Neural network based energy storage control for wind farms

Abstract

One of the main issues related with the wind energy systems is the unpredictable and fluctuating nature of the extracted wind power. The combinations of different types of energy storage systems and control strategies have been proposed in the literature in order to improve the power quality coming from the wind turbines. In the current paper, a novel neural network based control system is proposed for the entire wind farm with distributed storage system. Storage is integrated in every wind turbine (WT) in the wind farm and proposed control system reduces the total output power fluctuations by using the available energy storage distributed among the wind turbines in a cooperative manner. For the verification of the proposed control method a Simulink model for a wind farm containing 100 wind turbines was developed and simulated.