Articles | Volume 10, issue 4
https://doi.org/10.5194/wes-10-779-2025
© Author(s) 2025. 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-10-779-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
28 Apr 2025
Research article |
| 28 Apr 2025
| 28 Apr 2025
Modular deep learning approach for wind farm power forecasting and wake loss prediction
Artificial Intelligence Lab Brussels, Vrije Universiteit Brussel, Pleinlaan 9, 1050 Elsene, Belgium
Faculty of Engineering, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Timothy Verstraeten
Artificial Intelligence Lab Brussels, Vrije Universiteit Brussel, Pleinlaan 9, 1050 Elsene, Belgium
Faculty of Engineering, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Pieter-Jan Daems
Faculty of Engineering, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Ann Nowé
Artificial Intelligence Lab Brussels, Vrije Universiteit Brussel, Pleinlaan 9, 1050 Elsene, Belgium
Jan Helsen
Faculty of Engineering, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Flanders Make@VUB, Pleinlaan 2, 1050 Elsene, Belgium
Related authors
No articles found.
Simon Daenens, Timothy Verstraeten, Pieter-Jan Daems, Ann Nowé, and Jan Helsen
Wind Energ. Sci., 10, 1137–1152, https://doi.org/10.5194/wes-10-1137-2025, https://doi.org/10.5194/wes-10-1137-2025, 2025
Short summary
Short summary
This study presents a novel model for predicting wind turbine power output at a high temporal resolution in wind farms using a hybrid graph neural network (GNN) and long short-term memory (LSTM) architecture. By modeling the wind farm as a graph, the model captures both spatial and temporal dynamics, outperforming traditional power curve methods. Integrated with a normal behavior model (NBM) framework, the model effectively identifies and analyzes power loss events.
Ivo Vervlimmeren, Xavier Chesterman, Timothy Verstraeten, Ann Nowé, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-49, https://doi.org/10.5194/wes-2025-49, 2025
Preprint under review for WES
Short summary
Short summary
We introduce a new method to refine failure prediction for wind turbines, leading to better and more efficient alarming. We do this by filtering detected anomalies based on the anomalies from the whole fleet. We compare submethods and find one that removes up to 65 % of detected anomalies while leaving the failure-predicting ones. We also detail how we trained the model that generated these anomalies and discuss the construction of the scalable pipeline that was used to deploy such models.
Konstantinos Vratsinis, Rebeca Marini, Pieter-Jan Daems, Lukas Pauscher, Jeroen van Beeck, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-32, https://doi.org/10.5194/wes-2025-32, 2025
Preprint under review for WES
Short summary
Short summary
Using data collected over 13 months at an offshore wind farm, our study shows that a wind turbine’s position within the farm influences its energy output at a given wind speed. Front-row turbines respond differently to similar wind speeds and turbulence than those further back. This finding suggests that current methods for characterizing inflow conditions may not fully capture actual wind behavior, underscoring the need for improved performance analysis techniques.
Jakob Gebel, Ashkan Rezaei, Adithya Vemuri, Veronica Liverud Krathe, Pieter-Jan Daems, Jens Jo Matthys, Jonathan Sterckx, Konstantinos Vratsinis, Kayacan Kestel, Amir R. Nejad, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2024-173, https://doi.org/10.5194/wes-2024-173, 2025
Preprint under review for WES
Short summary
Short summary
A simulation model of a deployed offshore wind turbine was developed using real-world measurement data. The method shows how to obtain, update and validate a simulation model and allows to improve the efficiency and longevity of offshore wind turbines and support operation and maintenance decisions. Simulations were conducted to analyze the effects of turbulence and wind patterns on turbine lifespan, providing insights to improve maintenance planning and reduce operational costs.
Rebeca Marini, Konstantinos Vratsinis, Kayacan Kestel, Jonathan Sterckx, Jens Matthys, Pieter-Jan Daems, Timothy Verstraeten, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-9, https://doi.org/10.5194/wes-2025-9, 2025
Revised manuscript not accepted
Short summary
Short summary
This work evaluated the wind profile in a Belgian offshore zone. The estimated wind profile was made using measurements that allow for reconstruction at heights along the rotor area. The IEC standard defines these profiles as a 1/7th power law, which is proven not to occur 100 % of the time. It is also possible to infer that there will be differences when using different wind profiles for load assessment, as more realistic profiles can lead to a better assessment of the wind turbine's lifetime.
Faras Jamil, Cédric Peeters, Timothy Verstraeten, and Jan Helsen
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2024-114, https://doi.org/10.5194/wes-2024-114, 2024
Revised manuscript accepted for WES
Short summary
Short summary
A hybrid fault detection method is proposed, which combines physical domain knowledge with machine learning models to automatically detect mechanical faults in wind turbine drivetrain components. It offers detailed insights for experts while giving operators a high-level overview of the machine's health to assist in planning effective maintenance strategies. It was validated on multiple years of wind farm data and the potential faults were accurately predicted, which was confirmed by experts.
