wes-3-275-2018, https://doi.org/10.5194/wes-3-275-2018, 2018
Paul Fleming, Jennifer Annoni, Matthew Churchfield, Luis A. Martinez-Tossas, Kenny Gruchalla, Michael Lawson, and Patrick Moriarty
Wind Energ. Sci., 3, 243–255, https://doi.org/10.5194/wes-3-243-2018, https://doi.org/10.5194/wes-3-243-2018, 2018
Short summary
Short summary
This paper investigates the role of flow structures in wind farm control through yaw misalignment. A pair of counter-rotating vortices is shown to be important in deforming the shape of the wake. Further, we demonstrate that the vortex structures created in wake steering can enable a greater change power generation than currently modeled in control-oriented models. We propose that wind farm controllers can be made more effective if designed to take advantage of these effects.
Michael K. McWilliam, Thanasis K. Barlas, Helge A. Madsen, and Frederik Zahle
Wind Energ. Sci., 3, 231–241, https://doi.org/10.5194/wes-3-231-2018, https://doi.org/10.5194/wes-3-231-2018, 2018
Short summary
Short summary
Maximizing wind energy production is challenging because the winds are always changing. Design optimization was used to explore how flaps can give rotor design engineers greater ability to adapt the rotor for different conditions. For rotors designed for peak efficiency (i.e. older designs) the flap adds 0.5 % improvement in energy production. However, for modern designs that optimize both the performance and the structure, the flap can provide a 1 % improvement.
Carl R. Shapiro, Johan Meyers, Charles Meneveau, and Dennice F. Gayme
Wind Energ. Sci., 3, 11–24, https://doi.org/10.5194/wes-3-11-2018, https://doi.org/10.5194/wes-3-11-2018, 2018
Short summary
Short summary
We investigate the capability of wind farms to track a power reference signal to help ensure reliable power grid operations. The wind farm controller is based on a simple dynamic wind farm model and tested using high-fidelity simulations. We find that the dynamic nature of the wind farm model is vital for tracking the power signal, and the controlled wind farm would pass industry performance tests in most cases.
Paul Fleming, Jennifer Annoni, Jigar J. Shah, Linpeng Wang, Shreyas Ananthan, Zhijun Zhang, Kyle Hutchings, Peng Wang, Weiguo Chen, and Lin Chen
Wind Energ. Sci., 2, 229–239, https://doi.org/10.5194/wes-2-229-2017, https://doi.org/10.5194/wes-2-229-2017, 2017
Short summary
Short summary
In this paper, a field test of wake-steering control is presented. In the campaign, an array of turbines within an operating commercial offshore wind farm have the normal yaw controller modified to implement wake steering according to a yaw control strategy. Results indicate that, within the certainty afforded by the data, the wake-steering controller was successful in increasing power capture.
Edwin van Solingen, Sebastiaan Paul Mulders, and Jan-Willem van Wingerden
Wind Energ. Sci., 2, 153–173, https://doi.org/10.5194/wes-2-153-2017, https://doi.org/10.5194/wes-2-153-2017, 2017
Short summary
Short summary
The aim of this paper is to show that with an automated tuning strategy, wind turbine control performance can be significantly increased. To this end, iterative feedback tuning (IFT) is applied to two different turbine controllers. The results obtained by high-fidelity simulations indicate significant performance improvements over baseline controllers. It is concluded that IFT of turbine controllers has the potential to become a valuable tool for improving wind turbine performance.
Carlo L. Bottasso, Alessandro Croce, Federico Gualdoni, Pierluigi Montinari, and Carlo E. D. Riboldi
Wind Energ. Sci., 1, 297–310, https://doi.org/10.5194/wes-1-297-2016, https://doi.org/10.5194/wes-1-297-2016, 2016
Short summary
Short summary
The paper discusses different concepts for reducing loads on wind turbines using movable blade tips. Passive and semi-passive tip solutions move freely in response to air load fluctuations, while in the active case an actuator drives the tip motion in response to load measurements. The various solutions are compared with a standard blade and with each other in terms of their ability to reduce both fatigue and extreme loads.
