Evaluating Meteorological Effects on Wind Turbine Performance: Anomaly Analysis and Energy Loss Quantification

Year 2026, Volume: 15 Issue: 1, 492 - 505, 24.03.2026

Gökhan Yüksek

https://doi.org/10.17798/bitlisfen.1841878

https://izlik.org/JA77KE48RY

Abstract

This study investigates how ordinary atmospheric conditions induce systematic deviations from the nominal manufacturer's power curve of a modern wind turbine using a residual-based comparative power curve analysis. The approach directly compares theoretical power values with turbine-level SCADA measurements. It evaluates the difference between predicted and measured power as a continuous indicator of relative underperformance rather than as a classified anomaly. The dataset comprises wind speed, wind direction, air density, ambient temperature, cloud cover, solar irradiance, and measured electrical power from a Nordex N117/3600 wind turbine over a full annual period, complemented by temporally synchronized atmospheric data. Power residuals are analyzed as functions of wind speed and paired meteorological variables to reveal recurring deviation patterns and their physical context. The cumulative integration of positive residuals indicates an annual energy production loss of approximately 244,481 kWh, demonstrating that small but persistent power-curve departures accumulate into a substantial long-term deficit. The results show that performance deviations concentrate primarily in the partially loaded operating region and are strongly associated with variations in air density and wind regime. At the same time, temperature and radiative variables play a secondary role. The main contribution of this study is the presentation of a physically interpretable, residual-based performance deviation analysis that links power curve departures directly to atmospheric conditions and quantifies their cumulative energy impact without relying on predictive models or formal anomaly detection algorithms

Keywords

Wind turbine performance , Power curve anomaly detection , Energy loss quantification , Atmospheric effects , Wind energy assessment , Operational data analysis

Ethical Statement

This study does not involve human participants or animals. All analyses are based on operational wind turbine and meteorological data obtained from existing measurement systems. No ethical approval was required for this research.

Supporting Institution

No specific funding or institutional support was received for this study.