Diederik van Binsbergen, Pieter-Jan Daems, Timothy Verstraeten, Amir R. Nejad, and Jan Helsen
Wind Energ. Sci., 9, 1507–1526, https://doi.org/10.5194/wes-9-1507-2024, https://doi.org/10.5194/wes-9-1507-2024, 2024
Short summary
Short summary
Wind farm yield assessment often relies on analytical wake models. Calibrating these models can be challenging due to the stochastic nature of wind. We developed a calibration framework that performs a multi-phase optimization on the tuning parameters using time series SCADA data. This yields a parameter distribution that more accurately reflects reality than a single value. Results revealed notable variation in resultant parameter values, influenced by nearby wind farms and coastal effects.
Xavier Chesterman, Timothy Verstraeten, Pieter-Jan Daems, Ann Nowé, and Jan Helsen
Wind Energ. Sci., 8, 893–924, https://doi.org/10.5194/wes-8-893-2023, https://doi.org/10.5194/wes-8-893-2023, 2023
Short summary
Short summary
This paper reviews and implements several techniques that can be used for condition monitoring and failure prediction for wind turbines using SCADA data. The focus lies on techniques that respond to requirements of the industry, e.g., robustness, transparency, computational efficiency, and maintainability. The end result of this research is a pipeline that can accurately detect three types of failures, i.e., generator bearing failures, generator fan failures, and generator stator failures.
Adithya Vemuri, Sophia Buckingham, Wim Munters, Jan Helsen, and Jeroen van Beeck
Wind Energ. Sci., 7, 1869–1888, https://doi.org/10.5194/wes-7-1869-2022, https://doi.org/10.5194/wes-7-1869-2022, 2022
Short summary
Short summary
The sensitivity of the WRF mesoscale modeling framework in accurately representing and predicting wind-farm-level environmental variables for three extreme weather events over the Belgian North Sea is investigated in this study. The overall results indicate highly sensitive simulation results to the type and combination of physics parameterizations and the type of the weather phenomena, with indications that scale-aware physics parameterizations better reproduce wind-related variables.
Amir R. Nejad, Jonathan Keller, Yi Guo, Shawn Sheng, Henk Polinder, Simon Watson, Jianning Dong, Zian Qin, Amir Ebrahimi, Ralf Schelenz, Francisco Gutiérrez Guzmán, Daniel Cornel, Reza Golafshan, Georg Jacobs, Bart Blockmans, Jelle Bosmans, Bert Pluymers, James Carroll, Sofia Koukoura, Edward Hart, Alasdair McDonald, Anand Natarajan, Jone Torsvik, Farid K. Moghadam, Pieter-Jan Daems, Timothy Verstraeten, Cédric Peeters, and Jan Helsen
Wind Energ. Sci., 7, 387–411, https://doi.org/10.5194/wes-7-387-2022, https://doi.org/10.5194/wes-7-387-2022, 2022
Short summary
Short summary
This paper presents the state-of-the-art technologies and development trends of wind turbine drivetrains – the energy conversion systems transferring the kinetic energy of the wind to electrical energy – in different stages of their life cycle: design, manufacturing, installation, operation, lifetime extension, decommissioning and recycling. The main aim of this article is to review the drivetrain technology development as well as to identify future challenges and research gaps.
Related subject area
Thematic area: Dynamics and control | Topic: Wind farm control
A dynamic open-source model to investigate wake dynamics in response to wind farm flow control strategies
Load assessment of a wind farm considering negative and positive yaw misalignment for wake steering
Comparison of wind farm control strategies under realistic offshore wind conditions: turbine quantities of interest
Wind turbine wake detection and characterisation utilising blade loads and SCADA data: a generalised approach
Spectral proper orthogonal decomposition of active wake mixing dynamics in a stable atmospheric boundary layer
Development and validation of a hybrid data-driven model-based wake steering controller and its application at a utility-scale wind plant
Evaluating the potential of a wake steering co-design for wind farm layout optimization through a tailored genetic algorithm
Integer programming for optimal yaw control of wind farms
On the importance of wind predictions in wake steering optimization
On the power and control of a misaligned rotor – beyond the cosine law
Dynamic wind farm flow control using free-vortex wake models
The value of wake steering wind farm flow control in US energy markets
Towards real-time optimal control of wind farms using large-eddy simulations
Sensitivity analysis of wake steering optimisation for wind farm power maximisation
The dynamic coupling between the pulse wake mixing strategy and floating wind turbines
Validation of an interpretable data-driven wake model using lidar measurements from a field wake steering experiment
Wind farm flow control: prospects and challenges
Large-eddy simulation of a wind-turbine array subjected to active yaw control
FarmConners market showcase results: wind farm flow control considering electricity prices
The revised FLORIDyn model: implementation of heterogeneous flow and the Gaussian wake
Multifidelity multiobjective optimization for wake-steering strategies
Evaluation of different power tracking operating strategies considering turbine loading and power dynamics
A physically interpretable data-driven surrogate model for wake steering
Experimental analysis of the effect of dynamic induction control on a wind turbine wake
Marcus Becker, Maxime Lejeune, Philippe Chatelain, Dries Allaerts, Rafael Mudafort, and Jan-Willem van Wingerden
Wind Energ. Sci., 10, 1055–1075, https://doi.org/10.5194/wes-10-1055-2025, https://doi.org/10.5194/wes-10-1055-2025, 2025
Short summary
Short summary
Established turbine wake models are steady-state. This paper presents an open-source dynamic wake modeling framework that complements established steady-state wake models with dynamics. It is advantageous over steady-state wake models to describe wind farm power and energy over shorter periods. The model enables researchers to investigate the effectiveness of wind farm flow control strategies. This leads to a better utilization of wind farms and allows them to be used to their fullest extent.
