The Forecast of the Wind Turbine Generated Power Using Hybrid (LTC + XGBoost) Model
Source abstract
Abstract
This publication presents a novel approach to predicting the amount of electricity generated by wind power plants. The research focuses on data-driven models such as XGBoost, Liquid Time-constant Networks, and covers both the analysis of properties of individual forecasting models as well as aspects of their integration into a hybrid model. By analyzing real-world weather scenarios, the approach aims to identify the highest accuracy forecasting model for the short-term 24-h forecast of wind farm power output. A more accurate forecast allows for more efficient resource planning and better distribution of resources on the electricity grids, thus ensuring a greener approach to energy production. The study shows that the proposed Hybrid (XGBoost + LTC) model predicts wind power generation with an nMAE of 0.0856, representing an improvement over standalone XGBoost and LTC models, and outperforming classical approaches such as LSTM and statistical models like ARIMAX in terms of forecasting accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Solar Radiation and Photovoltaics · Electric Power System Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Applied Informatics, Kaunas University of Technology, 51368 Kaunas, Lithuania
Smart Grids and Renewable Energy Laboratory, Lithuanian Energy Institute, 44403 Kaunas, Lithuania
References (58)
Show source-provided references
1. (2025, March 28). Numerical Weather Prediction, Available online: https://www.weather.gov/media/ajk/brochures/NumericalWeatherPrediction.pdf.
2. Tsai, W.-C., Hong, C.-M., Tu, C.-S., Lin, W.-M., and Chen, C.-H. (2023). A Review of Modern Wind Power Generation Forecasting Technologies. Sustainability, 15.10.20944/preprints202304.0917.v1 ↗
3. (2025, March 29). Frontiers|Numerical Weather Prediction Correction Strategy for Short-Term Wind Power Forecasting Based on Bidirectional Gated Recurrent Unit and XGBoost. Available online: https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.836144/full.
4. Current Methods and Advances in Forecasting of Wind Power Generation10.1016/j.renene.2011.05.033 ↗
5. Linear Regression: A Predictive Modeling of Wind Direction Based on Its Speed
6. Wind Speed Forecasting Using Statistical and Machine Learning Methods: A Case Study in the UAE
7. Estimating the Wind Power by Using K-Nearest Neighbors (KNN) and Python
8. Short-Term Wind Power Forecasting Based on Support Vector Machine with Improved Dragonfly Algorithm10.1016/j.jclepro.2019.118447 ↗
9. Chen, T., and Guestrin, C. (2016, January 13). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
10. Xiong, X., Guo, X., Zeng, P., Zou, R., and Wang, X. (2022). A Short-Term Wind Power Forecast Method via XGBoost Hyper-Parameters Optimization. Front. Energy Res., 10.10.3389/fenrg.2022.905155 ↗
11. Wind Speed Forecasting Based on Extreme Gradient Boosting10.1109/ACCESS.2020.3025967 ↗
12. Dou, Y., Tan, S., and Xie, D. (2023). Comparison of Machine Learning and Statistical Methods in the Field of Renewable Energy Power Generation Forecasting: A Mini Review. Front. Energy Res., 11.10.3389/fenrg.2023.1218603 ↗
13. A Comprehensive Review on Deep Learning Approaches in Wind Forecasting Applications10.1049/cit2.12076 ↗
14. Lin, W.-H., Wang, P., Chao, K.-M., Lin, H.-C., Yang, Z.-Y., and Lai, Y.-H. (2021). Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting. Appl. Sci., 11.10.3390/app112110335 ↗
15. Lechner, M., Hasani, R.M., and Grosu, R. (2018). Neuronal Circuit Policies 2018. arXiv.
16. Belletreche, M., Bailek, N., Abotaleb, M., Bouchouicha, K., Zerouali, B., Guermoui, M., Kuriqi, A., Alharbi, A.H., Khafaga, D.S., and EL-Shimy, M. (2024). Hybrid Attention-Based Deep Neural Networks for Short-Term Wind Power Forecasting Using Meteorological Data in Desert Regions. Sci. Rep., 14.10.1038/s41598-024-73076-6 ↗
17. Ma, D., Gao, Y., and Dai, Q. (2024). LFformer: An Improved Transformer Model for Wind Power Prediction. PLoS ONE, 19.10.1371/journal.pone.0309676 ↗
18. A Novel Multi-Task Learning Model Based on Transformer-LSTM for Wind Power Forecasting10.1016/j.ijepes.2025.110732 ↗
19. Palma, G., Chengalipunath, E.S.J., and Rizzo, A. (2024). Time Series Forecasting for Energy Management: Neural Circuit Policies (NCPs) vs. Long Short-Term Memory (LSTM) Networks. Electronics, 13.10.3390/electronics13183641 ↗
