Abstract
Yaw misalignment, measured as the difference between the wind direction and the nacelle position of a wind turbine, has consequences on the power output, the safety and the lifetime of the turbine and its wind park as a whole. We use reinforcement learning to develop a yaw control agent to minimise yaw misalignment and optimally reallocate yaw resources, prioritising high-speed segments, while keeping yaw usage low. To achieve this, we carefully crafted and tested the reward metric to trade-off yaw usage versus yaw alignment (as proportional to power production), and created a novel simulator (environment) based on real-world wind logs obtained from a REpower MM82 2 MW turbine. The resulting algorithm decreased the yaw misalignment by 5.5% and 11.2% on two simulations of 2.7 h each, compared to the conventional active yaw control algorithm. The average net energy gain obtained was 0.31% and 0.33% respectively, compared to the traditional yaw control algorithm. On a single 2 MW turbine, this amounts to a 1.5 k–2.5 k euros annual gain, which sums up to very significant profits over an entire wind park.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
82 m rotor diameter, 8–11 GWh annual power production, 80 % of the time spent in region 2, cosine-cube power loss law, 0.09 euros per kWh.
References
Al-Addous, M., Jaradat, M., Albatayneh, A., Wellmann, J., Al Hmidan, S.: The significance of wind turbines layout optimization on the predicted farm energy yield. Atmosphere 11(1), 117 (2020)
Brockman, G., et al.: OpenAI gym (2016)
Burton, T., Sharpe, D., Jenkins, N., Bossanyi, E.: Wind Energy Handbook. John Wiley (2001). https://books.google.at/books?id=4UYm893y-34C
Dahlberg, J., Montgomerie, B.: Technical report, final report part 2, wake effects and other loads. Research program of the utgrunden demonstration offshore wind farm (2005)
Dalmas J., P.A.: Etude comparative de trois appareils pour la mesure d’alignement nacelle. In: 5th International Renewable Energy Congress (IREC) (2014)
Damiani, R., et al.: Assessment of wind turbine component loads under yaw-offset conditions. Wind Energy Sci. 3, 173–189 (2018)
Dijk, M., Wingerden, J.W., Ashuri, T., Li, Y., Rotea, M.: Yaw-misalignment and its impact on wind turbine loads and wind farm power output. J. Phys.: Conf. Ser. 753, 062013 (2016)
Dongran, R., et al.: Wind direction prediction for yaw control of wind turbines. Int. J. Control Autom. Syst. 15, 1720–1728 (2017). https://doi.org/10.1007/s12555-017-0289-6
Dongran, S., Li, L., Yang, J., Joo, Y.H.: A model predictive control for the yaw control system of horizontal-axis wind turbines. Energy Procedia 158, 237–242 (2019)
Dzulfikri, Z., Nuryanti, N., Erdani, Y.: Design and implementation of artificial neural networks to predict wind directions on controlling yaw of wind turbine prototype. J. Robot. Control (JRC) 1(1), 20–26 (2019)
Farret, F., Pfitscher, L., Bernardon, D.: Sensorless active yaw control for wind turbines. In: IECON 2001. 27th Annual Conference of the IEEE Industrial Electronics Society, vol. 2, pp. 1370–1375 (2001)
Fleming, P.A., et al.: Field-test results using a nacelle-mounted lidar for improving wind turbine power capture by reducing yaw misalignment. In: Journal of Physics: Conference Series, vol. 524 (2014)
Fleming, P., et al.: Simulation comparison of wake mitigation control strategies for a two-turbine case. Wind Energy 18(12), 2135–2143 (2015)
Kragh, K., Hansen, M.: Potential of power gain with improved yaw alignment. Wind Energy 18(6), 979–989 (2015)
Mademlis, C., Mesemanolis, A., Karakasis, N., Nalmpantis, T.: Active yaw control in a horizontal axis wind system without requiring wind direction measurement. IET Renew. Power Gener. 10(9), 1441–1449 (2016)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035 (2019)
Pedersen, M.: Yaw misalignment and power curve analysis. EWEA Analysis of operating wind farms (2016)
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1–8 (2021). https://jmlr.org/papers/v22/20-1364.html
Saenz-Aguirre, A., et al.: Artificial neural network based reinforcement learning for wind turbine yaw control. Energies 12, 436 (2019)
Saenz-Aguirre, A., Zulueta, E., Fernandez-Gamiz, U., Ulazia, A., Teso-Fz-Betono, D.: Performance enhancement of the artificial neural network-based reinforcement learning for wind turbine yaw control. Wind Energy 23(3), 676–690 (2020)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Urbán, A.M., Liew, J., Dellwik, E., Larsen, G.C.: The effect of wake position and yaw misalignment on power loss in wind turbines. J. Phys.: Conf. Ser. 1222(1) (2019)
Venkata, S., Krishnamurthy, S.: Wind energy explained: theory, design, and application. Power Energy Mag. IEEE 1, 50–51 (2003)
Wan, S., Cheng, L., Sheng, X.: Effects of yaw error on wind turbine running characteristics based on the equivalent wind speed model. Energies 8(7), 6286–6301 (2015)
Acknowledgements
We would like to thank Mohamed Alami Chehbourne from LIX as well as Walter Telsnig, Anatoliy Zabrovskiy and Martin Göldner from DEIF for the helpful discussions and insights on the topic during the preparation of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Puech, A., Read, J. (2023). An Improved Yaw Control Algorithm for Wind Turbines via Reinforcement Learning. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13717. Springer, Cham. https://doi.org/10.1007/978-3-031-26419-1_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-26419-1_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26418-4
Online ISBN: 978-3-031-26419-1
eBook Packages: Computer ScienceComputer Science (R0)
