English

On Additive Gaussian Processes for Wind Farm Power Prediction

Machine Learning 2026-03-20 v1
Authors: Simon M. Brealy , Lawrence A. Bull , Daniel S. Brennan , Pauline Beltrando , Anders Sommer , Nikolaos Dervilis , Keith Worden
View on arXiv ↗ PDF ↗ DOI ↗

Abstract

Population-based Structural Health Monitoring (PBSHM) aims to share information between similar machines or structures. This paper takes a population-level perspective, exploring the use of additive Gaussian processes to reveal variations in turbine-specific and farm-level power models over a collected wind farm dataset. The predictions illustrate patterns in wind farm power generation, which follow intuition and should enable more informed control and decision-making.

Cite

@article{arxiv.2603.18281,
  title  = {On Additive Gaussian Processes for Wind Farm Power Prediction},
  author = {Simon M. Brealy and Lawrence A. Bull and Daniel S. Brennan and Pauline Beltrando and Anders Sommer and Nikolaos Dervilis and Keith Worden},
  journal= {arXiv preprint arXiv:2603.18281},
  year   = {2026}
}

Related papers

View all related →
Artificial Intelligence · Computer Science
Towards risk-informed PBSHM: Populations as hierarchical systems
Aidan J. Hughes, Paul Gardner, Keith Worden
2023-03-27
Machine Learning · Computer Science
Anomaly Detection in Offshore Wind Turbine Structures using Hierarchical Bayesian Modelling
S. M. Smith, A. J. Hughes, T. A. Dardeno, L. A. Bull +2
2024-09-23
Machine Learning · Computer Science
Population-based wind farm monitoring based on a spatial autoregressive approach
W. Lin, K. Worden, E. J. Cross
2023-10-17
Machine Learning · Computer Science
Probabilistic Multi-Layer Perceptrons for Wind Farm Condition Monitoring
Filippo Fiocchi, Domna Ladopoulou, Petros Dellaportas
2025-11-10
Machine Learning · Computer Science
Multitask learning for improved scour detection: A dynamic wave tank study
Simon M. Brealy, Aidan J. Hughes, Tina A. Dardeno, Lawrence A. Bull +3
2024-08-30
Machine Learning · Computer Science
Physically Meaningful Uncertainty Quantification in Probabilistic Wind Turbine Power Curve Models as a Damage Sensitive Feature
J. H. Mclean, M. R. Jones, B. J. O'Connell, A. E Maguire +1
2022-10-03
Systems and Control · Electrical Eng. & Systems
Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis
Xiaopeng Li, Jiang Wu, Zhanbo Xu, Kun Liu +2
2021-10-08
Data Analysis, Statistics and Probability · Physics
A Conditional Model of Wind Power Forecast Errors and Its Application in Scenario Generation
Zhiwen Wang, Chen Shen, Feng Liu
2017-12-05
Machine Learning · Computer Science
Damage detection in operational wind turbine blades using a new approach based on machine learning
Kartik Chandrasekhar, Nevena Stevanovic, Elizabeth J. Cross, Nikolaos Dervilis +1
2021-01-29
Machine Learning · Computer Science
On an Application of Generative Adversarial Networks on Remaining Lifetime Estimation
G. Tsialiamanis, D. Wagg, N. Dervilis, K. Worden
2022-08-19
Signal Processing · Electrical Eng. & Systems
Data-Driven Structural State Estimation via Multi-Fidelity Gaussian Process Models
Yiming Fan, Fotis Kopsaftopoulos
2025-05-06
Machine Learning · Statistics
Physics-Informed Gaussian Process Regression for Probabilistic States Estimation and Forecasting in Power Grids
Tong Ma, David Alonso Barajas-Solano, Ramakrishna Tipireddy, Alexandre M. Tartakovsky
2020-10-12
Machine Learning · Statistics
On the topology and geometry of population-based SHM
Keith Worden, Tina A. Dardeno, Aidan J. Hughes, George Tsialiamanis
2024-10-03
Machine Learning · Computer Science
Quantifying the value of information transfer in population-based SHM
Aidan J. Hughes, Jack Poole, Nikolaos Dervilis, Paul Gardner +1
2023-11-07
Applications · Statistics
Directional Gaussian spatial processes for South African wind data
Jacobus S. Blom, Priyanka Nagar, Andriette Bekker
2023-11-13
Fluid Dynamics · Physics
Physics-guided machine learning for wind-farm power prediction: Toward interpretability and generalizability
Navid Zehtabiyan-Rezaie, Alexandros Iosifidis, Mahdi Abkar
2023-04-06
Systems and Control · Electrical Eng. & Systems
An Analytical Probabilistic Expression for Modeling Sum of Spatial-dependent Wind Power Output
Libao Shi, Yang Pan, Yixin Ni
2019-08-19
Machine Learning · Computer Science
Data-Driven Wind Turbine Wake Modeling via Probabilistic Machine Learning
S. Ashwin Renganathan, Romit Maulik, Stefano Letizia, Giacomo Valerio Iungo
2021-11-17
Machine Learning · Statistics
Grouped Gaussian Processes for Solar Power Prediction
Astrid Dahl, Edwin V. Bonilla
2018-12-05
Machine Learning · Computer Science
Towards an active-learning approach to resource allocation for population-based damage prognosis
George Tsialiamanis, Keith Worden, Nikolaos Dervilis, Aidan J Hughes
2024-09-30
Signal Processing · Electrical Eng. & Systems
A Distributed Probabilistic Modeling Algorithm for the Aggregated Power Forecast Error of Multiple Newly Built Wind Farms
Mengshuo Jia, Chen Shen, Zhiwen Wang
2018-12-19
Applications · Statistics
Probabilistic Wind Power Modelling via Heteroscedastic Non-Stationary Gaussian Processes
Domniki Ladopoulou, Dat Minh Hong, Petros Dellaportas
2025-11-11
Machine Learning · Statistics
Bayesian Modelling of Multivalued Power Curves from an Operational Wind Farm
L. A. Bull, P. A. Gardner, T. J. Rogers, N. Dervilis +5
2021-12-01
Machine Learning · Computer Science
A Multi-model Combination Approach for Probabilistic Wind Power Forecasting
You Lin, Ming Yang, Can Wan, Jianhui Wang +1
2017-02-14
Machine Learning · Computer Science
Modelling variability in vibration-based PBSHM via a generalised population form
Tina A Dardeno, Lawrence A Bull, Robin S Mills, Nikolaos Dervilis +1
2022-08-31
R2 v1 2026-07-01T11:27:06.763Z