References

• M. C. Alexiadis, P. S. Dokopoulos, H. S. Sahsamanoglou, and I. M. Manousaridis, "Short-term forecasting of wind speed and related electrical power," Solar Energy, vol. 63, no. 1, pp. 61–68, Jul. 1998, doi: 10.1016/S0038-092X(98)00032-2.
• T. Mahmoud, Z. Y. Dong, and J. Ma, "Advanced method for short‐term wind power prediction with multiple observation points using extreme learning machines," The Journal of Engineering, vol. 2018, no. 1, pp. 29–38, Jan. 2018, doi: 10.1049/joe.2017.0338.
• Nordex SE., “Nordex N117/3600 wind turbine specifications,” https://www.nordex-online.com/en/product/n117-3600/.
• X. Chen, X. Zhang, M. Dong, L. Huang, Y. Guo, and S. He, "Deep Learning-Based Prediction of Wind Power for Multi-turbines in a Wind Farm," Front. Energy Res., vol. 9, Jul. 2021, doi: 10.3389/fenrg.2021.723775.
• N. Kirchner-Bossi, G. Kathari, and F. Porté-Agel, "A hybrid physics-based and data-driven model for intra-day and day-ahead wind power forecasting considering a drastically expanded predictor search space," Appl. Energy, vol. 367, p. 123375, Aug. 2024, doi: 10.1016/j.apenergy.2024.123375.
• Y. Liu, J. Wang, and L. Liu, "Physics-informed reinforcement learning for probabilistic wind power forecasting under extreme events," Appl. Energy, vol. 376, p. 124068, Dec. 2024, doi: 10.1016/j.apenergy.2024.124068.
• F. Ye, J. Brodie, T. Miles, and A. Aziz Ezzat, "AIRU-WRF: A physics-guided spatio-temporal wind forecasting model and its application to the U.S. Mid Atlantic offshore wind energy areas," Renew. Energy, vol. 223, p. 119934, Mar. 2024, doi: 10.1016/j.renene.2023.119934.
• E. Zhao, S. Sun, and S. Wang, "New developments in wind energy forecasting with artificial intelligence and big data: a scientometric insight," Data Science and Management, vol. 5, no. 2, pp. 84–95, Jun. 2022, doi: 10.1016/j.dsm.2022.05.002.
• P. Ekanayake, O. Panahatipola, and J. Jayasinghe, "Development of wind energy prediction models using statistical, machine learning and hybrid techniques: a case study," J. Natl. Sci. Found., vol. 50, no. 2, p. 503, Sep. 2022, doi: 10.4038/jnsfsr.v50i2.10591.
• M. Li, M. Yang, Y. Yu, and W.-J. Lee, "A Wind Speed Correction Method Based on Modified Hidden Markov Model for Enhancing Wind Power Forecast," IEEE Trans. Ind. Appl., vol. 58, no. 1, pp. 656–666, Jan. 2022, doi: 10.1109/TIA.2021.3127145.
• K. L. Jorgensen and H. R. Shaker, "Wind Power Forecasting Using Machine Learning: State of the Art, Trends and Challenges," in 2020 IEEE 8th International Conference on Smart Energy Grid Engineering (SEGE), IEEE, Aug. 2020, pp. 44–50. doi: 10.1109/SEGE49949.2020.9181870.
• D. Alves, F. Mendonça, S. S. Mostafa, and F. Morgado-Dias, "The Potential of Machine Learning for Wind Speed and Direction Short-Term Forecasting: A Systematic Review," Computers, vol. 12, no. 10, p. 206, Oct. 2023, doi: 10.3390/computers12100206.
• Y. Zheng et al., "New ridge regression, artificial neural networks and support vector machine for wind speed prediction," Advances in Engineering Software, vol. 179, p. 103426, May 2023, doi: 10.1016/j.advengsoft.2023.103426.
• D. Zafirakis, G. Tzanes, and J. K. Kaldellis, "Forecasting of Wind Power Generation with the Use of Artificial Neural Networks and Support Vector Regression Models," Energy Procedia, vol. 159, pp. 509–514, Feb. 2019, doi: 10.1016/j.egypro.2018.12.007.
• H. Demolli, A. S. Dokuz, A. Ecemis, and M. Gokcek, "Wind power forecasting based on daily wind speed data using machine learning algorithms," Energy Convers. Manag., vol. 198, p. 111823, Oct. 2019, doi: 10.1016/j.enconman.2019.111823.
• J. Zhang, Z. Zhao, J. Yan, and P. Cheng, "Ultra-Short-Term Wind Power Forecasting Based on CGAN-CNN-LSTM Model Supported by Lidar," Sensors, vol. 23, no. 9, p. 4369, Apr. 2023, doi: 10.3390/s23094369.
• M. A. A. Al-qaness, A. A. Ewees, A. O. Aseeri, and M. Abd Elaziz, "Wind power forecasting using optimized LSTM by attraction–repulsion optimization algorithm," Ain Shams Engineering Journal, vol. 15, no. 12, p. 103150, Dec. 2024, doi: 10.1016/j.asej.2024.103150.
• Z. Zhao et al., "Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features," Eng. Appl. Artif. Intell., vol. 121, p. 105982, May 2023, doi: 10.1016/j.engappai.2023.105982.
• Y. Xiao, C. Zou, H. Chi, and R. Fang, "Boosted GRU model for short-term forecasting of wind power with feature-weighted principal component analysis," Energy, vol. 267, p. 126503, Mar. 2023, doi: 10.1016/j.energy.2022.126503.
• B. Erisen, "Wind Turbine Scada Dataset," https://www.kaggle.com/datasets/berkerisen/wind-turbine-scada-dataset/data.
• G. Yüksek, “Optimized GDTP-XGBoost Framework for Wind Power Forecasting Toward Condition-Based Maintenance,” Eksploatacja i Niezawodność – Maintenance and Reliability, Nov. 2025, doi: 10.17531/ein/214376.
• R. Gelaro et al., "The Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2)," J. Clim., vol. 30, no. 14, pp. 5419–5454, Jul. 2017, doi: 10.1175/JCLI-D-16-0758.1.
• J. F. Manwell, J. G. McGowan, and A. L. Rogers, Wind Energy Explained. Wiley, 2009. doi: 10.1002/9781119994367.
• T. Burton, N. Jenkins, D. Sharpe, and E. Bossanyi, Wind Energy Handbook. Wiley, 2011. doi: 10.1002/9781119992714.
• J. B. Olson et al., "Improving Wind Energy Forecasting through Numerical Weather Prediction Model Development," Bull. Am. Meteorol. Soc., vol. 100, no. 11, pp. 2201–2220, Nov. 2019, doi: 10.1175/BAMS-D-18-0040.1.
• M. Rezamand, M. Kordestani, R. Carriveau, D. S.-K. Ting, M. E. Orchard, and M. Saif, "Critical Wind Turbine Components Prognostics: A Comprehensive Review," IEEE Trans. Instrum. Meas., vol. 69, no. 12, pp. 9306–9328, Dec. 2020, doi: 10.1109/TIM.2020.3030165.