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

TL;DR

This paper presents a probabilistic multi-task learning approach for wind-farm power prediction that accounts for wake effects and spatial correlations, improving accuracy over benchmark models and enabling predictions for unobserved turbines.

Contribution

It introduces a hierarchical Bayesian metamodel that leverages spatial correlations in turbine data to enhance power prediction accuracy, including for turbines not in the training set.

Findings

The metamodel outperforms benchmark models in power prediction accuracy.

It effectively captures wake effects and spatial correlations in turbine data.

The approach enables predictions for previously unobserved turbines.

Abstract

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).