SCADA-Based AC Power Forecasting in a Utility-Scale PV Plant: Explainable HistGradientBoosting and Thermal Derating Quantification

Year 2026, Volume: 13 Issue: 1 , 452 - 482 , 31.03.2026

Hasan Uzel

https://doi.org/10.54287/gujsa.1818552

https://izlik.org/JA52DM97KL

Abstract

Accurate photovoltaic (PV) power modeling is essential for grid operation, short-term scheduling and plant-level decision making. However, reported performance in the literature varies widely due to differences in feature selection, forecast horizon definition and evaluation protocols. In particular, true exogenous forecasting is often conflated with contemporaneous power tracking, leading to optimistic accuracy estimates with limited operational relevance. This study aims to clarify how feature availability, evaluation design and operational intent shape reported performance in PV power modeling. A leakage-aware and operationally realistic framework is proposed that explicitly distinguishes between exogenous forecasting and operational tracking tasks. Using high-frequency SCADA data from a utility-scale PV plant, two modeling scenarios are evaluated. Scenario A relies exclusively on exogenous meteorological inputs and represents a forecasting-oriented inference task, whereas Scenario B augments these inputs with synchronous electrical current measurements and is interpreted as operational tracking (nowcasting) rather than forward-looking prediction. Multiple regression models, with emphasis on tree-based ensemble methods, are evaluated under transparent and scenario-consistent train–test splitting strategies. Model behavior is examined using post-hoc explainability tools to assess physical consistency and temperature-induced power derating is quantified using a semiparametric regression approach. The results indicate that exogenous-only models recover physically meaningful relationships but exhibit higher numerical errors than current-augmented configurations, reflecting the informational advantage of synchronous measurements rather than improved forecasting capability. Rather than claiming superior numerical accuracy, this work demonstrates how modeling assumptions and evaluation choices directly influence reported performance and its interpretation. By aligning feature availability with operational intent, the proposed framework provides practical guidance for the development, evaluation and deployment of PV power models in real-world applications.

Keywords

Photovoltaic (PV) , SCADA , AC Power Forecasting , HistGBDT , Thermal Derating

Ethical Statement

This study does not involve human participants, animals, or sensitive data, and therefore does not require ethical approval. The research was conducted using publicly available or institutionally collected SCADA data.

Supporting Institution

No financial or institutional support was received for this study.

Thanks

The author gratefully acknowledges the support and encouragement of his family during the preparation of this manuscript.