Regis Thedin, Garrett Barter, Jason Jonkman, Rafael Mudafort, Christopher J. Bay, Kelsey Shaler, and Jasper Kreeft
Wind Energ. Sci., 10, 1033–1053, https://doi.org/10.5194/wes-10-1033-2025, https://doi.org/10.5194/wes-10-1033-2025, 2025
Short summary
Short summary
We investigate asymmetries in terms of power performance and fatigue loading on a five-turbine wind farm subject to wake steering strategies. Both the yaw misalignment angle and the wind direction were varied from negative to positive. We highlight conditions in which fatigue loading is lower while still maintaining good power gains and show that a partial wake is the source of the asymmetries observed. We provide recommendations in terms of yaw misalignment angles for a given wind direction.
Joeri A. Frederik, Eric Simley, Kenneth A. Brown, Gopal R. Yalla, Lawrence C. Cheung, and Paul A. Fleming
Wind Energ. Sci., 10, 755–777, https://doi.org/10.5194/wes-10-755-2025, https://doi.org/10.5194/wes-10-755-2025, 2025
Short summary
Short summary
In this paper, we present results from advanced computer simulations to determine the effects of applying different control strategies to a small wind farm. We show that when there is variability in wind direction over height, steering the wake of a turbine away from other turbines is the most effective strategy. When this variability is not present, actively changing the pitch angle of the blades to increase turbulence in the wake could be more effective.
Piotr Fojcik, Edward Hart, and Emil Hedevang
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-17, https://doi.org/10.5194/wes-2025-17, 2025
Revised manuscript accepted for WES
Short summary
Short summary
Increasing the efficiency of wind farms can be achieved via reducing the impact of wakes: flow regions with lower wind speed occurring downwind from turbines. This work describes training and validation of a novel method for estimation of the wake effects impacting a turbine. The results show that for most tested wind conditions, the developed model is capable of robust detection of wake presence, and accurate characterisation of its properties. Further validation and improvements are planned.
Gopal R. Yalla, Kenneth Brown, Lawrence Cheung, Dan Houck, Nathaniel deVelder, and Nicholas Hamilton
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2025-14, https://doi.org/10.5194/wes-2025-14, 2025
Revised manuscript under review for WES
Short summary
Short summary
When wind reaches the first set of turbines in a wind farm, energy is extracted, reducing the energy available for downstream turbines. This study examines emerging technologies aimed at re-energizing the wind between turbines in a wind farm to improve overall power production. Optimizing these technologies depends on understanding complex features of the atmosphere and the wakes behind turbines, which is accomplished using high fidelity computer simulations and data analysis techniques.
Peter Bachant, Peter Ireland, Brian Burrows, Chi Qiao, James Duncan, Danian Zheng, and Mohit Dua
Wind Energ. Sci., 9, 2235–2259, https://doi.org/10.5194/wes-9-2235-2024, https://doi.org/10.5194/wes-9-2235-2024, 2024
Short summary
Short summary
Intentional misalignment of upstream turbines in wind plants in order to steer wakes away from downstream turbines has been a topic of research interest for years but has not yet achieved widespread commercial adoption. We deploy one such wake steering system to a utility-scale wind plant and then create a model to predict plant behavior and enable successful control. We apply calibrations to a physics-based model and use machine learning to correct its outputs to improve predictive capability.
