ePrints

Multilevel emulation for stochastic computer models with application to large offshore wind farms

Lookup NU author(s): Dr Jack Kennedy, Dr Daniel Henderson, Professor Kevin Wilson

Downloads

• Published version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

Renewable energy projects, such as large offshore wind farms, are criticalto achieving low-emission targets set by governments. Stochastic computer modelsallow us to explore future scenarios to aid decision making whilst consideringthe most relevant uncertainties. Complex stochastic computer models can be prohibitivelyslow and thus an emulator may be constructed and deployed to allow forefficient computation. We present a novel heteroscedastic Gaussian Process emulatorwhich exploits cheap approximations to a stochastic offshore wind farm simulator.We also conduct a probabilistic sensitivity analysis to understand the influence of keyparameters in the wind farm model which will help us to plan a probability elicitationin the future.

Publication metadata

Author(s): Kennedy JC, Henderson DA, Wilson KJ

Publication type: Article

Publication status: Published

Journal: Journal of the Royal Statistical Society, Series C: Applied Statistics

Year: 2023

Volume: 72

Issue: 3

Pages: 608-627

Print publication date: 01/06/2023

Online publication date: 21/03/2023

Acceptance date: 24/02/2023

Date deposited: 01/12/2022

ISSN (print): 0035-9254

ISSN (electronic): 1467-9876

Publisher: Oxford University Press

URL: https://doi.org/10.1093/jrsssc/qlad023

DOI: 10.1093/jrsssc/qlad023

Altmetrics

Funding

Share