References

• Alcañiz, A., Grzebyk, D., Ziar, H., & Isabella, O. (2023). Trends and gaps in photovoltaic power forecasting with machine learning. Energy Reports, 9, 447–471. https://doi.org/10.1016/J.EGYR.2022.11.208
• Antonanzas, J., Osorio, N., Escobar, R., Urraca, R., Martinez-de-Pison, F. J., & Antonanzas-Torres, F. (2016). Review of photovoltaic power forecasting. Solar Energy, 136, 78–111. https://doi.org/10.1016/J.SOLENER.2016.06.069
• Barhmi, K., Heynen, C., Golroodbari, S., & van Sark, W. (2024). A Review of Solar Forecasting Techniques and the Role of Artificial Intelligence. Solar 2024, Vol. 4, Pages 99-135, 4(1), 99–135. https://doi.org/10.3390/SOLAR4010005
• Bergmeir, C., Hyndman, R. J., & Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120, 70–83. https://doi.org/10.1016/J.CSDA.2017.11.003
• Böök, H., & Lindfors, A. V. (2020). Site-specific adjustment of a NWP-based photovoltaic production forecast. Solar Energy, 211, 779–788. https://doi.org/10.1016/J.SOLENER.2020.10.024
• Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (2017). Classification and regression trees. Classification and Regression Trees, 1–358. https://doi.org/10.1201/9781315139470
• Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13-17-Augu, 785–794. https://doi.org/10.1145/2939672.2939785
• Di Leo, P., Ciocia, A., Malgaroli, G., & Spertino, F. (2025). Advancements and Challenges in Photovoltaic Power Forecasting: A Comprehensive Review. Energies 2025, Vol. 18, Page 2108, 18(8), 2108. https://doi.org/10.3390/EN18082108
• Draper, N. R., & Smith, H. (2014). Applied regression analysis. In Applied Regression Analysis. wiley. https://doi.org/10.1002/9781118625590
• Dunn, P. K., & Smyth, G. K. (2005). Series evaluation of Tweedie exponential dispersion model densities. Statistics and Computing 2005 15:4, 15(4), 267–280. https://doi.org/10.1007/S11222-005-4070-Y
• Eseye, A. T., Zhang, J., & Zheng, D. (2018). Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information. Renewable Energy, 118, 357–367. https://doi.org/10.1016/J.RENENE.2017.11.011
• Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/AOS/1013203451
• Fu, J., Sun, Y., Li, Y., Wang, W., Wei, W., Ren, J., Han, S., & Di, H. (2025). An investigation of photovoltaic power forecasting in buildings considering shadow effects: Modeling approach and SHAP analysis. Renewable Energy, 245, 122821. https://doi.org/10.1016/J.RENENE.2025.122821
• Hyndman, R. J., & Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4), 679–688. https://doi.org/10.1016/J.IJFORECAST.2006.03.001
• Inman, R. H., Pedro, H. T. C., & Coimbra, C. F. M. (2013). Solar forecasting methods for renewable energy integration. Progress in Energy and Combustion Science, 39(6), 535–576. https://doi.org/10.1016/J.PECS.2013.06.002
• Kanagolkar, A. (n.d.). SolarGeneration. Retrieved September 30, 2025, from https://www.kaggle.com/datasets/arunkanagolkar/solargeneration/data
• Kuzlu, M., Cali, U., Sharma, V., & Güler, Ö. (2020). Gaining insight into solar photovoltaic power generation forecasting utilizing explainable artificial intelligence tools. IEEE Access, 8, 187814–187823. https://doi.org/10.1109/ACCESS.2020.3031477
• Lundberg, S. M., & Lee, S. I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 2017-December, 4766–4775. https://arxiv.org/pdf/1705.07874
• Nan, C., Hao, Y., Huang, X., Wang, H., & Yang, H. (2024). Investigation on temperature dependence of recent high-efficiency silicon solar modules. Solar Energy Materials and Solar Cells, 266, 112649. https://doi.org/10.1016/J.SOLMAT.2023.112649
• Perin Gasparin, F., Detzel Kipper, F., Schuck de Oliveira, F., & Krenzinger, A. (2022). Assessment on the variation of temperature coefficients of photovoltaic modules with solar irradiance. Solar Energy, 244, 126–133. https://doi.org/10.1016/J.SOLENER.2022.08.052
• Piantadosi, G., Dutto, S., Galli, A., De Vito, S., Sansone, C., & Di Francia, G. (2024). Photovoltaic power forecasting: A Transformer based framework. Energy and AI, 18, 100444. https://doi.org/10.1016/J.EGYAI.2024.100444
• Porawagamage, G., Dharmapala, K., Chaves, J. S., Villegas, D., & Rajapakse, A. (2024). A review of machine learning applications in power system protection and emergency control: opportunities, challenges, and future directions. Frontiers in Smart Grids, 3, 1371153. https://doi.org/10.3389/frsgr.2024.1371153
• Singla, P., Duhan, M., & Saroha, S. (2021). A comprehensive review and analysis of solar forecasting techniques. Frontiers in Energy 2021 16:2, 16(2), 187–223. https://doi.org/10.1007/S11708-021-0722-7
• Skoplaki, E., & Palyvos, J. A. (2009). On the temperature dependence of photovoltaic module electrical performance: A review of efficiency/power correlations. Solar Energy, 83(5), 614–624. https://doi.org/10.1016/J.SOLENER.2008.10.008
• Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing 2004 14:3, 14(3), 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
• Sobri, S., Koohi-Kamali, S., & Rahim, N. A. (2018). Solar photovoltaic generation forecasting methods: A review. Energy Conversion and Management, 156, 459–497. https://doi.org/10.1016/J.ENCONMAN.2017.11.019
• Wang, J., Li, P., Ran, R., Che, Y., & Zhou, Y. (2018). A Short-Term Photovoltaic Power Prediction Model Based on the Gradient Boost Decision Tree. Applied Sciences 2018, Vol. 8, Page 689, 8(5), 689. https://doi.org/10.3390/APP8050689
• Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79–82. https://doi.org/10.3354/CR030079
• Xie, R., Pan, G., Liang, C., Lin, B., & Yu, O. (2025). Research on Output Prediction Method of Large-Scale Photovoltaic Power Station Based on Gradient-Boosting Decision Trees. Processes 2025, Vol. 13, Page 477, 13(2), 477. https://doi.org/10.3390/PR13020477