Matteo Baricchio, Pieter M. O. Gebraad, and Jan-Willem van Wingerden
Wind Energ. Sci., 9, 2113–2132, https://doi.org/10.5194/wes-9-2113-2024, https://doi.org/10.5194/wes-9-2113-2024, 2024
Short summary
Short summary
Wake steering can be integrated into wind farm layout optimization through a co-design approach. This study estimates the potential of this method for a wide range of realistic conditions, adopting a tailored genetic algorithm and novel geometric yaw relations. A gain in the annual energy yield between 0.3 % and 0.4 % is obtained for a 16-tubrine farm, and a multi-objective implementation is used to limit loss in the case that wake steering is not used during farm operation.
Felix Bestehorn, Florian Bürgel, Christian Kirches, Sebastian Stiller, and Andreas M. Tillmann
Wind Energ. Sci. Discuss., https://doi.org/10.5194/wes-2024-120, https://doi.org/10.5194/wes-2024-120, 2024
Revised manuscript accepted for WES
Short summary
Short summary
Wind turbines organized in wind farms are an important electric power source. Thereby, each wind turbine causes a so-called wake with a reduced wind speed. This can influence following wind turbines and is an opportunity to optimize the operation of the complete wind farm, i.e., we steer the wakes to increase the total power output of the wind farm. In order to do this efficiently, we exploit repetitive structures within a wind farm.
Elie Kadoche, Pascal Bianchi, Florence Carton, Philippe Ciblat, and Damien Ernst
Wind Energ. Sci., 9, 1577–1594, https://doi.org/10.5194/wes-9-1577-2024, https://doi.org/10.5194/wes-9-1577-2024, 2024
Short summary
Short summary
This work proposes a new wind farm controller based on wind predictions and conducts a synthetic sensitivity analysis of wake steering and the variations of the wind direction. For wind turbines that can rotate from −15 to 15° every 10 min, if the wind direction changes by more than 7.34° every 10 min, it is important to consider future wind data in a steady-state yaw control optimization.
Simone Tamaro, Filippo Campagnolo, and Carlo L. Bottasso
Wind Energ. Sci., 9, 1547–1575, https://doi.org/10.5194/wes-9-1547-2024, https://doi.org/10.5194/wes-9-1547-2024, 2024
Short summary
Short summary
We develop a new simple model to predict power losses incurred by a wind turbine when it yaws out of the wind. The model reveals the effects of a number of rotor design parameters and how the turbine is governed when it yaws. The model exhibits an excellent agreement with large eddy simulations and wind tunnel measurements. We showcase the capabilities of the model by deriving the power-optimal yaw strategy for a single turbine and for a cluster of wake-interacting turbines.
Maarten J. van den Broek, Marcus Becker, Benjamin Sanderse, and Jan-Willem van Wingerden
Wind Energ. Sci., 9, 721–740, https://doi.org/10.5194/wes-9-721-2024, https://doi.org/10.5194/wes-9-721-2024, 2024
Short summary
Short summary
Wind turbine wakes negatively affect wind farm performance as they impinge on downstream rotors. Wake steering reduces these losses by redirecting wakes using yaw misalignment of the upstream rotor. We develop a novel control strategy based on model predictions to implement wake steering under time-varying conditions. The controller is tested in a high-fidelity simulation environment and improves wind farm power output compared to a state-of-the-art reference controller.
Eric Simley, Dev Millstein, Seongeun Jeong, and Paul Fleming
Wind Energ. Sci., 9, 219–234, https://doi.org/10.5194/wes-9-219-2024, https://doi.org/10.5194/wes-9-219-2024, 2024
Short summary
Short summary
Wake steering is a wind farm control technology in which turbines are misaligned with the wind to deflect their wakes away from downstream turbines, increasing total power production. In this paper, we use a wind farm control model and historical electricity prices to assess the potential increase in market value from wake steering for 15 US wind plants. For most plants, we find that the relative increase in revenue from wake steering exceeds the relative increase in energy production.
Nick Janssens and Johan Meyers
Wind Energ. Sci., 9, 65–95, https://doi.org/10.5194/wes-9-65-2024, https://doi.org/10.5194/wes-9-65-2024, 2024
Short summary
Short summary
Proper wind farm control may vastly contribute to Europe's plan to go carbon neutral. However, current strategies don't account for turbine–wake interactions affecting power extraction. High-fidelity models (e.g., LES) are needed to accurately model this but are considered too slow in practice. By coarsening the resolution, we were able to design an efficient LES-based controller with real-time potential. This may allow us to bridge the gap towards practical wind farm control in the near future.
Filippo Gori, Sylvain Laizet, and Andrew Wynn
Wind Energ. Sci., 8, 1425–1451, https://doi.org/10.5194/wes-8-1425-2023, https://doi.org/10.5194/wes-8-1425-2023, 2023
Short summary
Short summary
Wake steering is a promising strategy to increase the power output of modern wind farms by mitigating the negative effects of aerodynamic interaction among turbines. As farm layouts grow in size to meet renewable targets, the complexity of wake steering optimisation increases too. With the objective of enabling robust and predictable wake steering solutions, this study investigates the sensitivity of wake steering optimisation for three different farm layouts with increasing complexity levels.
