Articles | Volume 10, issue 6
https://doi.org/10.5194/wes-10-1137-2025
© 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-10-1137-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
25 Jun 2025
Research article |
| 25 Jun 2025
| 25 Jun 2025
Spatio-temporal graph neural networks for power prediction in offshore wind farms using SCADA data
OWI-Lab, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Acoustics & Vibration Research Group, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Artificial Intelligence Lab Brussels, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Timothy Verstraeten
OWI-Lab, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Acoustics & Vibration Research Group, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Artificial Intelligence Lab Brussels, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Pieter-Jan Daems
OWI-Lab, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Acoustics & Vibration Research Group, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Ann Nowé
Artificial Intelligence Lab Brussels, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Jan Helsen
OWI-Lab, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Acoustics & Vibration Research Group, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Flanders Make, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Elsene, Belgium
Viewed
Total article views: 5,459 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 23 Sep 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 4,005 | 1,103 | 351 | 5,459 | 130 | 192 |
- HTML: 4,005
- PDF: 1,103
- XML: 351
- Total: 5,459
- BibTeX: 130
- EndNote: 192
Total article views: 3,880 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 25 Jun 2025)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 3,069 | 700 | 111 | 3,880 | 79 | 98 |
- HTML: 3,069
- PDF: 700
- XML: 111
- Total: 3,880
- BibTeX: 79
- EndNote: 98
Total article views: 1,579 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 23 Sep 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 936 | 403 | 240 | 1,579 | 51 | 94 |
- HTML: 936
- PDF: 403
- XML: 240
- Total: 1,579
- BibTeX: 51
- EndNote: 94
Viewed (geographical distribution)
Total article views: 5,459 (including HTML, PDF, and XML)
Thereof 5,296 with geography defined
and 163 with unknown origin.
Total article views: 3,880 (including HTML, PDF, and XML)
Thereof 3,736 with geography defined
and 144 with unknown origin.
Total article views: 1,579 (including HTML, PDF, and XML)
Thereof 1,560 with geography defined
and 19 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
15 citations as recorded by crossref.
- Triple-Flow Dynamic Graph Convolutional Network for Wind Power Forecasting B. Li et al. https://doi.org/10.3390/sym17122026
- Abnormal Data Identification and Cleaning Techniques for Wind Turbine Systems Q. Zhang et al. https://doi.org/10.3390/en19051283
- DG-TFT-CQR: A Dynamic Graph–Temporal Fusion Transformer with Conformalized Quantile Regression for Wind Power Forecasting Y. El Bakkali et al. https://doi.org/10.3390/forecast8040055
- A Methodology for Turbine-Level Possible Power Prediction and Uncertainty Estimations Using Farm-Wide Autoregressive Information on High-Frequency Data F. Jara Ávila et al. https://doi.org/10.3390/en18143764
- A Spatio-Temporal Error-Aware Multi-Path Graph Convolutional Network for Iterative Forecasting of Wind Turbine Clusters B. Fu et al. https://doi.org/10.1007/s40998-026-01076-5
- Research and Application of a Model Selection Forecasting System for Wind Speed and Theoretical Power Generation M. Zeng et al. https://doi.org/10.3390/fi18010007
- Physics-guided multiscale fusion network for ultra-short-term wind power forecasting F. Guo et al. https://doi.org/10.1016/j.compeleceng.2026.111367
- Spatiotemporal Prediction of Wind Fields in Coastal Urban Environments Using Multi-Source Satellite Data: A GeoAI Approach Y. Shi et al. https://doi.org/10.3390/rs18050716
- SCADA-Driven big data framework for fault prediction in spiral steel pipe manufacturing using fuzzy and neural network models B. BAKHTIYAROV et al. https://doi.org/10.35784/acs_8104
- Wind Farm Performance Prediction via Graph Neural Networks with Wake-geometry-based Edge Connectivity A. Encalada-Davila et al. https://doi.org/10.1088/1742-6596/3224/6/062037
- Mechanism-aligned machine learning for membrane fouling prediction and process control in pressure-driven water treatment membranes: A review X. Yang et al. https://doi.org/10.1016/j.jwpe.2026.110543
- A Hybrid LSTM Framework for Short-Term Regional Wind Speed Forecasting Based on PCA and SSA-Optimized VMD H. Li et al. https://doi.org/10.3390/app16094225
- Forecasting of wind speed and power generation prediction using machine learning algorithms M. Rajkamal et al. https://doi.org/10.1177/09266801251412546
- A Comprehensive Review of AI-based Wind Power Forecasting Over Multiple Time Horizons I. Arrassi et al. https://doi.org/10.1007/s41660-026-00730-z
- Overview on Predictive Maintenance Techniques for Turbomachinery P. Dini et al. https://doi.org/10.3390/machines14040396
15 citations as recorded by crossref.
- Triple-Flow Dynamic Graph Convolutional Network for Wind Power Forecasting B. Li et al. https://doi.org/10.3390/sym17122026
- Abnormal Data Identification and Cleaning Techniques for Wind Turbine Systems Q. Zhang et al. https://doi.org/10.3390/en19051283
- DG-TFT-CQR: A Dynamic Graph–Temporal Fusion Transformer with Conformalized Quantile Regression for Wind Power Forecasting Y. El Bakkali et al. https://doi.org/10.3390/forecast8040055
- A Methodology for Turbine-Level Possible Power Prediction and Uncertainty Estimations Using Farm-Wide Autoregressive Information on High-Frequency Data F. Jara Ávila et al. https://doi.org/10.3390/en18143764
- A Spatio-Temporal Error-Aware Multi-Path Graph Convolutional Network for Iterative Forecasting of Wind Turbine Clusters B. Fu et al. https://doi.org/10.1007/s40998-026-01076-5
- Research and Application of a Model Selection Forecasting System for Wind Speed and Theoretical Power Generation M. Zeng et al. https://doi.org/10.3390/fi18010007
- Physics-guided multiscale fusion network for ultra-short-term wind power forecasting F. Guo et al. https://doi.org/10.1016/j.compeleceng.2026.111367
- Spatiotemporal Prediction of Wind Fields in Coastal Urban Environments Using Multi-Source Satellite Data: A GeoAI Approach Y. Shi et al. https://doi.org/10.3390/rs18050716
- SCADA-Driven big data framework for fault prediction in spiral steel pipe manufacturing using fuzzy and neural network models B. BAKHTIYAROV et al. https://doi.org/10.35784/acs_8104
- Wind Farm Performance Prediction via Graph Neural Networks with Wake-geometry-based Edge Connectivity A. Encalada-Davila et al. https://doi.org/10.1088/1742-6596/3224/6/062037
- Mechanism-aligned machine learning for membrane fouling prediction and process control in pressure-driven water treatment membranes: A review X. Yang et al. https://doi.org/10.1016/j.jwpe.2026.110543
- A Hybrid LSTM Framework for Short-Term Regional Wind Speed Forecasting Based on PCA and SSA-Optimized VMD H. Li et al. https://doi.org/10.3390/app16094225
- Forecasting of wind speed and power generation prediction using machine learning algorithms M. Rajkamal et al. https://doi.org/10.1177/09266801251412546
- A Comprehensive Review of AI-based Wind Power Forecasting Over Multiple Time Horizons I. Arrassi et al. https://doi.org/10.1007/s41660-026-00730-z
- Overview on Predictive Maintenance Techniques for Turbomachinery P. Dini et al. https://doi.org/10.3390/machines14040396
Saved (final revised paper)
Latest update: 24 Jul 2026
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.
This study presents a novel model for predicting wind turbine power output at a high temporal...
Altmetrics
Final-revised paper
Preprint