Sachin T. Navalkar, Lars O. Bernhammer, Jurij Sodja, Edwin van Solingen, Gijs A. M. van Kuik, and Jan-Willem van Wingerden
Wind Energ. Sci., 1, 205–220, https://doi.org/10.5194/wes-1-205-2016, https://doi.org/10.5194/wes-1-205-2016, 2016
Short summary
Short summary
In order to reduce the cost of wind energy, it is necessary to reduce the loads that wind turbines withstand over their lifetime. The combination of blade rotation with newly designed blade shape changing actuators is demonstrated experimentally. While load reduction is achieved, the additional flexibility implies that careful control design is needed to avoid instability.
Riccardo Riva, Stefano Cacciola, and Carlo Luigi Bottasso
Wind Energ. Sci., 1, 177–203, https://doi.org/10.5194/wes-1-177-2016, https://doi.org/10.5194/wes-1-177-2016, 2016
Short summary
Short summary
This paper presents a method to assess the stability of a wind turbine. The proposed approach uses the recorded time history of the system response and fits to it a periodic reduced-order model that can handle stochastic disturbances. Stability is computed by using Floquet theory on the reduced-order model. Since the method only uses response data, it is applicable to any simulation model as well as to experimental test data. The method is compared to the well-known operational modal analysis.
Karl O. Merz
Wind Energ. Sci., 1, 153–175, https://doi.org/10.5194/wes-1-153-2016, https://doi.org/10.5194/wes-1-153-2016, 2016
Short summary
Short summary
Wind turbines are controlled through the electrical torque on the generator and the pitch of the blades. The tuning of the controller determines the dynamics of the system, which can then be good (smooth yet responsive) or bad (ineffective or unstable). A methodical investigation was conducted to determine the minimal model of the wind turbine structure and aerodynamics that can be used to tune the controller gains for large, multi-MW offshore wind turbines.
Cited articles
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M.,
Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R.,
Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P.,
Wicke, M., Yu, Y., Zheng, X., and Brain, G.: TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine
learning, in: 12th USENIX Symposium on Operating Systems Design and
Implementation (OSDI '16), 2–4 November 2016, Savannah, GA, USA, ISBN 9781931971331, 265–284, https://doi.org/10.1038/nn.3331, 2016. a
Annoni, J., Taylor, T., Bay, C., Johnson, K., Pao, L., Fleming, P., and Dykes, K.: Sparse-Sensor Placement for Wind Farm Control, J. Phys.: Conf. Ser., 1037, 032019, https://doi.org/10.1088/1742-6596/1037/3/032019, 2018. a
Attya, A., Dominguez-Garcia, J., and Anaya-Lara, O.: A review on frequency
support provision by wind power plants: Current and future challenges, Renew. Sustain. Energ. Rev., 81, 2071–2087, https://doi.org/10.1016/j.rser.2017.06.016, 2018. a
Bak, C., Bitsche, R., Yde, A., Kim, T., Hansen, M. H., Zahle, F., Gaunaa, M.,
Blasques, J., Døssing, M., Heinen, J. J. W., and Behrens, T.: Light
rotor: The 10-MW Reference Wind Turbine, in: European Wind Energy Conference
and Exhibition 2012, EWEC 2012, 16–19 April 2012, Copenhagen, Denmark, 2012. a, b
Bak, C., Zahle, F., Bitsche, R., Kim, T., Yde, A., Henriksen, L. C., Hansen, M. H., Blasques, J. P. A. A., Gaunaa, M., and Natarajan, A.: The DTU 10-MW Reference Wind Turbine, in: Danish Wind Power Research 2013, 27–28 May 2013, Denmark, https://doi.org/10.1017/CBO9781107415324.004, 2013. a
Bali, V., Kumar, A., and Gangwar, S.: Deep learning based wind speed
forecasting- A review, in: Proceedings of the 9th International Conference On Cloud Computing, Data Science and Engineering, Confluence 2019, 26–28 February 2019, Orlando, FL, USA, https://doi.org/10.1109/CONFLUENCE.2019.8776923, 2019. a
Bandi, M. and Apt, J.: Variability of the Wind Turbine Power Curve, Appl.