20. Hasani, R., Lechner, M., Amini, A., Rus, D., and Grosu, R. (2020). Liquid Time-Constant Networks 2020. arXiv.
21. Nielsen, M.H., Yeh, C.-Y., Shen, M., and Médard, M. (2023, January 17–22). Blockage Prediction in Directional mmWave Links Using Liquid Time Constant Network 2023. Proceedings of the 2023 48th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz), Montreal, Canada.10.1109/IRMMW-THz57677.2023.10299092 ↗
22. Ultra-Short-Term Power Forecast Method for the Wind Farm Based on Feature Selection and Temporal Convolution Network10.1016/j.isatra.2022.01.024 ↗
23. CNN–LSTM–AM: A Power Prediction Model for Offshore Wind Turbines10.1016/j.oceaneng.2024.117598 ↗
24. Short-Term Offshore Wind Power Forecasting—A Hybrid Model Based on Discrete Wavelet Transform (DWT), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Deep-Learning-Based Long Short-Term Memory (LSTM)10.1016/j.renene.2021.12.100 ↗
25. Short-Term Offshore Wind Speed Forecast by Seasonal ARIMA—A Comparison against GRU and LSTM10.1016/j.energy.2021.120492 ↗
26. Multi-step Wind Power Forecast Based on VMD-LSTM10.1049/iet-rpg.2018.5781 ↗
27. A Robust Deep Learning Framework for Short-Term Wind Power Forecast of a Full-Scale Wind Farm Using Atmospheric Variables10.1016/j.energy.2021.119759 ↗
28. Enhanced Renewable Power and Load Forecasting Using RF-XGBoost Stacked Ensemble10.1007/s00202-024-02273-3 ↗
29. Cao, L., Wang, L., Huang, C., Luo, X., and Wang, J.-H. (2018, January 30). A Transfer Learning Strategy for Short-Term Wind Power Forecasting. Proceedings of the 2018 Chinese Automation Congress (CAC), Xi’an, China.10.1109/CAC.2018.8623453 ↗
30. Hybrid Neurofuzzy Wind Power Forecast and Wind Turbine Location for Embedded Generation10.1002/er.5620 ↗
31. A Regional Wind Power Probabilistic Forecast Method Based on Deep Quantile Regression10.1109/TIA.2021.3086077 ↗
32. Forecast of Daily Output Energy of Wind Turbine Using sARIMA and Nonlinear Autoregressive Models10.1177/1687814018813464 ↗
33. Leveraging LSTM-SMI and ARIMA Architecture for Robust Wind Power Plant Forecasting10.1016/j.asoc.2025.112765 ↗
34. A Generalized Framework for Reduced-order Modeling of a Wind Turbine Wake10.1002/we.2167 ↗
35. Validation of a Hybrid Modeling Approach to Floating Wind Turbine Basin Testing10.1002/we.2168 ↗
36. Predicting Wind Turbine Power Output Based on XGBoost10.1007/978-3-031-53401-0_28 ↗
37. Verma, S.M., Reddy, V., Verma, K., and Kumar, R. (2018, January 22–23). Markov Models Based Short Term Forecasting of Wind Speed for Estimating Day-Ahead Wind Power. Proceedings of the 2018 International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), Chennai, India.10.1109/ICPECTS.2018.8521645 ↗
38. A Wind Field Downscaling Strategy Based on Domain Segmentation and Transfer Functions10.1002/we.2169 ↗
39. Intermediate Layer as Measure against Rolling Bearing Creep10.1002/we.2170 ↗
40. Wind Power Forecast Based on Improved Long Short Term Memory Network10.1016/j.energy.2019.116300 ↗
41. A Hybrid Framework for Forecasting Power Generation of Multiple Renewable Energy Sources10.1016/j.rser.2022.113046 ↗
42. Assessing Stacked Physics-Informed Machine Learning Models for Co-Located Wind–Solar Power Forecasting10.1016/j.segan.2022.100943 ↗
43. An Algorithm for Forecasting Day-Ahead Wind Power via Novel Long Short-Term Memory and Wind Power Ramp Events10.1016/j.energy.2022.125888 ↗
44. Mughees, M., Li, Y., and Li, R.Y. (2024, January 3–6). From C. Elegans to Liquid Neural Networks: A Robust Wind Power Multi-Time Scale Prediction Framework 2024. Proceedings of the IECON 2024—50th Annual Conference of the IEEE Industrial Electronics Society, Chicago, IL, USA.10.1109/IECON55916.2024.10905676 ↗
45. Forecasted Scenarios of Regional Wind Farms Based on Regular Vine Copulas10.35833/MPCE.2017.000570 ↗
46. A Unified Multi-Step Wind Speed Forecasting Framework Based on Numerical Weather Prediction Grids and Wind Farm Monitoring Data10.1016/j.renene.2023.05.006 ↗
47. Hybrid VMD-CNN-GRU-Based Model for Short-Term Forecasting of Wind Power Considering Spatio-Temporal Features10.1016/j.engappai.2023.105982 ↗
48. Medium-Term Wind Power Forecasting Based on Multi-Resolution Multi-Learner Ensemble and Adaptive Model Selection10.1016/j.enconman.2020.112492 ↗
49. (2025, April 15). Day-Ahead Wind Power Forecasting Based on Wind Load Data Using Hybrid Optimization Algorithm. Available online: https://www.mdpi.com/2071-1050/13/3/1164.10.3390/su13031164 ↗
50. (2025, April 15). Hourly Day-Ahead Wind Power Prediction Using the Hybrid Model of Variational Model Decomposition and Long Short-Term Memory. Available online: https://www.mdpi.com/1996-1073/11/11/3227.10.3390/en11113227 ↗
51. An Improved Deep Belief Network Based Hybrid Forecasting Method for Wind Power10.1016/j.energy.2021.120185 ↗
52. (2025, March 29). Root-Mean-Squared Error—An Overview|ScienceDirect Topics. Available online: https://www.sciencedirect.com/topics/engineering/root-mean-squared-error.
53. Random Forests10.1023/A:1010933404324 ↗
54. (2025, March 29). Understanding Feature Importance in Machine Learning. Available online: https://builtin.com/data-science/feature-importance.
55. Feature Selection for Classification10.3233/IDA-1997-1302 ↗
56. (2025, March 29). Standard Climate Normals—Meteo.Lt. Available online: https://www.meteo.lt/en/climate/lithuanian-climate/standard-climate-normals/.
57. Wind Speed Forecasting Using Univariate and Multivariate Time Series Models10.1007/s00477-024-02881-2 ↗
58. Galvonaitė, A. (2007). Lietuvos klimatas: Monografija, Lietuvos Hidrometeorologijos Tarnyba.