| The importance and future prospects of offshore wind power generation invite great efforts and investments to make it an efficient technology. A crucial aspect is the development of efficient control strategies, which in many cases require models to identify time accurately the state of the turbine at a given. These models must be simple enough not to increase the computational complexity of the control algorithm while being able to capture the nonlinearity and coupling of the wind devices. In this work, we exploit the possibility of using neural networks to identify a wind turbine control-oriented model to predict its power output. Two nonlinear autoregressive with exogenous inputs models, with different input variables, have been proposed, based on feedforward neural networks. Results are satisfactory in terms of model accuracy of an offshore 5MW WT even ruling out relevant variables. |
*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.