Daniel van den Berg, Delphine de Tavernier, and Jan-Willem van Wingerden
Wind Energ. Sci., 8, 849–864, https://doi.org/10.5194/wes-8-849-2023, https://doi.org/10.5194/wes-8-849-2023, 2023
Short summary
Short summary
Wind turbines placed in farms interact with their wake, lowering the power production of the wind farm. This can be mitigated using so-called wake mixing techniques. This work investigates the coupling between the pulse wake mixing technique and the motion of floating wind turbines using the pulse. Frequency response experiments and time domain simulations show that extra movement is undesired and that the
optimalexcitation frequency is heavily platform dependent.
Balthazar Arnoldus Maria Sengers, Gerald Steinfeld, Paul Hulsman, and Martin Kühn
Wind Energ. Sci., 8, 747–770, https://doi.org/10.5194/wes-8-747-2023, https://doi.org/10.5194/wes-8-747-2023, 2023
Short summary
Short summary
The optimal misalignment angles for wake steering are determined using wake models. Although mostly analytical, data-driven models have recently shown promising results. This study validates a previously proposed data-driven model with results from a field experiment using lidar measurements. In a comparison with a state-of-the-art analytical model, it shows systematically more accurate estimates of the available power. Also when using only commonly available input data, it gives good results.
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).
Mou Lin and Fernando Porté-Agel
Wind Energ. Sci., 7, 2215–2230, https://doi.org/10.5194/wes-7-2215-2022, https://doi.org/10.5194/wes-7-2215-2022, 2022
Short summary
Short summary
Large-eddy simulation (LES) is a widely used method to study wind turbine flow. To save computational resources, the turbine-inducing forces in LES are often modelled by parametrisations. We validate three widely used turbine parametrisations in LES in different yaw and offset configurations with wind tunnel measurements, and we find that, in comparison with other parametrisations, the blade element actuator disk model strikes a good balance of accuracy and computational cost.
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.
Marcus Becker, Bastian Ritter, Bart Doekemeijer, Daan van der Hoek, Ulrich Konigorski, Dries Allaerts, and Jan-Willem van Wingerden
Wind Energ. Sci., 7, 2163–2179, https://doi.org/10.5194/wes-7-2163-2022, https://doi.org/10.5194/wes-7-2163-2022, 2022
Short summary
Short summary
In this paper we present a revised dynamic control-oriented wind farm model. The model can simulate turbine wake behaviour in heterogeneous and changing wind conditions at a very low computational cost. It utilizes a three-dimensional turbine wake model which also allows capturing vertical wind speed differences. The model could be used to maximise the power generation of with farms, even during events like a wind direction change. It is publicly available and open for further development.
Julian Quick, Ryan N. King, Garrett Barter, and Peter E. Hamlington
Wind Energ. Sci., 7, 1941–1955, https://doi.org/10.5194/wes-7-1941-2022, https://doi.org/10.5194/wes-7-1941-2022, 2022
Short summary
Short summary
Wake steering is an emerging wind power plant control strategy where upstream turbines are intentionally yawed out of alignment with the incoming wind, thereby steering wakes away from downstream turbines. Trade-offs between the gains in power production and fatigue loads induced by this control strategy are the subject of continuing investigation. In this study, we present an optimization approach for efficiently exploring the trade-offs between power and loading during wake steering.
Florian Pöschke and Horst Schulte
Wind Energ. Sci., 7, 1593–1604, https://doi.org/10.5194/wes-7-1593-2022, https://doi.org/10.5194/wes-7-1593-2022, 2022
Short summary
Short summary
The paper compares two different strategies for wind turbine control when following a power command. A model-based control scheme for a 5 MW wind turbine is designed, and a comparison in terms of the mechanical loading and the attainable power dynamics is drawn based on simulation studies. Reduced-order models suitable for integration into an upper-level control design are discussed. The dependence of the turbine behavior on the chosen strategy is illustrated and analyzed.
Balthazar Arnoldus Maria Sengers, Matthias Zech, Pim Jacobs, Gerald Steinfeld, and Martin Kühn
Wind Energ. Sci., 7, 1455–1470, https://doi.org/10.5194/wes-7-1455-2022, https://doi.org/10.5194/wes-7-1455-2022, 2022
Short summary
Short summary
Wake steering aims to redirect the wake away from a downstream turbine. This study explores the potential of a data-driven surrogate model whose equations can be interpreted physically. It estimates wake characteristics from measurable input variables by utilizing a simple linear model. The model shows encouraging results in estimating available power in the far wake, with significant improvements over currently used analytical models in conditions where wake steering is deemed most effective.
