Probabilistic access forecasting for improved offshore operations

Ciaran Gilbert; Jethro Browell; David McMillan

doi:10.1016/j.ijforecast.2020.03.007

Probabilistic access forecasting for improved offshore operations

Ciaran Gilbert, Jethro Browell, David McMillan

Research output: Contribution to journal › Article

4 Downloads (Pure)

Abstract

Improving access is a priority in the offshore wind sector, driven by the opportunity to increase revenues, reduce costs, and improve safety at operational wind farms. This paper describes a novel method for producing probabilistic forecasts of safetycritical access conditions during crew transfers. Methods of generating density forecasts of significant wave height and peak wave period are developed and evaluated. It is found that boosted semi-parametric models outperform those estimated via maximum likelihood, as well as a non-parametric approach. Scenario forecasts of sea-state variables are generated and used as inputs to a datadriven vessel motion model, based on telemetry recorded during 700 crew transfers. This enables the production of probabilistic access forecasts of vessel motion during crew transfer up to 5 days ahead. The above methodology is implemented on a case study at a wind farm off the east coast of the UK.

Original language	English
Journal	International Journal of Forecasting
Early online date	12 May 2020
DOIs	https://doi.org/10.1016/j.ijforecast.2020.03.007
Publication status	E-pub ahead of print - 12 May 2020

Keywords

wind energy
offshore access
probabilistic forecasting
multivariate forecasting
forecast visualisation
generalised additive models

Access to Document

10.1016/j.ijforecast.2020.03.007Licence: CC BY 4.0

Gilbert-etal-IJF-2020-Probabilistic-access-forecasting-for-improved-offshore-operationsFinal published version, 1.44 MBLicence: CC BY 4.0

Fingerprint Dive into the research topics of 'Probabilistic access forecasting for improved offshore operations'. Together they form a unique fingerprint.

Profiles

Jethro Browell

jethro.browell@strath.ac.uk

Electronic And Electrical Engineering - Lecturer B
Wind Energy Systems

Person: Academic, Doctor of Philosophy

Projects

1 Finished

Offshore Renewables Accessibility for Crew transfer, Loss Estimation & Safety (ORACLES)

McMillan, D., Browell, J. & Gilbert, C.

1/02/18 → 31/01/19

Project: Research

File

Datasets

Code for: "Probabilistic Access Forecasting for Improved Offshore Operations"

Gilbert, C. (Creator), Browell, J. (Creator), McMillan, D. (Creator), University of Strathclyde, 30 Mar 2020

DOI: 10.15129/d4055a23-f2f7-482d-9cb2-4e15960b17f6, https://www.ecmwf.int/ and one more link, http://wavenet.cefas.co.uk/ (show fewer)

Dataset

Research Output

1 Conference contribution book
1 Speech
1 Conference Contribution

Access forecasting for safety-critical crew transfers in offshore environments

Browell, J., Gilbert, C. & McMillan, D., 18 Jun 2019.

Research output: Contribution to conference › Speech

A data-driven vessel motion model for offshore access forecasting

Gilbert, C., Browell, J. & McMillan, D., 19 Oct 2019, OCEANS 2019 - Marseille. Piscataway, NJ.: IEEE, 6 p. 8867176

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

Open Access

File

6 Downloads (Pure)

Visualisation of probabilistic access forecasts for offshore operations

Gilbert, C., Browell, J. & McMillan, D., 21 May 2019, In : Journal of Physics: Conference Series. 1222, 1, 9 p., 012040.

Research output: Contribution to journal › Conference Contribution

Open Access

File

1 Citation (Scopus)

5 Downloads (Pure)

Activities

1 Organiser of special symposia

Wind Energy Science conference 2019

David McMillan (Chair), Sally Shenton (Keynote/plenary speaker), Chris Briggs (Keynote/plenary speaker), James Carroll (Keynote/plenary speaker)

2019

Activity: Participating in or organising an event types › Organiser of special symposia

Cite this

Gilbert, C., Browell, J., & McMillan, D. (2020). Probabilistic access forecasting for improved offshore operations. International Journal of Forecasting. https://doi.org/10.1016/j.ijforecast.2020.03.007

@article{9ba57c0dcf79433da0de2c67d5e12fdc,

title = "Probabilistic access forecasting for improved offshore operations",

abstract = "Improving access is a priority in the offshore wind sector, driven by the opportunity to increase revenues, reduce costs, and improve safety at operational wind farms. This paper describes a novel method for producing probabilistic forecasts of safetycritical access conditions during crew transfers. Methods of generating density forecasts of significant wave height and peak wave period are developed and evaluated. It is found that boosted semi-parametric models outperform those estimated via maximum likelihood, as well as a non-parametric approach. Scenario forecasts of sea-state variables are generated and used as inputs to a datadriven vessel motion model, based on telemetry recorded during 700 crew transfers. This enables the production of probabilistic access forecasts of vessel motion during crew transfer up to 5 days ahead. The above methodology is implemented on a case study at a wind farm off the east coast of the UK.",

keywords = "wind energy, offshore access, probabilistic forecasting, multivariate forecasting, forecast visualisation, generalised additive models",

author = "Ciaran Gilbert and Jethro Browell and David McMillan",

year = "2020",

month = "5",

day = "12",

doi = "10.1016/j.ijforecast.2020.03.007",

language = "English",

journal = "International Journal of Forecasting",

issn = "0169-2070",

}

TY - JOUR

T1 - Probabilistic access forecasting for improved offshore operations

AU - Gilbert, Ciaran

AU - Browell, Jethro

AU - McMillan, David

PY - 2020/5/12

Y1 - 2020/5/12

N2 - Improving access is a priority in the offshore wind sector, driven by the opportunity to increase revenues, reduce costs, and improve safety at operational wind farms. This paper describes a novel method for producing probabilistic forecasts of safetycritical access conditions during crew transfers. Methods of generating density forecasts of significant wave height and peak wave period are developed and evaluated. It is found that boosted semi-parametric models outperform those estimated via maximum likelihood, as well as a non-parametric approach. Scenario forecasts of sea-state variables are generated and used as inputs to a datadriven vessel motion model, based on telemetry recorded during 700 crew transfers. This enables the production of probabilistic access forecasts of vessel motion during crew transfer up to 5 days ahead. The above methodology is implemented on a case study at a wind farm off the east coast of the UK.

AB - Improving access is a priority in the offshore wind sector, driven by the opportunity to increase revenues, reduce costs, and improve safety at operational wind farms. This paper describes a novel method for producing probabilistic forecasts of safetycritical access conditions during crew transfers. Methods of generating density forecasts of significant wave height and peak wave period are developed and evaluated. It is found that boosted semi-parametric models outperform those estimated via maximum likelihood, as well as a non-parametric approach. Scenario forecasts of sea-state variables are generated and used as inputs to a datadriven vessel motion model, based on telemetry recorded during 700 crew transfers. This enables the production of probabilistic access forecasts of vessel motion during crew transfer up to 5 days ahead. The above methodology is implemented on a case study at a wind farm off the east coast of the UK.

KW - wind energy

KW - offshore access

KW - probabilistic forecasting

KW - multivariate forecasting

KW - forecast visualisation

KW - generalised additive models

U2 - 10.1016/j.ijforecast.2020.03.007

DO - 10.1016/j.ijforecast.2020.03.007

M3 - Article

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

ER -