A multi-timescale framework for maintenance planning at offshore wind farms

Tools

Moros, Demitri and Berrabah, Nassif and Ashton, Ian and Searle, Kit and Lazakis, Iraklis (2025) A multi-timescale framework for maintenance planning at offshore wind farms. Other. Social Science Research Network (SSRN), Amsterdam. (https://doi.org/10.2139/ssrn.5147352)

[thumbnail of Moros-etalSSRN-2025-A-multi-timescale-framework-for-maintenance-planning-at-offshore-wind-farms]
Preview
 Text. Filename: Moros-etalSSRN-2025-A-multi-timescale-framework-for-maintenance-planning-at-offshore-wind-farms.pdf
Final Published Version
License: Strathprints license 1.0
Download (764kB)| Preview

Abstract

To facilitate the continued growth of offshore wind farm developments, operations and maintenance costs, estimated at 30% of the lifetime costs of wind farms must be reduced. To help enable this reduction a framework is presented for minimising the costs, including lost revenues, of planning maintenance across tactical and operational timescales. The tactical timescale is addressed by solving a long-term job allocation problem, formulated as a mixed-integer linear program, that allocates jobs to time periods within a year. As new maintenance jobs arise and forecasts are updated the longterm job allocation problem is resolved and the maintenance teams choose a new tactical plan. A maintenance routing and scheduling problem is then solved for the jobs assigned to the relevant time period by the tactical model, producing a schedule and set of routes that the maintenance teams can use to plan their operational activities. This model is formulated as a mixed-integer linear program and adaptive large neighbourhood search meta and matheuristic solution methods are proposed for efficient computation. Computational experiments verify that the proposed metaheuristic method is able to obtain solutions on the order of minutes and offer up to 49% improvements in maintenance costs over current practices. Further computational experiments reveal that the framework, applied to a full year of historic maintenance jobs, could lead to an improvement of 66% over the historical baseline. Implementing computational methods for planning maintenance will help to reduce wind farm revenue losses and aid the work of maintenance teams.

ORCID iDs

Moros, Demitri, Berrabah, Nassif, Ashton, Ian, Searle, Kit and Lazakis, Iraklis ORCID logoORCID: https://orcid.org/0000-0002-6130-9410;
CORE (COnnecting REpositories)