Project description
Performance boost for offshore hybrid energy platforms
Floating offshore wind turbines (FOWTs) present a promising renewable energy solution for countries with high energy demands and access to deeper offshore regions rich in clean energy resources. However, their efficiency can be hampered by suboptimal platform stability. The MSCA-funded POHOWEP project seeks to address this issue by employing Oscillating Water Columns (OWCs). These OWCs serve a dual purpose: harnessing both wave and wind energy while enhancing the structural control and stability of FOWTs. The project will develop a machine learning-based control strategy and explore efficient integration and optimisation methods for these technologies.
Objective
Floating Offshore Wind Turbines (FOWTs) have become an emerging trend in wind energy development in the past few years. They offer the possibility of a clean power supply for highly populated countries with access to a deeper offshore area. The main hurdle with FOWTs is that they need to be stabilized since platform motion is undesirable. It makes the rotor aerodynamics and control more complex and reduces aerodynamic efficiency. Additionally, platform motion increases stress on the blades, rotor shaft, yaw bearing, and tower base and it can reduce the component lifespans. FOWT platform motions in pitch, roll and heave must be limited within an acceptable range. Some researchers hypothesized that the platform stabilization may decrease the need for the platform steel mass, active ballast or/and taut mooring lines.
Performance Optimization of a Hybrid Offshore Wind-Wave Energy Platform (POHOWEP) is a project which aims to (1) combine a FOWT with Oscillating Water Columns (OWCs) to harness both wave and wind energies and (2) improve the stabilization of the FOWT using the OWCs as an active structural control. The OWCs will be integrated into the floating barge platform which has not been investigated in previous research works. A Machine Learning-based control strategy will be developed to control all the Power Take-Off systems of the OWCs at once. The control of multiple OWCs on a single FOWT requires an adequate strategy that takes into account not only the plant’s state variables but external environmental conditions as well (wind speed, wave speed, wave heights, etc…). The consideration of this external data motivates the use of a Machine Learning (ML) module for the estimation and prediction problems. An ML module will help in the prediction of future wind and wave speeds and estimate the proper reference input value of the designed controllers. Many research works using ML for FOWT’s have been published and proved that ML is a promising solution.
Fields of science
- engineering and technologycivil engineeringwater engineeringocean engineering
- engineering and technologyenvironmental engineeringenergy and fuelsrenewable energywind power
- engineering and technologymechanical engineeringvehicle engineeringaerospace engineeringaeronautical engineering
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Keywords
Programme(s)
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Funding Scheme
HORIZON-TMA-MSCA-PF-GF - HORIZON TMA MSCA Postdoctoral Fellowships - Global FellowshipsCoordinator
48940 Leioa
Spain