Daan van der Hoek, Joeri Frederik, Ming Huang, Fulvio Scarano, Carlos Simao Ferreira, and Jan-Willem van Wingerden
Wind Energ. Sci., 7, 1305–1320, https://doi.org/10.5194/wes-7-1305-2022, https://doi.org/10.5194/wes-7-1305-2022, 2022
Short summary
Short summary
The paper presents a wind tunnel experiment where dynamic induction control was implemented on a small-scale turbine. By periodically changing the pitch angle of the blades, the low-velocity turbine wake is perturbed, and hence it recovers at a faster rate. Small particles were released in the flow and subsequently recorded with a set of high-speed cameras. This allowed us to reconstruct the flow behind the turbine and investigate the effect of dynamic induction control on the wake.
Cited articles
Becker, M., Allaerts, D., and van Wingerden, J. W.: FLORIDyn – A dynamic and flexible framework for real-time wind farm control, J. Phys. Conf. Ser., 2265, 032103, https://doi.org/10.1088/1742-6596/2265/3/032103, 2022. a
Bleeg, J., Purcell, M., Ruisi, R., and Traiger, E.: Wind farm blockage and the consequences of neglecting its impact on energy production, Energies, 11, 1609, https://doi.org/10.3390/en11061609, 2018. a
Boersma, S., Doekemeijer, B. M., Gebraad, P. M., Fleming, P. A., Annoni, J., Scholbrock, A. K., Frederik, J. A., and van Wingerden, J.-W.: A tutorial on control-oriented modeling and control of wind farms, in: 2017 American control conference (ACC), Seattle, WA, USA, 24–26 May 2017, IEEE, 1–18, https://doi.org/10.23919/ACC.2017.7962923, 2017. a, b
Bossanyi, E. and Ruisi, R.: Axial induction controller field test at Sedini wind farm, Wind Energ. Sci., 6, 389–408, https://doi.org/10.5194/wes-6-389-2021, 2021. a
Braun, M., Gruhl, C., Hans, C. A., Härtel, P., Scholz, C., Sick, B., Siefert, M., Steinke, F., Stursberg, O., and von Berg, S. W.: Predictions and Decision Making for Resilient Intelligent Sustainable Energy Systems, arXiv [preprint], https://doi.org/10.48550/arXiv.2407.03021, 2024. a
Daenens, S., Vervlimmeren, I., Verstraeten, T., Daems, P.-J., Nowé, A., and Helsen, J.: Power prediction using high-resolution SCADA data with a farm-wide deep neural network approach, J. Phys. Conf. Ser., 2767, 092014, https://doi.org/10.1088/1742-6596/2767/9/092014, 2024. a
Fleming, P., King, J., Simley, E., Roadman, J., Scholbrock, A., Murphy, P., Lundquist, J. K., Moriarty, P., Fleming, K., van Dam, J., Bay, C., Mudafort, R., Jager, D., Skopek, J., Scott, M., Ryan, B., Guernsey, C., and Brake, D.: Continued results from a field campaign of wake steering applied at a commercial wind farm – Part 2, Wind Energ. Sci., 5, 945–958, https://doi.org/10.5194/wes-5-945-2020, 2020. a
Fleming, P. A., Ning, A., Gebraad, P. M., and Dykes, K.: Wind plant system engineering through optimization of layout and yaw control, Wind Energy, 19, 329–344, 2016. a
Foloppe, B., Munters, W., Buckingham, S., Vandevelde, L., and van Beeck, J.: Coupling of a dynamic wake model with WRF: a case study of the Belgian wind farms, in: 18th EAWE PhD Seminar, Bruges, Belgium,, 2 to 4 November 2022, 30–31, 2022. a
Gal, Y. and Ghahramani, Z.: Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning, in: Proceedings of The 33rd International Conference on Machine Learning, edited by: Balcan, M. F. and Weinberger, K. Q., vol. 48 of Proceedings of Machine Learning Research, PMLR, New York, New York, USA, 1050–1059, https://proceedings.mlr.press/v48/gal16.html (last access: 25 July 2024), 2016. a
Gebraad, P. M. and Van Wingerden, J.: A control-oriented dynamic model for wakes in wind plants, J. Phys. Conf. Ser., 524, 012186, https://doi.org/10.1088/1742-6596/524/1/012186, 2014. a
IEA: Renewables 2022 – Analysis and forecast to 2027, https://iea.blob.core.windows.net/assets/ada7af90-e280-46c4-a577-df2e4fb44254/Renewables2022.pdf (last access: 25 July 2024), 2022. a
Jensen, N. O.: A note on wind generator interaction, vol. 2411, Citeseer, https://backend.orbit.dtu.dk/ws/portalfiles/portal/55857682/ris_m_2411.pdf (last access: 25 July 2024), 1983. a
