Inter-turbine Modelling of Wind-Farm Power using Multi-task Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brealy, Simon M., Bull, Lawrence A., Beltrando, Pauline, Sommer, Anders, Dervilis, Nikolaos, Worden, Keith
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909872114630656
author Brealy, Simon M.
Bull, Lawrence A.
Beltrando, Pauline
Sommer, Anders
Dervilis, Nikolaos
Worden, Keith
author_facet Brealy, Simon M.
Bull, Lawrence A.
Beltrando, Pauline
Sommer, Anders
Dervilis, Nikolaos
Worden, Keith
contents Because of the global need to increase power production from renewable energy resources, developments in the online monitoring of the associated infrastructure is of interest to reduce operation and maintenance costs. However, challenges exist for data-driven approaches to this problem, such as incomplete or limited histories of labelled damage-state data, operational and environmental variability, or the desire for the quantification of uncertainty to support risk management. This work first introduces a probabilistic regression model for predicting wind-turbine power, which adjusts for wake effects learnt from data. Spatial correlations in the learned model parameters for different tasks (turbines) are then leveraged in a hierarchical Bayesian model (an approach to multi-task learning) to develop a "metamodel", which can be used to make power-predictions which adjust for turbine location - including on previously unobserved turbines not included in the training data. The results show that the metamodel is able to outperform a series of benchmark models, and demonstrates a novel strategy for making efficient use of data for inference in populations of structures, in particular where correlations exist in the variable(s) of interest (such as those from wind-turbine wake-effects).
format Preprint
id arxiv_https___arxiv_org_abs_2502_14527
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inter-turbine Modelling of Wind-Farm Power using Multi-task Learning
Brealy, Simon M.
Bull, Lawrence A.
Beltrando, Pauline
Sommer, Anders
Dervilis, Nikolaos
Worden, Keith
Machine Learning
Because of the global need to increase power production from renewable energy resources, developments in the online monitoring of the associated infrastructure is of interest to reduce operation and maintenance costs. However, challenges exist for data-driven approaches to this problem, such as incomplete or limited histories of labelled damage-state data, operational and environmental variability, or the desire for the quantification of uncertainty to support risk management. This work first introduces a probabilistic regression model for predicting wind-turbine power, which adjusts for wake effects learnt from data. Spatial correlations in the learned model parameters for different tasks (turbines) are then leveraged in a hierarchical Bayesian model (an approach to multi-task learning) to develop a "metamodel", which can be used to make power-predictions which adjust for turbine location - including on previously unobserved turbines not included in the training data. The results show that the metamodel is able to outperform a series of benchmark models, and demonstrates a novel strategy for making efficient use of data for inference in populations of structures, in particular where correlations exist in the variable(s) of interest (such as those from wind-turbine wake-effects).
title Inter-turbine Modelling of Wind-Farm Power using Multi-task Learning
topic Machine Learning
url https://arxiv.org/abs/2502.14527