One of the most promising solutions that stands out to mitigate climate change is floating offshore wind turbines (FOWTs). Although they are very efficient in producing clean energy, the harsh environmental conditions they are subjected to, mainly strong winds and waves, produce structural fatigue and may cause them to lose efficiency. Thus, it is imperative to develop models to facilitate their deployment while maximizing energy production and ensuring the structure’s safety. This work applies machine learning (ML) techniques to obtain predictive models of the most relevant metocean variables involved. Specifically, wind speed, significant wave height, and the misalignment between wind and waves have been analyzed, pre-processed and modeled based on actual data. Linear regression (LR), support vector machines regression (SVR), Gaussian process regression (GPR) and neural network (NN)-based solutions have been applied and compared. The results show that Nonlinear autoregressive with an exogenous input neural network (NARX) is the best algorithm for both wind speed and misalignment forecasting in the time domain (72% accuracy) and GPR for wave height (90.85% accuracy). In conclusion, these models are vital to deploying and installing FOWTs and making them profitable.

No abstract

This work presents a case study of floating offshore parks in the Mediterranean Sea. There are several constraints that determinate the location of the park: the availability of a sufficient wind resource, environmental laws, sea routes, the seabed depth (what will condition the whole project), the proximity of the necessary infrastructures and a social constraint. The Mediterranean seabed depth conditions the structure of the wind farm, which consists of the selection of the most adequate platform, the configuration of the mooring lines of those platforms, the type of wind turbine to install and their layout. The calculation of the power production is based on SIMAR data set, supplied by Puertos del Estado. A study of the wake effect produced by wind turbines based on the Jensen's model has also been carried out. The power extraction system consists of three parts: a 33 kV line for the inter-array cables, an offshore substation located in the middle of the wind farm and a 220 kV line for the connection to shore. The conclusions obtained from this study are clear: this kind of projects are available in our country, and they are quite profitable if they are structured properly, though its profitability is lower than in other countries. In any case, there is still quite uncertainty concerning to that, a fact mainly motivated by the lack of a specific legislation in Spain.