Kölle, K., Göçmen, T., Garcia-Rosa, P. B., Petrović, V., Eguinoa, I., Vrana, T. K., Long, Q., Pettas, V., Anand, A., Barlas, T. K., Cutululis, N., Manjock, A., Tande, J. O., Ruisi, R., and Bossanyi, E.: Towards integrated wind farm control: Interfacing farm flow and power plant controls, Advanced Control for Applications: Engineering and Industrial Systems, 4, e105, https://doi.org/10.1002/adc2.105, 2022. a
Larsen, G. C., Madsen, H. A., Bingöl, F., Mann, J., Ott, S., Sorensen, J. N., Okulov, V., Troldborg, N., Nielsen, M., Thomsen, K., Larsen, T. J., and Mikkelsen, R.: Dynamic wake meandering modeling, ISBN 978-87-550-3602-4, https://www.osti.gov/etdeweb/servlets/purl/20941220#page=1.00&gsr=0 (last access: 25 July 2024), 2007. a
Laves, M.-H., Ihler, S., Fast, J. F., Kahrs, L. A., and Ortmaier, T.: Well-calibrated regression uncertainty in medical imaging with deep learning, in: Medical Imaging with Deep Learning, PMLR, 393–412, https://proceedings.mlr.press/v121/laves20a/laves20a.pdf (last access: 25 July 2024), 2020. a
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, 2015. a
Lee, J. C. Y. and Fields, M. J.: An overview of wind-energy-production prediction bias, losses, and uncertainties, Wind Energ. Sci., 6, 311–365, https://doi.org/10.5194/wes-6-311-2021, 2021. a
Lin, Z. and Liu, X.: Wind power forecasting of an offshore wind turbine based on high-frequency SCADA data and deep learning neural network, Energy, 201, 117693, https://doi.org/10.1016/j.energy.2020.117693, 2020. a
Liu, T., Huang, Z., Tian, L., Zhu, Y., Wang, H., and Feng, S.: Enhancing wind turbine power forecast via convolutional neural network, Electronics, 10, 261, https://doi.org/10.3390/electronics10030261, 2021. a
Martínez-Tossas, L. A., Annoni, J., Fleming, P. A., and Churchfield, M. J.: The aerodynamics of the curled wake: a simplified model in view of flow control, Wind Energ. Sci., 4, 127–138, https://doi.org/10.5194/wes-4-127-2019, 2019. a
Martínez-Tossas, L. A., King, J., Quon, E., Bay, C. J., Mudafort, R., Hamilton, N., Howland, M. F., and Fleming, P. A.: The curled wake model: a three-dimensional and extremely fast steady-state wake solver for wind plant flows, Wind Energ. Sci., 6, 555–570, https://doi.org/10.5194/wes-6-555-2021, 2021. a
Meyers, J., Bottasso, C., Dykes, K., Fleming, P., Gebraad, P., Giebel, G., Göçmen, T., and van Wingerden, J.-W.: Wind farm flow control: prospects and challenges, Wind Energ. Sci., 7, 2271–2306, https://doi.org/10.5194/wes-7-2271-2022, 2022. a
Nejad, A. R., Keller, J., Guo, Y., Sheng, S., Polinder, H., Watson, S., Dong, J., Qin, Z., Ebrahimi, A., Schelenz, R., Gutiérrez Guzmán, F., Cornel, D., Golafshan, R., Jacobs, G., Blockmans, B., Bosmans, J., Pluymers, B., Carroll, J., Koukoura, S., Hart, E., McDonald, A., Natarajan, A., Torsvik, J., Moghadam, F. K., Daems, P.-J., Verstraeten, T., Peeters, C., and Helsen, J.: Wind turbine drivetrains: state-of-the-art technologies and future development trends, Wind Energ. Sci., 7, 387–411, https://doi.org/10.5194/wes-7-387-2022, 2022. a
NREL: OpenFAST, https://github.com/OpenFAST/openfast, GitHub [code], https://github.com/OpenFAST/openfast (last access: 25 July 2024), 2025a. a
NREL: FLORIS Wake Modeling and Wind Farm Controls Software (FLORIS v3.4.1), GitHub [code], https://github.com/NREL/floris (last access: 25 July 2024), 2025b. a
NREL: Simulator fOr Wind Farm Applications (SOWFA), https://github.com/NREL/SOWFA, GitHub [code], https://github.com/NREL/SOWFA (last access: 25 July 2024), 2025c. a
Nygaard, N. G., Steen, S. T., Poulsen, L., and Pedersen, J. G.: Modelling cluster wakes and wind farm blockage, J. Phys. Conf. Ser., 1618, 062072, https://doi.org/10.1088/1742-6596/1618/6/062072, 2020. a
Park, J. and Park, J.: Physics-induced graph neural network: An application to wind-farm power estimation, Energy, 187, 115883, https://doi.org/10.1016/j.energy.2019.115883, 2019. a