Sci., 6, 262, https://doi.org/10.3390/app6090262, 2016. a
Bhowmik, S., Spee, R., and Enslin, J. H.: Performance optimization for
doubly-fed wind power generation systems, in: vol. 3, Conference Record of 1998 IEEE Industry Applications Conference, Thirty-Third IAS Annual Meeting (Cat. No. 98CH36242), 12–15 October 1998, St. Louis, MO, USA, 2387–2394, 1998. a
Chen, J., Zeng, G. Q., Zhou, W., Du, W., and Lu, K. D.: Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization, Energ. Convers. Manage., 165, 681–695,
https://doi.org/10.1016/j.enconman.2018.03.098, 2018. a
Chinmoy, L., Iniyan, S., and Goic, R.: Modeling wind power investments,
policies and social benefits for deregulated electricity market – A review, Appl. Energy, 242, 364–377, https://doi.org/10.1016/j.apenergy.2019.03.088, 2019. a
50Hertz, Amprion, Tennet, TransnetBW: Leitfaden zur Präqualifikation von
Windenergieanlagen zur Erbringung von Minutenreserveleistung im Rahmen einer
Pilotphase/Guidelines for Prequalification of Wind parks to provide
Minutenreserveleistung (MRL) during a Pilot Phase, Tech. rep., German
Tranmission System Operators, available at: https://www.regelleistung.net/ext/download/pqWindkraft (last access: 29 July 2020), 2016. a, b, c
Fleming, P. A., Aho, J., Buckspan, A., Ela, E., Zhang, Y., Gevorgian, V.,
Scholbrock, A., Pao, L., and Damiani, R.: Effects of power reserve control on
wind turbine structural loading, Wind Energy, 19, 453–469, 2016. a
Gers, F. A. and Schmidhuber, E.: LSTM recurrent networks learn simple
context-free and context-sensitive languages, IEEE T. Neural Netw., 12, 1333–1340, 2001. a
Gers, F. A., Schmidhuber, J., and Cummins, F.: Learning to Forget: Continual
Prediction with LSTM, Neural Comput,, 12, 2451–2471,
https://doi.org/10.1162/089976600300015015, 2000. a
Ghaderi, A., Sanandaji, B. M., and Ghaderi, F.: Deep Forecast: Deep
Learning-based Spatio-Temporal Forecasting, preprint arXiv:1707.08110, ISSN 23318422, 2017. a
Göçmen, T. and Giebel, G.: Data-driven Wake Modelling for Reduced
Uncertainties in short-term Possible Power Estimation, J. Phys.: Conf. Ser., 1037, 072002, https://doi.org/10.1088/1742-6596/1037/7/072002, 2018. a, b
Göçmen, T., Giebel, G., Poulsen, N. K., and Mirzaei, M.: Wind speed estimation and parametrization of wake models for downregulated offshore wind farms within the scope of PossPOW project, J. Phys.: Conf. Ser., 524, 012156–012163, https://doi.org/10.1088/1742-6596/524/1/012156, 2014. a
Göçmen, T., Giebel, G., Réthoré, P.-E., and Murcia Leon, J. P.: Uncertainty Quantification of the Real-Time Reserves for Offshore Wind Power Plants, in: 15th Wind Integration Workshop, 15–17 November 2016, Vienna, Austria, 2016. a
Göçmen, T., Giebel, G., Poulsen, N. K., and Sørensen, P. E.:
Possible power of down-regulated offshore wind power plants: The PossPOW
algorithm, Wind Energy, 22, 205–218, https://doi.org/10.1002/we.2279, 2019. a
Göçmen, T., Meseguer Urbán, A., and Liew, J.: Deep Learning for Available Power Estimation, Zenodo, https://doi.org/10.5281/zenodo.3531414, 2020. a
Hansen, A. D., Sørensen, P., Iov, F., and Blaabjerg, F.: Grid support of a
wind farm with active stall wind turbines and AC grid connection, Wind Energy, 9, 341–359, 2006. a
Henriksen, L., Hansen, M., and Poulsen, N.: A simplified dynamic inflow model
and its effect on the performance of free mean wind speed estimation, Wind
Energy, 17, 1213–1224, https://doi.org/10.1002/we.1548, 2012. a
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997. a
Jena, D. and Rajendran, S.: A review of estimation of effective wind speed
based control of wind turbines, Renew. Sustain. Energ Rev., 43, 1046–1062, 2015. a
Jin, T. and Tian, Z.: Uncertainty analysis for wind energy production with
dynamic power curves, in: 2010 IEEE 11th International Conference on
Probabilistic Methods Applied to Power Systems, PMAPS 2010, 14–17 June 2010, Singapore, https://doi.org/10.1109/PMAPS.2010.5528405, 2010. a
