On Additive Gaussian Processes for Wind Farm Power Prediction

Simon M. Brealy; Lawrence A. Bull; Daniel S. Brennan; Pauline Beltrando; Anders Sommer; Nikolaos Dervilis; Keith Worden

cs.LGMar 18, 2026

On Additive Gaussian Processes for Wind Farm Power Prediction

Authors: Simon M. Brealy, Lawrence A. Bull, Daniel S. Brennan, Pauline Beltrando, Anders Sommer, Nikolaos Dervilis, Keith Worden

Organizations: Dynamics Research Group, Department of Mechanical Engineering, The University of Sheffield, Mappin Street, Sheffield, S1 3JD, UK · Computational Statistics and Machine Learning Group, Department of Engineering, University of Cambridge, Cambridge, CB3 0FA, UK · Vattenfall R&D, Vattenfall AB, Älvkarleby, Sweden

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.

Figures & tables

Panel of Figure 1 — Figure 1: Normalised data showing the power curve relationships for wind farm Ciabatta . Plot (a) shows data at the individual turbine level, whilst plot (b) shows data at the aggregate wind farm level.

Panel of Figure 2 — Figure 2: Filtered data showing the power curves for both individual turbines (a), and at the aggregate wind farm level (b)

Panel of Figure 3 — Figure 3: Filtered data showing the zonal and meridional wind speeds, coloured by power output for both an turbine X (a), and at the aggregate wind farm level (b)

Panel of Figure 4 — Figure 4: Freestream wind and summed directional component mean predictions for turbine X ( 4(a) ), turbine Y ( 4(b) ), and wind farm Ciabbata ( 4(c) ). The colours show the relative impact on the predicted power (in the transformed space)

Wind Power Forecasting

Wind power forecasting predicts turbine and farm output from operational data, weather forecasts, and remote observations to support reliable energy planning.

See all 24 papers

Latent variable models for simultaneous EOV identification and removal in population-based SHM
Aug 12, 2026M. D. Champneys, M. R. Jones, A. J. Hughes +3Latent Variable Models Structural Health Monitoring
Dynamics Research Group, University of Sheffield, Mappin Street, Sheffield S1 3JD, UK · Centre for Machine Intelligence, University of Sheffield, Mappin Street, Sheffield S1 3JD, UK
Spatio-Temporal Gaussian Process for Building Terrain-Incorporating Wind Power Curves
Jun 30, 2026Ahmadreza Chokhachian, V. Roshan Joseph, Yu DingGaussian Processes Gaussian Process Regression
H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology
Tyan-WP: A Wind Power Foundation Model for Ultra-Short-Term Probabilistic Forecasting
Jun 7, 2026Jiahui Huang, Ao Luo, Lei Liu +6Zero-Shot Time Series Forecasting Time Series Forecasting
School of Information Science and Technology, University of Science and Technology of China, Hefei, 230022, China · China Electric Power Research Institute, Beijing, 100192, China

Aug 12, 2026J/K move · Enter open · S save

Latent variable models for simultaneous EOV identification and removal in population-based SHM

M. D. Champneys, M. R. Jones, A. J. Hughes, T. J. Rogers+2

Dynamics Research Group, University of Sheffield, Mappin Street, Sheffield S1 3JD, UK · Centre for Machine Intelligence, University of Sheffield, Mappin Street, Sheffield S1 3JD, UK

Latent Variable Models Structural Health Monitoring

Open paper AskPDF arXiv

The robust treatment of environmental and operational variability (EOV) is an open challenge in population-based structural health monitoring (PBSHM). The difficulty is compounded in the case that the EOV signals are unmeasured. A common approach in conventional SHM is to apply projection-based methods that discard subspaces of healthy feature data, reasoning that the EOV signal dominates the variance of the measured features. However, a common pitfall of projection-based approaches is that when damage acts close to the same variance-dominant direction, damage sensitivity is removed along with the EOV. An alternative identifying assumption for the removal of particular unmeasured EOVs is slowness; the latent EOV process is characterised by its long temporal correlation. In this paper, the latent EOV is cast as a state-space Gaussian process, enabling tractable

\mathcal{O}(T)

inference via a Kalman filter. A robust hierarchical Bayesian identification framework is developed that enables population-level identification of latent EOVs and EOV-free residual features, using a Laplace approximation. The approach is first validated on a single laboratory-scale benchmark structure from the literature, subject to thermal EOVs, demonstrating robust damage detection and EOV recovery. The method is then applied to a simulated nine-turbine offshore wind farm with staggered deployment and damage, where it delivers a substantial true-positive uplift over projection and cointegration-based baselines at matched false-positive rates.

Abstract

Wind Power Forecasting

Explore similar work

Latent variable models for simultaneous EOV identification and removal in population-based SHM

Spatio-Temporal Gaussian Process for Building Terrain-Incorporating Wind Power Curves

Tyan-WP: A Wind Power Foundation Model for Ultra-Short-Term Probabilistic Forecasting