Optimising floating wind turbine layouts with wake modelling and reinforcement learning

Lewis, Jack and Jia, Laibing (2024) Optimising floating wind turbine layouts with wake modelling and reinforcement learning. In: 11th PRIMaRE Conference, 2024-06-27 - 2024-06-28.

[thumbnail of Lewis-Jia-PRIMaRE-2024-Optimising-floating-wind-turbine-layouts]
Preview
 Text. Filename: Lewis-Jia-PRIMaRE-2024-Optimising-floating-wind-turbine-layouts.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (494kB)| Preview

Abstract

With 80% of offshore wind resources located at depths greater than 60m, beyond the reach of fixed-bottom turbines, the focus is increasingly on floating offshore wind technologies. This shift towards larger turbines and rotor diameters introduces complex interactions with environmental variables, which traditional simulation methods struggle to model accurately and efficiently. Our research aims to explore the application of machine learning techniques to predict and optimise the layouts of floating offshore wind farms, considering specific turbine characteristics and geographical constraints. This research will enhance our ability to design optimal layouts for floating wind farms, leading to more sustainable solutions supporting global renewable energy targets and promoting environmental stewardship.

ORCID iDs

Lewis, Jack and Jia, Laibing ORCID logoORCID: https://orcid.org/0000-0003-1327-5516;
CORE (COnnecting REpositories)