Knudsen, T., Bak, T., and Soltani, M.: Prediction models for wind speed at
turbine locations in a wind farm, Wind Energy, 14, 877–894, https://doi.org/10.1002/we.491, 2011. a, b
Kristoffersen, J.: The Horns Rev Wind Farm and the Operational Experience with the Wind Farm Main Controller, in: Proceedings of the Copenhagen Offshore Wind, 26–28 October 2005, Copenhagen, Denmark, 2005. a
Lange, M.: On the uncertainty of wind power predictions – Analysis of the
forecast accuracy and statistical distribution of errors, J. Solar Energ. Eng., T. ASME, 127, 177–184, https://doi.org/10.1115/1.1862266, 2005. a
Lio, W. H.: Blade-Pitch Control for Wind Turbine Load Reductions, Springer
Theses, Springer International Publishing, New York, NY, USA, https://doi.org/10.1007/978-3-319-75532-8, 2018. a
Lio, W. H., Mirzaei, M., and Larsen, G. C.: On wind turbine down-regulation
control strategies and rotor speed set-point, J. Phys.: Conf. Ser., 1037, 032040, https://doi.org/10.1088/1742-6596/1037/3/032040, 2018. a
Lydia, M., Kumar, S. S., Selvakumar, A. I., and Prem Kumar, G. E.: A
comprehensive review on wind turbine power curve modeling techniques,
Renew. Sustain. Energ. Rev., 30, 452–460, https://doi.org/10.1016/j.rser.2013.10.030, 2014. a
Ma, X., Poulsen, N. K., and Bindner, H.: Estimation of Wind Speed in
Connection to a Wind Turbine, Tech. rep., Technical report, Technical University of Denmark, Technical report, Technical University of Denmark,
Copenhagen, Denmark, 1995. a
Manobel, B., Sehnke, F., Lazzús, J. A., Salfate, I., Felder, M., and
Montecinos, S.: Wind turbine power curve modeling based on Gaussian Processes and Artificial Neural Networks, Renew. Energy, 125, 1015–1020, https://doi.org/10.1016/j.renene.2018.02.081, 2018. a
Meng, F., Wenske, J., and Gambier, A.: Wind turbine loads reduction using
feedforward feedback collective pitch control based on the estimated
effective wind speed, in: Proceedings of the American Control Conference,
2016 July, Boston, MA, USA, 2289–2294, https://doi.org/10.1109/ACC.2016.7525259, 2016. a
Mujeeb, S., Alghamdi, T. A., Ullah, S., Fatima, A., Javaid, N., and Saba, T.:
Exploiting deep learning for wind power forecasting based on big data analytics, Appl. Sci. (Switzerland), 9, 4417–4435, https://doi.org/10.3390/app9204417, 2019. a
Murcia, J. P., Réthoré, P. E., Dimitrov, N., Natarajan, A., Sørensen, J. D., Graf, P., and Kim, T.: Uncertainty propagation through an aeroelastic wind turbine model using polynomial surrogates, Renew. Energy, 119, 910–922, https://doi.org/10.1016/j.renene.2017.07.070, 2018. a
Ortega, R., Mancilla-David, F., and Jaramillo, F.: A globally convergent wind speed estimator for windmill systems, in: Proceedings of the IEEE Conference on Decision and Control, 12–15 December 2011, Orlando, FL, USA, 6079–6084, https://doi.org/10.1109/CDC.2011.6160544, 2011. a
Ortega, R., Mancilla-David, F., and Jaramillo, F.: A globally convergent wind
speed estimator for wind turbine systems, Int. J. Adapt. Contr. Sig. Process., 27, 413–425, https://doi.org/10.1002/acs.2319, 2013. a
Østergaard, K. Z., Brath, P., and Stoustrup, J.: Estimation of effective
wind speed, J. Phys.: Conf. Ser., 75, 012082, https://doi.org/10.1088/1742-6596/75/1/012082, 2007. a, b
Ouyang, T., Kusiak, A., and He, Y.: Modeling wind-turbine power curve: A data
partitioning and mining approach, Renew. Energy, 102, 1–8, https://doi.org/10.1016/j.renene.2016.10.032, 2017. a
Pan, S. J. and Yang, Q.: A Survey on Transfer Learning, IEEE T. Knowl. Data Eng., 22, 1345–1359, https://doi.org/10.1109/TKDE.2009.191, 2010. a
Pelletier, F., Masson, C., and Tahan, A.: Wind turbine power curve modelling
using artificial neural network, Renew. Energy, 89, 207–214, https://doi.org/10.1016/j.renene.2015.11.065, 2016. a
