Spatio-temporal graph neural networks for power prediction in offshore wind farms using SCADA data

Simon Daenens, Timothy Verstraeten, Pieter-Jan Daems, Ann Nowé, and Jan Helsen

Viewed

Total article views: 1,353 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
898	209	246	1,353	38	60

HTML: 898
PDF: 209
XML: 246
Total: 1,353
BibTeX: 38
EndNote: 60

Views and downloads (calculated since 23 Sep 2024)

Month	HTML	PDF	XML	Total
Sep 2024	74	19	3	96
Oct 2024	64	24	1	89
Nov 2024	57	29	1	87
Dec 2024	27	17	1	45
Jan 2025	37	17	2	56
Feb 2025	29	14	41	84
Mar 2025	59	10	72	141
Apr 2025	39	13	50	102
May 2025	42	13	48	103
Jun 2025	276	32	17	325
Jul 2025	194	21	10	225

Cumulative views and downloads (calculated since 23 Sep 2024)

Month	HTML	PDF	XML	Total
Sep 2024	74	19	3	96
Oct 2024	64	24	1	89
Nov 2024	57	29	1	87
Dec 2024	27	17	1	45
Jan 2025	37	17	2	56
Feb 2025	29	14	41	84
Mar 2025	59	10	72	141
Apr 2025	39	13	50	102
May 2025	42	13	48	103
Jun 2025	276	32	17	325
Jul 2025	194	21	10	225

HTML	PDF	XML	Total	BibTeX	EndNote
297	30	13	340	5	14

HTML	PDF	XML	Total	BibTeX	EndNote
601	179	233	1,013	33	46

Viewed (geographical distribution)

Total article views: 1,353 (including HTML, PDF, and XML) Thereof 1,334 with geography defined and 19 with unknown origin.

Country	#	Views	%


Total:	0
HTML:	0
PDF:	0
XML:	0


Total:	0
HTML:	0
PDF:	0
XML:	0


Total:	0
HTML:	0
PDF:	0
XML:	0

Latest update: 16 Jul 2025

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.