Perez-Sanjines, F., Verstraeten, T., Nowé, A., and Helsen, J.: Deep ensemble with Neural Networks to model power curve uncertainty, J. Phys. Conf. Ser., 2362, 012029, https://doi.org/10.1088/1742-6596/2362/1/012029, 2022. a, b
Pettas, V., Kretschmer, M., Clifton, A., and Cheng, P. W.: On the effects of inter-farm interactions at the offshore wind farm Alpha Ventus, Wind Energ. Sci., 6, 1455–1472, https://doi.org/10.5194/wes-6-1455-2021, 2021. a
Piotrowski, P., Rutyna, I., Baczyński, D., and Kopyt, M.: Evaluation metrics for wind power forecasts: A comprehensive review and statistical analysis of errors, Energies, 15, 9657, https://doi.org/10.3390/en15249657, 2022. a
Pombo, D. V., Göçmen, T., Das, K., and Sørensen, P.: Multi-horizon data-driven wind power forecast: From nowcast to 2 days-ahead, in: 2021 International Conference on Smart Energy Systems and Technologies (SEST), 1–6, https://doi.org/10.1109/SEST50973.2021.9543173, 2021. a
Porté-Agel, F., Bastankhah, M., and Shamsoddin, S.: Wind-turbine and wind-farm flows: A review, Boundary-Lay. Meteorol., 174, 1–59, https://doi.org/10.1007/s10546-019-00473-0, 2020. a, b
Schepers, J.: WakeFarm: nabij zog model en ongestoord wind snelheidsveld, Energieonderzoek Centrum Nederland, Technical Report, ECN-C-98-016, 1998. a
Sood, I., Simon, E., Vitsas, A., Blockmans, B., Larsen, G. C., and Meyers, J.: Comparison of large eddy simulations against measurements from the Lillgrund offshore wind farm, Wind Energ. Sci., 7, 2469–2489, https://doi.org/10.5194/wes-7-2469-2022, 2022. a
Strickland, J. M., Gadde, S. N., and Stevens, R. J.: Wind farm blockage in a stable atmospheric boundary layer, Renewable Energy, 197, 50–58, https://doi.org/10.1016/j.renene.2022.07.108, 2022. a
University of Hannover: Parallelized Large-Eddy Simulation Model (PALM), GitLab [code], https://gitlab.palm-model.org/releases/palm_model_system (last access: 25 July 2024), 2021. a
Van Der Laan, M., Pena, A., Volker, P., Hansen, K. S., Sørensen, N. N., Ott, S., and Hasager, C. B.: Challenges in simulating coastal effects on an offshore wind farm, J. Phys. Conf. Ser., 854, 012046, https://doi.org/10.1088/1742-6596/854/1/012046, 2017. a
Verstraeten, T., Nowé, A., Keller, J., Guo, Y., Sheng, S., and Helsen, J.: Fleetwide data-enabled reliability improvement of wind turbines, Renew. Sust. Energ. Rev., 109, 428–437, 2019. a
Verstraeten, T., Daems, P.-J., Bargiacchi, E., Roijers, D. M., Libin, P. J., and Helsen, J.: Scalable optimization for wind farm control using coordination graphs, arXiv [preprint], https://doi.org/10.48550/arXiv.2101.07844, 2021. a
Wang, H.-Z., Li, G.-Q., Wang, G.-B., Peng, J.-C., Jiang, H., and Liu, Y.-T.: Deep learning based ensemble approach for probabilistic wind power forecasting, Appl. Energ., 188, 56–70, 2017. a
Wang, Y., Zou, R., Liu, F., Zhang, L., and Liu, Q.: A review of wind speed and wind power forecasting with deep neural networks, Appl. Energ., 304, 117766, https://doi.org/10.1016/j.apenergy.2021.117766, 2021. a
Yin, X. and Zhao, X.: Big data driven multi-objective predictions for offshore wind farm based on machine learning algorithms, Energy, 186, 115704, https://doi.org/10.1016/j.energy.2019.07.034, 2019. a
Zehtabiyan-Rezaie, N., Iosifidis, A., and Abkar, M.: Physics-guided machine learning for wind-farm power prediction: Toward interpretability and generalizability, PRX Energy, 2, 013009, https://doi.org/10.1103/PRXEnergy.2.013009, 2023. a, b
Short summary
Wind farms are crucial for a sustainable energy future. However, their power can fluctuate significantly due to changing weather conditions, which complexly affect their power generation. This paper presents a novel machine-learning-based method to enhance wind farm power predictions, enabling improved power scheduling, trading and grid balancing. This makes wind power more valuable and easier to integrate into the energy system.
Wind farms are crucial for a sustainable energy future. However, their power can fluctuate...
Altmetrics
Final-revised paper
Preprint