Pinson, P.: Estimation of the uncertainty in wind power forecasting, PhD thesis, École Nationale Supérieure des Mines de Paris, Paris, France, 2006. a
Pinson, P., Chevallier, C., and Kariniotakis, G. N.: Trading wind generation
from short-term probabilistic forecasts of wind power, IEEE T. Power Syst., 22, 1148–1156, https://doi.org/10.1109/TPWRS.2007.901117, 2007. a
Rana, M. and Koprinska, I.: Forecasting electricity load with advanced wavelet neural networks, Neurocomputing, 182, 118–132,
https://doi.org/10.1016/j.neucom.2015.12.004, 2016. a
Ritter, B., Mora, E., Schlicht, T., Schild, A., and Konigorski, U.: Adaptive
Sigma-Point Kalman Filtering for Wind Turbine State and Process Noise Estimation, J. Phys.: Conf. Ser., 1037, 032003–032014, https://doi.org/10.1088/1742-6596/1037/3/032003, 2018. a
Saini, V. K., Kumar, R., Mathur, A., and Saxena, A.: Short term forecasting based on hourly wind speed data using deep learning algorithms, in: 2020 3rd International Conference on Emerging Technologies in Computer
Engineering: Machine Learning and Internet of Things (ICETCE), 7–8 February 2020, Jaipur, India, 1–6, 2020. a
Selvam, K.: Individual Pitch Control for Large scale wind turbines
Multivariable control approach, ECN Report ECN-E-07-053, ECN, Delft, the Netherlands, 2007. a
Simley, E. and Pao, L. Y.: Evaluation of a wind speed estimator for effective
hub-height and shear components, Wind Energy, 19, 167–184, https://doi.org/10.1002/we.1817, 2016. a
Soltani, M. N., Knudsen, T., Svenstrup, M., Wisniewski, R., Brath, P., Ortega, R., and Johnson, K.: Estimation of rotor effective wind speed: A
comparison, IEEE T. Contr. Syst. Technol., 21, 1155–1167, https://doi.org/10.1109/TCST.2013.2260751, 2013. a
Stol, K. A. and Balas, M. J.: Periodic Disturbance Accommodating Control for
Blade Load Mitigation in Wind Turbines Performance, J. Sol. Energ. Eng., 125, 379–385, https://doi.org/10.1115/1.1621672, 2003. a
Thiringer, T. and Petersson, A.: Control of a variable-speed pitch-regulated
wind turbine, Dept. of Energy and Environ., Chalmers Univ. of Technol.,
Göteborg, Sweden, 2005. a
van der Hooft, E. and van Engelen, T.: Estimated wind speed feed forward
control for wind turbine operation optimisation, in: European Wind Energy
Conference 2, 22–25 November 2004, London, UK, 2004. a
Wang, N., Wright, A. D., and Johnson, K. E.: Independent blade pitch
controller design for a three-bladed turbine using disturbance accommodating
control, in: IEEE 2016 American Control Conference (ACC), 6–8 July 2016, Boston, MA, USA, 2301–2306, https://doi.org/10.1109/ACC.2016.7525261, 2016.
a
Weiss, K., Khoshgoftaar, T. M., and Wang, D.: A survey of transfer learning,
J. Big Data, 3, 9–49, https://doi.org/10.1186/s40537-016-0043-6, 2016. a
Wilches-Bernal, F., Chow, J. H., and Sanchez-Gasca, J. J.: A Fundamental Study of Applying Wind Turbines for Power System Frequency Control, IEEE T. Power Syst., 31, 1496–1505, https://doi.org/10.1109/TPWRS.2015.2433932, 2016. a
Zhang, J., Yan, J., Infield, D., Liu, Y., and Lien, F.-S.: Short-term
forecasting and uncertainty analysis of wind turbine power based on long
short-term memory network and Gaussian mixture model, Appl. Energy, 241, 229–244, https://doi.org/10.1016/j.apenergy.2019.03.044, 2019. a, b
Short summary
Currently, the available power estimation is highly dependent on the pre-defined performance parameters of the turbine and the curtailment strategy followed. This paper proposes a model-free approach for a single-input dynamic estimation of the available power using RNNs. The unsteady patterns are represented by LSTM neurons, and the network is adapted to changing inflow conditions via transfer learning. Including highly turbulent flows, the validation shows easy compliance with the grid codes.
Currently, the available power estimation is highly dependent on the pre-defined performance...
Altmetrics
Final-revised paper
Preprint